Siyu Tang

Qianli Ma, Jinlong Yang, Michael J. Black et al.

Parametric 3D body models like SMPL only represent minimally-clothed people and are hard to extend to clothing because they have a fixed mesh topology and resolution. To address these limitations, recent work uses implicit surfaces or point clouds to model clothed bodies. While not limited by topology, such methods still struggle to model clothing that deviates significantly from the body, such as skirts and dresses. This is because they rely on the body to canonicalize the clothed surface by reposing it to a reference shape. Unfortunately, this process is poorly defined when clothing is far from the body. Additionally, they use linear blend skinning to pose the body and the skinning weights are tied to the underlying body parts. In contrast, we model the clothing deformation in a local coordinate space without canonicalization. We also relax the skinning weights to let multiple body parts influence the surface. Specifically, we extend point-based methods with a coarse stage, that replaces canonicalization with a learned pose-independent "coarse shape" that can capture the rough surface geometry of clothing like skirts. We then refine this using a network that infers the linear blend skinning weights and pose dependent displacements from the coarse representation. The approach works well for garments that both conform to, and deviate from, the body. We demonstrate the usefulness of our approach by learning person-specific avatars from examples and then show how they can be animated in new poses and motions. We also show that the method can learn directly from raw scans with missing data, greatly simplifying the process of creating realistic avatars. Code is available for research purposes at {\small\url{https://qianlim.github.io/SkiRT}}.

Marko Mihajlovic, Aayush Bansal, Michael Zollhoefer et al. · cmu

Image-based volumetric humans using pixel-aligned features promise generalization to unseen poses and identities. Prior work leverages global spatial encodings and multi-view geometric consistency to reduce spatial ambiguity. However, global encodings often suffer from overfitting to the distribution of the training data, and it is difficult to learn multi-view consistent reconstruction from sparse views. In this work, we investigate common issues with existing spatial encodings and propose a simple yet highly effective approach to modeling high-fidelity volumetric humans from sparse views. One of the key ideas is to encode relative spatial 3D information via sparse 3D keypoints. This approach is robust to the sparsity of viewpoints and cross-dataset domain gap. Our approach outperforms state-of-the-art methods for head reconstruction. On human body reconstruction for unseen subjects, we also achieve performance comparable to prior work that uses a parametric human body model and temporal feature aggregation. Our experiments show that a majority of errors in prior work stem from an inappropriate choice of spatial encoding and thus we suggest a new direction for high-fidelity image-based human modeling. https://markomih.github.io/KeypointNeRF

Kaifeng Zhao, Shaofei Wang, Yan Zhang et al.

Synthesizing natural interactions between virtual humans and their 3D environments is critical for numerous applications, such as computer games and AR/VR experiences. Our goal is to synthesize humans interacting with a given 3D scene controlled by high-level semantic specifications as pairs of action categories and object instances, e.g., "sit on the chair". The key challenge of incorporating interaction semantics into the generation framework is to learn a joint representation that effectively captures heterogeneous information, including human body articulation, 3D object geometry, and the intent of the interaction. To address this challenge, we design a novel transformer-based generative model, in which the articulated 3D human body surface points and 3D objects are jointly encoded in a unified latent space, and the semantics of the interaction between the human and objects are embedded via positional encoding. Furthermore, inspired by the compositional nature of interactions that humans can simultaneously interact with multiple objects, we define interaction semantics as the composition of varying numbers of atomic action-object pairs. Our proposed generative model can naturally incorporate varying numbers of atomic interactions, which enables synthesizing compositional human-scene interactions without requiring composite interaction data. We extend the PROX dataset with interaction semantic labels and scene instance segmentation to evaluate our method and demonstrate that our method can generate realistic human-scene interactions with semantic control. Our perceptual study shows that our synthesized virtual humans can naturally interact with 3D scenes, considerably outperforming existing methods. We name our method COINS, for COmpositional INteraction Synthesis with Semantic Control. Code and data are available at https://github.com/zkf1997/COINS.

Vasileios Choutas, Lea Muller, Chun-Hao P. Huang et al. · eth-zurich

While methods that regress 3D human meshes from images have progressed rapidly, the estimated body shapes often do not capture the true human shape. This is problematic since, for many applications, accurate body shape is as important as pose. The key reason that body shape accuracy lags pose accuracy is the lack of data. While humans can label 2D joints, and these constrain 3D pose, it is not so easy to "label" 3D body shape. Since paired data with images and 3D body shape are rare, we exploit two sources of information: (1) we collect internet images of diverse "fashion" models together with a small set of anthropometric measurements; (2) we collect linguistic shape attributes for a wide range of 3D body meshes and the model images. Taken together, these datasets provide sufficient constraints to infer dense 3D shape. We exploit the anthropometric measurements and linguistic shape attributes in several novel ways to train a neural network, called SHAPY, that regresses 3D human pose and shape from an RGB image. We evaluate SHAPY on public benchmarks, but note that they either lack significant body shape variation, ground-truth shape, or clothing variation. Thus, we collect a new dataset for evaluating 3D human shape estimation, called HBW, containing photos of "Human Bodies in the Wild" for which we have ground-truth 3D body scans. On this new benchmark, SHAPY significantly outperforms state-of-the-art methods on the task of 3D body shape estimation. This is the first demonstration that 3D body shape regression from images can be trained from easy-to-obtain anthropometric measurements and linguistic shape attributes. Our model and data are available at: shapy.is.tue.mpg.de

Marko Mihajlovic, Shunsuke Saito, Aayush Bansal et al. · cmu

We present a novel neural implicit representation for articulated human bodies. Compared to explicit template meshes, neural implicit body representations provide an efficient mechanism for modeling interactions with the environment, which is essential for human motion reconstruction and synthesis in 3D scenes. However, existing neural implicit bodies suffer from either poor generalization on highly articulated poses or slow inference time. In this work, we observe that prior knowledge about the human body's shape and kinematic structure can be leveraged to improve generalization and efficiency. We decompose the full-body geometry into local body parts and employ a part-aware encoder-decoder architecture to learn neural articulated occupancy that models complex deformations locally. Our local shape encoder represents the body deformation of not only the corresponding body part but also the neighboring body parts. The decoder incorporates the geometric constraints of local body shape which significantly improves pose generalization. We demonstrate that our model is suitable for resolving self-intersections and collisions with 3D environments. Quantitative and qualitative experiments show that our method largely outperforms existing solutions in terms of both efficiency and accuracy. The code and models are available at https://neuralbodies.github.io/COAP/index.html

Anpei Chen, Zexiang Xu, Xinyue Wei et al. · eth-zurich

We present Factor Fields, a novel framework for modeling and representing signals. Factor Fields decomposes a signal into a product of factors, each represented by a classical or neural field representation which operates on transformed input coordinates. This decomposition results in a unified framework that accommodates several recent signal representations including NeRF, Plenoxels, EG3D, Instant-NGP, and TensoRF. Additionally, our framework allows for the creation of powerful new signal representations, such as the "Dictionary Field" (DiF) which is a second contribution of this paper. Our experiments show that DiF leads to improvements in approximation quality, compactness, and training time when compared to previous fast reconstruction methods. Experimentally, our representation achieves better image approximation quality on 2D image regression tasks, higher geometric quality when reconstructing 3D signed distance fields, and higher compactness for radiance field reconstruction tasks. Furthermore, DiF enables generalization to unseen images/3D scenes by sharing bases across signals during training which greatly benefits use cases such as image regression from sparse observations and few-shot radiance field reconstruction.

Siwei Zhang, Qianli Ma, Yan Zhang et al.

Automatic perception of human behaviors during social interactions is crucial for AR/VR applications, and an essential component is estimation of plausible 3D human pose and shape of our social partners from the egocentric view. One of the biggest challenges of this task is severe body truncation due to close social distances in egocentric scenarios, which brings large pose ambiguities for unseen body parts. To tackle this challenge, we propose a novel scene-conditioned diffusion method to model the body pose distribution. Conditioned on the 3D scene geometry, the diffusion model generates bodies in plausible human-scene interactions, with the sampling guided by a physics-based collision score to further resolve human-scene inter-penetrations. The classifier-free training enables flexible sampling with different conditions and enhanced diversity. A visibility-aware graph convolution model guided by per-joint visibility serves as the diffusion denoiser to incorporate inter-joint dependencies and per-body-part control. Extensive evaluations show that our method generates bodies in plausible interactions with 3D scenes, achieving both superior accuracy for visible joints and diversity for invisible body parts. The code is available at https://sanweiliti.github.io/egohmr/egohmr.html.

Shaofei Wang, Katja Schwarz, Andreas Geiger et al.

Combining human body models with differentiable rendering has recently enabled animatable avatars of clothed humans from sparse sets of multi-view RGB videos. While state-of-the-art approaches achieve realistic appearance with neural radiance fields (NeRF), the inferred geometry often lacks detail due to missing geometric constraints. Further, animating avatars in out-of-distribution poses is not yet possible because the mapping from observation space to canonical space does not generalize faithfully to unseen poses. In this work, we address these shortcomings and propose a model to create animatable clothed human avatars with detailed geometry that generalize well to out-of-distribution poses. To achieve detailed geometry, we combine an articulated implicit surface representation with volume rendering. For generalization, we propose a novel joint root-finding algorithm for simultaneous ray-surface intersection search and correspondence search. Our algorithm enables efficient point sampling and accurate point canonicalization while generalizing well to unseen poses. We demonstrate that our proposed pipeline can generate clothed avatars with high-quality pose-dependent geometry and appearance from a sparse set of multi-view RGB videos. Our method achieves state-of-the-art performance on geometry and appearance reconstruction while creating animatable avatars that generalize well to out-of-distribution poses beyond the small number of training poses.

Hongwei Yi, Chun-Hao P. Huang, Dimitrios Tzionas et al.

Humans are in constant contact with the world as they move through it and interact with it. This contact is a vital source of information for understanding 3D humans, 3D scenes, and the interactions between them. In fact, we demonstrate that these human-scene interactions (HSIs) can be leveraged to improve the 3D reconstruction of a scene from a monocular RGB video. Our key idea is that, as a person moves through a scene and interacts with it, we accumulate HSIs across multiple input images, and optimize the 3D scene to reconstruct a consistent, physically plausible and functional 3D scene layout. Our optimization-based approach exploits three types of HSI constraints: (1) humans that move in a scene are occluded or occlude objects, thus, defining the depth ordering of the objects, (2) humans move through free space and do not interpenetrate objects, (3) when humans and objects are in contact, the contact surfaces occupy the same place in space. Using these constraints in an optimization formulation across all observations, we significantly improve the 3D scene layout reconstruction. Furthermore, we show that our scene reconstruction can be used to refine the initial 3D human pose and shape (HPS) estimation. We evaluate the 3D scene layout reconstruction and HPS estimation qualitatively and quantitatively using the PROX and PiGraphs datasets. The code and data are available for research purposes at https://mover.is.tue.mpg.de/.

Jonas Schult, Francis Engelmann, Alexander Hermans et al.

Modern 3D semantic instance segmentation approaches predominantly rely on specialized voting mechanisms followed by carefully designed geometric clustering techniques. Building on the successes of recent Transformer-based methods for object detection and image segmentation, we propose the first Transformer-based approach for 3D semantic instance segmentation. We show that we can leverage generic Transformer building blocks to directly predict instance masks from 3D point clouds. In our model called Mask3D each object instance is represented as an instance query. Using Transformer decoders, the instance queries are learned by iteratively attending to point cloud features at multiple scales. Combined with point features, the instance queries directly yield all instance masks in parallel. Mask3D has several advantages over current state-of-the-art approaches, since it neither relies on (1) voting schemes which require hand-selected geometric properties (such as centers) nor (2) geometric grouping mechanisms requiring manually-tuned hyper-parameters (e.g. radii) and (3) enables a loss that directly optimizes instance masks. Mask3D sets a new state-of-the-art on ScanNet test (+6.2 mAP), S3DIS 6-fold (+10.1 mAP), STPLS3D (+11.2 mAP) and ScanNet200 test (+12.4 mAP).

Marko Mihajlovic, Sergey Prokudin, Marc Pollefeys et al.

Neural fields, a category of neural networks trained to represent high-frequency signals, have gained significant attention in recent years due to their impressive performance in modeling complex 3D data, such as signed distance (SDFs) or radiance fields (NeRFs), via a single multi-layer perceptron (MLP). However, despite the power and simplicity of representing signals with an MLP, these methods still face challenges when modeling large and complex temporal signals due to the limited capacity of MLPs. In this paper, we propose an effective approach to address this limitation by incorporating temporal residual layers into neural fields, dubbed ResFields. It is a novel class of networks specifically designed to effectively represent complex temporal signals. We conduct a comprehensive analysis of the properties of ResFields and propose a matrix factorization technique to reduce the number of trainable parameters and enhance generalization capabilities. Importantly, our formulation seamlessly integrates with existing MLP-based neural fields and consistently improves results across various challenging tasks: 2D video approximation, dynamic shape modeling via temporal SDFs, and dynamic NeRF reconstruction. Lastly, we demonstrate the practical utility of ResFields by showcasing its effectiveness in capturing dynamic 3D scenes from sparse RGBD cameras of a lightweight capture system.

Taein Kwon, Bugra Tekin, Siyu Tang et al.

Temporal alignment of fine-grained human actions in videos is important for numerous applications in computer vision, robotics, and mixed reality. State-of-the-art methods directly learn image-based embedding space by leveraging powerful deep convolutional neural networks. While being straightforward, their results are far from satisfactory, the aligned videos exhibit severe temporal discontinuity without additional post-processing steps. The recent advancements in human body and hand pose estimation in the wild promise new ways of addressing the task of human action alignment in videos. In this work, based on off-the-shelf human pose estimators, we propose a novel context-aware self-supervised learning architecture to align sequences of actions. We name it CASA. Specifically, CASA employs self-attention and cross-attention mechanisms to incorporate the spatial and temporal context of human actions, which can solve the temporal discontinuity problem. Moreover, we introduce a self-supervised learning scheme that is empowered by novel 4D augmentation techniques for 3D skeleton representations. We systematically evaluate the key components of our method. Our experiments on three public datasets demonstrate CASA significantly improves phase progress and Kendall's Tau scores over the previous state-of-the-art methods.

Theodora Kontogianni, Ekin Celikkan, Siyu Tang et al.

We propose an interactive approach for 3D instance segmentation, where users can iteratively collaborate with a deep learning model to segment objects in a 3D point cloud directly. Current methods for 3D instance segmentation are generally trained in a fully-supervised fashion, which requires large amounts of costly training labels, and does not generalize well to classes unseen during training. Few works have attempted to obtain 3D segmentation masks using human interactions. Existing methods rely on user feedback in the 2D image domain. As a consequence, users are required to constantly switch between 2D images and 3D representations, and custom architectures are employed to combine multiple input modalities. Therefore, integration with existing standard 3D models is not straightforward. The core idea of this work is to enable users to interact directly with 3D point clouds by clicking on desired 3D objects of interest~(or their background) to interactively segment the scene in an open-world setting. Specifically, our method does not require training data from any target domain, and can adapt to new environments where no appropriate training sets are available. Our system continuously adjusts the object segmentation based on the user feedback and achieves accurate dense 3D segmentation masks with minimal human effort (few clicks per object). Besides its potential for efficient labeling of large-scale and varied 3D datasets, our approach, where the user directly interacts with the 3D environment, enables new applications in AR/VR and human-robot interaction.

Korrawe Karunratanakul, Sergey Prokudin, Otmar Hilliges et al.

We present HARP (HAnd Reconstruction and Personalization), a personalized hand avatar creation approach that takes a short monocular RGB video of a human hand as input and reconstructs a faithful hand avatar exhibiting a high-fidelity appearance and geometry. In contrast to the major trend of neural implicit representations, HARP models a hand with a mesh-based parametric hand model, a vertex displacement map, a normal map, and an albedo without any neural components. As validated by our experiments, the explicit nature of our representation enables a truly scalable, robust, and efficient approach to hand avatar creation. HARP is optimized via gradient descent from a short sequence captured by a hand-held mobile phone and can be directly used in AR/VR applications with real-time rendering capability. To enable this, we carefully design and implement a shadow-aware differentiable rendering scheme that is robust to high degree articulations and self-shadowing regularly present in hand motion sequences, as well as challenging lighting conditions. It also generalizes to unseen poses and novel viewpoints, producing photo-realistic renderings of hand animations performing highly-articulated motions. Furthermore, the learned HARP representation can be used for improving 3D hand pose estimation quality in challenging viewpoints. The key advantages of HARP are validated by the in-depth analyses on appearance reconstruction, novel-view and novel pose synthesis, and 3D hand pose refinement. It is an AR/VR-ready personalized hand representation that shows superior fidelity and scalability.

Sergey Prokudin, Qianli Ma, Maxime Raafat et al.

Recent years have witnessed significant progress in the field of neural surface reconstruction. While the extensive focus was put on volumetric and implicit approaches, a number of works have shown that explicit graphics primitives such as point clouds can significantly reduce computational complexity, without sacrificing the reconstructed surface quality. However, less emphasis has been put on modeling dynamic surfaces with point primitives. In this work, we present a dynamic point field model that combines the representational benefits of explicit point-based graphics with implicit deformation networks to allow efficient modeling of non-rigid 3D surfaces. Using explicit surface primitives also allows us to easily incorporate well-established constraints such as-isometric-as-possible regularisation. While learning this deformation model is prone to local optima when trained in a fully unsupervised manner, we propose to additionally leverage semantic information such as keypoint dynamics to guide the deformation learning. We demonstrate our model with an example application of creating an expressive animatable human avatar from a collection of 3D scans. Here, previous methods mostly rely on variants of the linear blend skinning paradigm, which fundamentally limits the expressivity of such models when dealing with complex cloth appearances such as long skirts. We show the advantages of our dynamic point field framework in terms of its representational power, learning efficiency, and robustness to out-of-distribution novel poses.

Ayça Takmaz, Jonas Schult, Irem Kaftan et al.

Segmenting humans in 3D indoor scenes has become increasingly important with the rise of human-centered robotics and AR/VR applications. To this end, we propose the task of joint 3D human semantic segmentation, instance segmentation and multi-human body-part segmentation. Few works have attempted to directly segment humans in cluttered 3D scenes, which is largely due to the lack of annotated training data of humans interacting with 3D scenes. We address this challenge and propose a framework for generating training data of synthetic humans interacting with real 3D scenes. Furthermore, we propose a novel transformer-based model, Human3D, which is the first end-to-end model for segmenting multiple human instances and their body-parts in a unified manner. The key advantage of our synthetic data generation framework is its ability to generate diverse and realistic human-scene interactions, with highly accurate ground truth. Our experiments show that pre-training on synthetic data improves performance on a wide variety of 3D human segmentation tasks. Finally, we demonstrate that Human3D outperforms even task-specific state-of-the-art 3D segmentation methods.

Yuanwen Yue, Anurag Das, Francis Engelmann et al.

Current visual foundation models are trained purely on unstructured 2D data, limiting their understanding of 3D structure of objects and scenes. In this work, we show that fine-tuning on 3D-aware data improves the quality of emerging semantic features. We design a method to lift semantic 2D features into an efficient 3D Gaussian representation, which allows us to re-render them for arbitrary views. Using the rendered 3D-aware features, we design a fine-tuning strategy to transfer such 3D awareness into a 2D foundation model. We demonstrate that models fine-tuned in that way produce features that readily improve downstream task performance in semantic segmentation and depth estimation through simple linear probing. Notably, though fined-tuned on a single indoor dataset, the improvement is transferable to a variety of indoor datasets and out-of-domain datasets. We hope our study encourages the community to consider injecting 3D awareness when training 2D foundation models. Project page: https://ywyue.github.io/FiT3D.

Yiming Wang, Siyu Tang, Mengyu Chu

We delve into the physics-informed neural reconstruction of smoke and obstacles through sparse-view RGB videos, tackling challenges arising from limited observation of complex dynamics. Existing physics-informed neural networks often emphasize short-term physics constraints, leaving the proper preservation of long-term conservation less explored. We introduce Neural Characteristic Trajectory Fields, a novel representation utilizing Eulerian neural fields to implicitly model Lagrangian fluid trajectories. This topology-free, auto-differentiable representation facilitates efficient flow map calculations between arbitrary frames as well as efficient velocity extraction via auto-differentiation. Consequently, it enables end-to-end supervision covering long-term conservation and short-term physics priors. Building on the representation, we propose physics-informed trajectory learning and integration into NeRF-based scene reconstruction. We enable advanced obstacle handling through self-supervised scene decomposition and seamless integrated boundary constraints. Our results showcase the ability to overcome challenges like occlusion uncertainty, density-color ambiguity, and static-dynamic entanglements. Code and sample tests are at \url{https://github.com/19reborn/PICT_smoke}.

Anpei Chen, Haofei Xu, Stefano Esposito et al.

Radiance field methods have achieved photorealistic novel view synthesis and geometry reconstruction. But they are mostly applied in per-scene optimization or small-baseline settings. While several recent works investigate feed-forward reconstruction with large baselines by utilizing transformers, they all operate with a standard global attention mechanism and hence ignore the local nature of 3D reconstruction. We propose a method that unifies local and global reasoning in transformer layers, resulting in improved quality and faster convergence. Our model represents scenes as Gaussian Volumes and combines this with an image encoder and Group Attention Layers for efficient feed-forward reconstruction. Experimental results demonstrate that our model, trained for two days on four GPUs, demonstrates high fidelity in reconstructing 360 deg radiance fields, and robustness to zero-shot and out-of-domain testing. Our project Page: https://apchenstu.github.io/LaRa/.

Marko Mihajlovic, Sergey Prokudin, Siyu Tang et al.

Digitizing 3D static scenes and 4D dynamic events from multi-view images has long been a challenge in computer vision and graphics. Recently, 3D Gaussian Splatting (3DGS) has emerged as a practical and scalable reconstruction method, gaining popularity due to its impressive reconstruction quality, real-time rendering capabilities, and compatibility with widely used visualization tools. However, the method requires a substantial number of input views to achieve high-quality scene reconstruction, introducing a significant practical bottleneck. This challenge is especially severe in capturing dynamic scenes, where deploying an extensive camera array can be prohibitively costly. In this work, we identify the lack of spatial autocorrelation of splat features as one of the factors contributing to the suboptimal performance of the 3DGS technique in sparse reconstruction settings. To address the issue, we propose an optimization strategy that effectively regularizes splat features by modeling them as the outputs of a corresponding implicit neural field. This results in a consistent enhancement of reconstruction quality across various scenarios. Our approach effectively handles static and dynamic cases, as demonstrated by extensive testing across different setups and scene complexities.

Zhiyin Qian, Siwei Zhang, Bharat Lal Bhatnagar et al.

Human motion reconstruction from monocular videos is a fundamental challenge in computer vision, with broad applications in AR/VR, robotics, and digital content creation, but remains challenging under frequent occlusions in real-world settings. Existing regression-based methods are efficient but fragile to missing observations, while optimization- and diffusion-based approaches improve robustness at the cost of slow inference speed and heavy preprocessing steps. To address these limitations, we leverage recent advances in generative masked modeling and present MoRo: Masked Modeling for human motion Recovery under Occlusions. MoRo is an occlusion-robust, end-to-end generative framework that formulates motion reconstruction as a video-conditioned task, and efficiently recover human motion in a consistent global coordinate system from RGB videos. By masked modeling, MoRo naturally handles occlusions while enabling efficient, end-to-end inference. To overcome the scarcity of paired video-motion data, we design a cross-modality learning scheme that learns multi-modal priors from a set of heterogeneous datasets: (i) a trajectory-aware motion prior trained on MoCap datasets, (ii) an image-conditioned pose prior trained on image-pose datasets, capturing diverse per-frame poses, and (iii) a video-conditioned masked transformer that fuses motion and pose priors, finetuned on video-motion datasets to integrate visual cues with motion dynamics for robust inference. Extensive experiments on EgoBody and RICH demonstrate that MoRo substantially outperforms state-of-the-art methods in accuracy and motion realism under occlusions, while performing on-par in non-occluded scenarios. MoRo achieves real-time inference at 70 FPS on a single H200 GPU.

Deheng Zhang, Jingyu Wang, Shaofei Wang et al.

In this paper, we propose a novel end-to-end relightable neural inverse rendering system that achieves high-quality reconstruction of geometry and material properties, thus enabling high-quality relighting. The cornerstone of our method is a two-stage approach for learning a better factorization of scene parameters. In the first stage, we develop a reflection-aware radiance field using a neural signed distance field (SDF) as the geometry representation and deploy an MLP (multilayer perceptron) to estimate indirect illumination. In the second stage, we introduce a novel information-sharing network structure to jointly learn the radiance field and the physically based factorization of the scene. For the physically based factorization, to reduce the noise caused by Monte Carlo sampling, we apply a split-sum approximation with a simplified Disney BRDF and cube mipmap as the environment light representation. In the relighting phase, to enhance the quality of indirect illumination, we propose a second split-sum algorithm to trace secondary rays under the split-sum rendering framework. Furthermore, there is no dataset or protocol available to quantitatively evaluate the inverse rendering performance for glossy objects. To assess the quality of material reconstruction and relighting, we have created a new dataset with ground truth BRDF parameters and relighting results. Our experiments demonstrate that our algorithm achieves state-of-the-art performance in inverse rendering and relighting, with particularly strong results in the reconstruction of highly reflective objects.

Jonas Hein, Lilian Calvet, Matthias Seibold et al.

Purpose: Accurate detection and 6D pose estimation of surgical instruments are crucial for many computer-assisted interventions. However, supervised methods lack flexibility for new or unseen tools and require extensive annotated data. This work introduces a training-free pipeline for accurate multi-view 6D pose estimation of unseen surgical instruments, which only requires a textured CAD model as prior knowledge. Methods: Our pipeline consists of two main stages. First, for detection, we generate object mask proposals in each view and score their similarity to rendered templates using a pre-trained feature extractor. Detections are matched across views, triangulated into 3D instance candidates, and filtered using multi-view geometric consistency. Second, for pose estimation, a set of pose hypotheses is iteratively refined and scored using feature-metric scores with cross-view attention. The best hypothesis undergoes a final refinement using a novel multi-view, occlusion-aware contour registration, which minimizes reprojection errors of unoccluded contour points. Results: The proposed method was rigorously evaluated on real-world surgical data from the MVPSP dataset. The method achieves millimeter-accurate pose estimates that are on par with supervised methods under controlled conditions, while maintaining full generalization to unseen instruments. These results demonstrate the feasibility of training-free, marker-less detection and tracking in surgical scenes, and highlight the unique challenges in surgical environments. Conclusion: We present a novel and flexible pipeline that effectively combines state-of-the-art foundational models, multi-view geometry, and contour-based refinement for high-accuracy 6D pose estimation of surgical instruments without task-specific training. This approach enables robust instrument tracking and scene understanding in dynamic clinical environments.

Yiming Wang, Qihang Zhang, Shengqu Cai et al.

Emerging video diffusion models achieve high visual fidelity but fundamentally couple scene dynamics with camera motion, limiting their ability to provide precise spatial and temporal control. We introduce a 4D-controllable video diffusion framework that explicitly decouples scene dynamics from camera pose, enabling fine-grained manipulation of both scene dynamics and camera viewpoint. Our framework takes continuous world-time sequences and camera trajectories as conditioning inputs, injecting them into the video diffusion model through a 4D positional encoding in the attention layer and adaptive normalizations for feature modulation. To train this model, we curate a unique dataset in which temporal and camera variations are independently parameterized; this dataset will be made public. Experiments show that our model achieves robust real-world 4D control across diverse timing patterns and camera trajectories, while preserving high generation quality and outperforming prior work in controllability. See our website for video results: https://19reborn.github.io/Bullet4D/

Yutong Chen, Yiming Wang, Xucong Zhang et al.

Recent feed-forward networks have achieved remarkable progress in sparse-view 3D reconstruction by predicting dense point maps directly from RGB images. However, they often suffer from geometric inconsistencies and limited fine-grained accuracy due to the absence of explicit multi-view constraints. We introduce the Geometry-Grounded Point Transformer (GGPT), a framework that augments feed-forward reconstruction with reliable sparse geometric guidance. We first propose an improved Structure-from-Motion pipeline based on dense feature matching and lightweight geometric optimisation to efficiently estimate accurate camera poses and partial 3D point clouds from sparse input views. Building on this foundation, we propose a geometry-guided 3D point transformer that refines dense point maps under explicit partial-geometry supervision using an optimised guidance encoding. Extensive experiments demonstrate that our method provides a principled mechanism for integrating geometric priors with dense feed-forward predictions, producing reconstructions that are both geometrically consistent and spatially complete, recovering fine structures and filling gaps in textureless areas. Trained solely on ScanNet++ with VGGT predictions, GGPT generalises across architectures and datasets, substantially outperforming state-of-the-art feed-forward 3D reconstruction models in both in-domain and out-of-domain settings.

Gen Li, Yutong Chen, Yiqian Wu et al.

Understanding multimodal signals in egocentric vision, such as RGB video, depth, camera poses, and gaze, is essential for applications in augmented reality, robotics, and human-computer interaction, enabling systems to better interpret the camera wearer's actions, intentions, and surrounding environment. However, building large-scale egocentric multimodal and multitask models presents unique challenges. Egocentric data are inherently heterogeneous, with large variations in modality coverage across devices and settings. Generating pseudo-labels for missing modalities, such as gaze or head-mounted camera trajectories, is often infeasible, making standard supervised learning approaches difficult to scale. Furthermore, dynamic camera motion and the complex temporal and spatial structure of first-person video pose additional challenges for the direct application of existing multimodal foundation models. To address these challenges, we introduce a set of efficient temporal tokenizers and propose EgoM2P, a masked modeling framework that learns from temporally-aware multimodal tokens to train a large, general-purpose model for egocentric 4D understanding. This unified design supports multitasking across diverse egocentric perception and synthesis tasks, including gaze prediction, egocentric camera tracking, and monocular depth estimation from egocentric video, and also serves as a generative model for conditional egocentric video synthesis. Across these tasks, EgoM2P matches or outperforms specialist models while being an order of magnitude faster. We will fully open-source EgoM2P to support the community and advance egocentric vision research. Project page: https://egom2p.github.io/.

Zhiyin Qian, Shaofei Wang, Marko Mihajlovic et al.

We introduce an approach that creates animatable human avatars from monocular videos using 3D Gaussian Splatting (3DGS). Existing methods based on neural radiance fields (NeRFs) achieve high-quality novel-view/novel-pose image synthesis but often require days of training, and are extremely slow at inference time. Recently, the community has explored fast grid structures for efficient training of clothed avatars. Albeit being extremely fast at training, these methods can barely achieve an interactive rendering frame rate with around 15 FPS. In this paper, we use 3D Gaussian Splatting and learn a non-rigid deformation network to reconstruct animatable clothed human avatars that can be trained within 30 minutes and rendered at real-time frame rates (50+ FPS). Given the explicit nature of our representation, we further introduce as-isometric-as-possible regularizations on both the Gaussian mean vectors and the covariance matrices, enhancing the generalization of our model on highly articulated unseen poses. Experimental results show that our method achieves comparable and even better performance compared to state-of-the-art approaches on animatable avatar creation from a monocular input, while being 400x and 250x faster in training and inference, respectively.

Siwei Zhang, Bharat Lal Bhatnagar, Yuanlu Xu et al.

We propose RoHM, an approach for robust 3D human motion reconstruction from monocular RGB(-D) videos in the presence of noise and occlusions. Most previous approaches either train neural networks to directly regress motion in 3D or learn data-driven motion priors and combine them with optimization at test time. The former do not recover globally coherent motion and fail under occlusions; the latter are time-consuming, prone to local minima, and require manual tuning. To overcome these shortcomings, we exploit the iterative, denoising nature of diffusion models. RoHM is a novel diffusion-based motion model that, conditioned on noisy and occluded input data, reconstructs complete, plausible motions in consistent global coordinates. Given the complexity of the problem -- requiring one to address different tasks (denoising and infilling) in different solution spaces (local and global motion) -- we decompose it into two sub-tasks and learn two models, one for global trajectory and one for local motion. To capture the correlations between the two, we then introduce a novel conditioning module, combining it with an iterative inference scheme. We apply RoHM to a variety of tasks -- from motion reconstruction and denoising to spatial and temporal infilling. Extensive experiments on three popular datasets show that our method outperforms state-of-the-art approaches qualitatively and quantitatively, while being faster at test time. The code is available at https://sanweiliti.github.io/ROHM/ROHM.html.

Gen Li, Kaifeng Zhao, Siwei Zhang et al.

Understanding the world in first-person view is fundamental in Augmented Reality (AR). This immersive perspective brings dramatic visual changes and unique challenges compared to third-person views. Synthetic data has empowered third-person-view vision models, but its application to embodied egocentric perception tasks remains largely unexplored. A critical challenge lies in simulating natural human movements and behaviors that effectively steer the embodied cameras to capture a faithful egocentric representation of the 3D world. To address this challenge, we introduce EgoGen, a new synthetic data generator that can produce accurate and rich ground-truth training data for egocentric perception tasks. At the heart of EgoGen is a novel human motion synthesis model that directly leverages egocentric visual inputs of a virtual human to sense the 3D environment. Combined with collision-avoiding motion primitives and a two-stage reinforcement learning approach, our motion synthesis model offers a closed-loop solution where the embodied perception and movement of the virtual human are seamlessly coupled. Compared to previous works, our model eliminates the need for a pre-defined global path, and is directly applicable to dynamic environments. Combined with our easy-to-use and scalable data generation pipeline, we demonstrate EgoGen's efficacy in three tasks: mapping and localization for head-mounted cameras, egocentric camera tracking, and human mesh recovery from egocentric views. EgoGen will be fully open-sourced, offering a practical solution for creating realistic egocentric training data and aiming to serve as a useful tool for egocentric computer vision research. Refer to our project page: https://ego-gen.github.io/.

Qianli Ma, Jinlong Yang, Siyu Tang et al.

Currently it requires an artist to create 3D human avatars with realistic clothing that can move naturally. Despite progress on 3D scanning and modeling of human bodies, there is still no technology that can easily turn a static scan into an animatable avatar. Automating the creation of such avatars would enable many applications in games, social networking, animation, and AR/VR to name a few. The key problem is one of representation. Standard 3D meshes are widely used in modeling the minimally-clothed body but do not readily capture the complex topology of clothing. Recent interest has shifted to implicit surface models for this task but they are computationally heavy and lack compatibility with existing 3D tools. What is needed is a 3D representation that can capture varied topology at high resolution and that can be learned from data. We argue that this representation has been with us all along -- the point cloud. Point clouds have properties of both implicit and explicit representations that we exploit to model 3D garment geometry on a human body. We train a neural network with a novel local clothing geometric feature to represent the shape of different outfits. The network is trained from 3D point clouds of many types of clothing, on many bodies, in many poses, and learns to model pose-dependent clothing deformations. The geometry feature can be optimized to fit a previously unseen scan of a person in clothing, enabling the scan to be reposed realistically. Our model demonstrates superior quantitative and qualitative results in both multi-outfit modeling and unseen outfit animation. The code is available for research purposes.

Qianli Ma, Shunsuke Saito, Jinlong Yang et al.

Learning to model and reconstruct humans in clothing is challenging due to articulation, non-rigid deformation, and varying clothing types and topologies. To enable learning, the choice of representation is the key. Recent work uses neural networks to parameterize local surface elements. This approach captures locally coherent geometry and non-planar details, can deal with varying topology, and does not require registered training data. However, naively using such methods to model 3D clothed humans fails to capture fine-grained local deformations and generalizes poorly. To address this, we present three key innovations: First, we deform surface elements based on a human body model such that large-scale deformations caused by articulation are explicitly separated from topological changes and local clothing deformations. Second, we address the limitations of existing neural surface elements by regressing local geometry from local features, significantly improving the expressiveness. Third, we learn a pose embedding on a 2D parameterization space that encodes posed body geometry, improving generalization to unseen poses by reducing non-local spurious correlations. We demonstrate the efficacy of our surface representation by learning models of complex clothing from point clouds. The clothing can change topology and deviate from the topology of the body. Once learned, we can animate previously unseen motions, producing high-quality point clouds, from which we generate realistic images with neural rendering. We assess the importance of each technical contribution and show that our approach outperforms the state-of-the-art methods in terms of reconstruction accuracy and inference time. The code is available for research purposes at https://qianlim.github.io/SCALE .

Leonid Pishchulin, Eldar Insafutdinov, Siyu Tang et al.

This paper considers the task of articulated human pose estimation of multiple people in real world images. We propose an approach that jointly solves the tasks of detection and pose estimation: it infers the number of persons in a scene, identifies occluded body parts, and disambiguates body parts between people in close proximity of each other. This joint formulation is in contrast to previous strategies, that address the problem by first detecting people and subsequently estimating their body pose. We propose a partitioning and labeling formulation of a set of body-part hypotheses generated with CNN-based part detectors. Our formulation, an instance of an integer linear program, implicitly performs non-maximum suppression on the set of part candidates and groups them to form configurations of body parts respecting geometric and appearance constraints. Experiments on four different datasets demonstrate state-of-the-art results for both single person and multi person pose estimation. Models and code available at http://pose.mpi-inf.mpg.de.

Rui Huang, Zhiqian Cai, Siyu Tang et al.

Modular Aerial Robot Systems (MARS) comprise multiple drone units with reconfigurable connected formations, providing high adaptability to diverse mission scenarios, fault conditions, and payload capacities. However, existing control algorithms for MARS rely on simplified quasi-static models and rule-based allocation, which generate discontinuous and unbounded motor commands. This leads to attitude error accumulation as the number of drone units scales, ultimately causing severe oscillations during docking, separation, and waypoint tracking. To address these limitations, we first design a compact mechanical system that enables passive docking, detection-free passive locking, and magnetic-assisted separation using a single micro servo. Second, we introduce a force-torque-equivalent and polytope-constraint virtual quadrotor that explicitly models feasible wrench sets. Together, these abstractions capture the full MARS dynamics and enable existing quadrotor controllers to be applied across different configurations. We further optimize the yaw angle that maximizes control authority to enhance agility. Third, building on this abstraction, we design a two-stage predictive-allocation pipeline: a constrained predictive tracker computes virtual inputs while respecting force/torque bounds, and a dynamic allocator maps these inputs to individual modules with balanced objectives to produce smooth, trackable motor commands. Simulations across over 10 configurations and real-world experiments demonstrate stable docking, locking, and separation, as well as effective control performance. To our knowledge, this is the first real-world demonstration of MARS achieving agile flight and transport with 40 deg peak pitch while maintaining an average position error of 0.0896 m. The video is available at: https://youtu.be/yqjccrIpz5o

Malte Prinzler, Paulo Gotardo, Siyu Tang et al.

We present MATCH (Multi-view Avatars from Topologically Corresponding Heads), a multi-view Gaussian registration method for high-quality head avatar creation and editing. State-of-the-art multi-view head avatar methods require time-consuming head tracking followed by expensive avatar optimization, often resulting in a total creation time of more than one day. MATCH, in contrast, directly predicts Gaussian splat textures in correspondence from calibrated multi-view images in just 0.5 seconds per frame, without requiring data preprocessing. The learned intra-subject correspondence across frames enables fast creation of personalized head avatars, while correspondence across subjects supports applications such as expression transfer, optimization-free tracking, semantic editing, and identity interpolation. We establish these correspondences end-to-end using a transformer-based model that predicts Gaussian splat textures in the fixed UV layout of a template mesh. To achieve this, we introduce a novel registration-guided attention block, where each UV-map token attends exclusively to image tokens depicting its corresponding mesh region. This design improves efficiency and performance compared to dense cross-view attention. MATCH outperforms existing methods in novel-view synthesis, geometry registration, and head avatar generation, while making avatar creation 10 times faster than the closest competing baseline. The code and model weights are available on the project website.

Korrawe Karunratanakul, Konpat Preechakul, Emre Aksan et al. · berkeley

We propose Diffusion Noise Optimization (DNO), a new method that effectively leverages existing motion diffusion models as motion priors for a wide range of motion-related tasks. Instead of training a task-specific diffusion model for each new task, DNO operates by optimizing the diffusion latent noise of an existing pre-trained text-to-motion model. Given the corresponding latent noise of a human motion, it propagates the gradient from the target criteria defined on the motion space through the whole denoising process to update the diffusion latent noise. As a result, DNO supports any use cases where criteria can be defined as a function of motion. In particular, we show that, for motion editing and control, DNO outperforms existing methods in both achieving the objective and preserving the motion content. DNO accommodates a diverse range of editing modes, including changing trajectory, pose, joint locations, or avoiding newly added obstacles. In addition, DNO is effective in motion denoising and completion, producing smooth and realistic motion from noisy and partial inputs. DNO achieves these results at inference time without the need for model retraining, offering great versatility for any defined reward or loss function on the motion representation.

Shaofei Wang, Božidar Antić, Andreas Geiger et al.

We present IntrinsicAvatar, a novel approach to recovering the intrinsic properties of clothed human avatars including geometry, albedo, material, and environment lighting from only monocular videos. Recent advancements in human-based neural rendering have enabled high-quality geometry and appearance reconstruction of clothed humans from just monocular videos. However, these methods bake intrinsic properties such as albedo, material, and environment lighting into a single entangled neural representation. On the other hand, only a handful of works tackle the problem of estimating geometry and disentangled appearance properties of clothed humans from monocular videos. They usually achieve limited quality and disentanglement due to approximations of secondary shading effects via learned MLPs. In this work, we propose to model secondary shading effects explicitly via Monte-Carlo ray tracing. We model the rendering process of clothed humans as a volumetric scattering process, and combine ray tracing with body articulation. Our approach can recover high-quality geometry, albedo, material, and lighting properties of clothed humans from a single monocular video, without requiring supervised pre-training using ground truth materials. Furthermore, since we explicitly model the volumetric scattering process and ray tracing, our model naturally generalizes to novel poses, enabling animation of the reconstructed avatar in novel lighting conditions.

Jonas Hein, Frédéric Giraud, Lilian Calvet et al.

Surgery digitalization is the process of creating a virtual replica of real-world surgery, also referred to as a surgical digital twin (SDT). It has significant applications in various fields such as education and training, surgical planning, and automation of surgical tasks. In addition, SDTs are an ideal foundation for machine learning methods, enabling the automatic generation of training data. In this paper, we present a proof of concept (PoC) for surgery digitalization that is applied to an ex-vivo spinal surgery. The proposed digitalization focuses on the acquisition and modelling of the geometry and appearance of the entire surgical scene. We employ five RGB-D cameras for dynamic 3D reconstruction of the surgeon, a high-end camera for 3D reconstruction of the anatomy, an infrared stereo camera for surgical instrument tracking, and a laser scanner for 3D reconstruction of the operating room and data fusion. We justify the proposed methodology, discuss the challenges faced and further extensions of our prototype. While our PoC partially relies on manual data curation, its high quality and great potential motivate the development of automated methods for the creation of SDTs.

Yiqian Wu, Hao Xu, Xiangjun Tang et al.

Existing neural rendering-based text-to-3D-portrait generation methods typically make use of human geometry prior and diffusion models to obtain guidance. However, relying solely on geometry information introduces issues such as the Janus problem, over-saturation, and over-smoothing. We present Portrait3D, a novel neural rendering-based framework with a novel joint geometry-appearance prior to achieve text-to-3D-portrait generation that overcomes the aforementioned issues. To accomplish this, we train a 3D portrait generator, 3DPortraitGAN-Pyramid, as a robust prior. This generator is capable of producing 360° canonical 3D portraits, serving as a starting point for the subsequent diffusion-based generation process. To mitigate the "grid-like" artifact caused by the high-frequency information in the feature-map-based 3D representation commonly used by most 3D-aware GANs, we integrate a novel pyramid tri-grid 3D representation into 3DPortraitGAN-Pyramid. To generate 3D portraits from text, we first project a randomly generated image aligned with the given prompt into the pre-trained 3DPortraitGAN-Pyramid's latent space. The resulting latent code is then used to synthesize a pyramid tri-grid. Beginning with the obtained pyramid tri-grid, we use score distillation sampling to distill the diffusion model's knowledge into the pyramid tri-grid. Following that, we utilize the diffusion model to refine the rendered images of the 3D portrait and then use these refined images as training data to further optimize the pyramid tri-grid, effectively eliminating issues with unrealistic color and unnatural artifacts. Our experimental results show that Portrait3D can produce realistic, high-quality, and canonical 3D portraits that align with the prompt.

Xiyi Chen, Marko Mihajlovic, Shaofei Wang et al.

Recent advances in generative diffusion models have enabled the previously unfeasible capability of generating 3D assets from a single input image or a text prompt. In this work, we aim to enhance the quality and functionality of these models for the task of creating controllable, photorealistic human avatars. We achieve this by integrating a 3D morphable model into the state-of-the-art multi-view-consistent diffusion approach. We demonstrate that accurate conditioning of a generative pipeline on the articulated 3D model enhances the baseline model performance on the task of novel view synthesis from a single image. More importantly, this integration facilitates a seamless and accurate incorporation of facial expression and body pose control into the generation process. To the best of our knowledge, our proposed framework is the first diffusion model to enable the creation of fully 3D-consistent, animatable, and photorealistic human avatars from a single image of an unseen subject; extensive quantitative and qualitative evaluations demonstrate the advantages of our approach over existing state-of-the-art avatar creation models on both novel view and novel expression synthesis tasks. The code for our project is publicly available.

Shaofei Wang, Tomas Simon, Igor Santesteban et al.

We propose Relightable Full-Body Gaussian Codec Avatars, a new approach for modeling relightable full-body avatars with fine-grained details including face and hands. The unique challenge for relighting full-body avatars lies in the large deformations caused by body articulation and the resulting impact on appearance caused by light transport. Changes in body pose can dramatically change the orientation of body surfaces with respect to lights, resulting in both local appearance changes due to changes in local light transport functions, as well as non-local changes due to occlusion between body parts. To address this, we decompose the light transport into local and non-local effects. Local appearance changes are modeled using learnable zonal harmonics for diffuse radiance transfer. Unlike spherical harmonics, zonal harmonics are highly efficient to rotate under articulation. This allows us to learn diffuse radiance transfer in a local coordinate frame, which disentangles the local radiance transfer from the articulation of the body. To account for non-local appearance changes, we introduce a shadow network that predicts shadows given precomputed incoming irradiance on a base mesh. This facilitates the learning of non-local shadowing between the body parts. Finally, we use a deferred shading approach to model specular radiance transfer and better capture reflections and highlights such as eye glints. We demonstrate that our approach successfully models both the local and non-local light transport required for relightable full-body avatars, with a superior generalization ability under novel illumination conditions and unseen poses.

Francis Engelmann, Ayca Takmaz, Jonas Schult et al.

This report provides an overview of the challenge hosted at the OpenSUN3D Workshop on Open-Vocabulary 3D Scene Understanding held in conjunction with ICCV 2023. The goal of this workshop series is to provide a platform for exploration and discussion of open-vocabulary 3D scene understanding tasks, including but not limited to segmentation, detection and mapping. We provide an overview of the challenge hosted at the workshop, present the challenge dataset, the evaluation methodology, and brief descriptions of the winning methods. For additional details, please see https://opensun3d.github.io/index_iccv23.html.

Theodora Kontogianni, Yuanwen Yue, Siyu Tang et al.

Despite continual learning's long and well-established academic history, its application in real-world scenarios remains rather limited. This paper contends that this gap is attributable to a misalignment between the actual challenges of continual learning and the evaluation protocols in use, rendering proposed solutions ineffective for addressing the complexities of real-world setups. We validate our hypothesis and assess progress to date, using a new 3D semantic segmentation benchmark, OCL-3DSS. We investigate various continual learning schemes from the literature by utilizing more realistic protocols that necessitate online and continual learning for dynamic, real-world scenarios (eg., in robotics and 3D vision applications). The outcomes are sobering: all considered methods perform poorly, significantly deviating from the upper bound of joint offline training. This raises questions about the applicability of existing methods in realistic settings. Our paper aims to initiate a paradigm shift, advocating for the adoption of continual learning methods through new experimental protocols that better emulate real-world conditions to facilitate breakthroughs in the field.

Yan Wu, Korrawe Karunratanakul, Zhengyi Luo et al.

Generating natural and physically plausible character motion remains challenging, particularly for long-horizon control with diverse guidance signals. While prior work combines high-level diffusion-based motion planners with low-level physics controllers, these systems suffer from domain gaps that degrade motion quality and require task-specific fine-tuning. To tackle this problem, we introduce UniPhys, a diffusion-based behavior cloning framework that unifies motion planning and control into a single model. UniPhys enables flexible, expressive character motion conditioned on multi-modal inputs such as text, trajectories, and goals. To address accumulated prediction errors over long sequences, UniPhys is trained with the Diffusion Forcing paradigm, learning to denoise noisy motion histories and handle discrepancies introduced by the physics simulator. This design allows UniPhys to robustly generate physically plausible, long-horizon motions. Through guided sampling, UniPhys generalizes to a wide range of control signals, including unseen ones, without requiring task-specific fine-tuning. Experiments show that UniPhys outperforms prior methods in motion naturalness, generalization, and robustness across diverse control tasks.

Yutong Chen, Marko Mihajlovic, Xiyi Chen et al.

3D Gaussian Splatting (3DGS) has recently transformed photorealistic reconstruction, achieving high visual fidelity and real-time performance. However, rendering quality significantly deteriorates when test views deviate from the camera angles used during training, posing a major challenge for applications in immersive free-viewpoint rendering and navigation. In this work, we conduct a comprehensive evaluation of 3DGS and related novel view synthesis methods under out-of-distribution (OOD) test camera scenarios. By creating diverse test cases with synthetic and real-world datasets, we demonstrate that most existing methods, including those incorporating various regularization techniques and data-driven priors, struggle to generalize effectively to OOD views. To address this limitation, we introduce SplatFormer, the first point transformer model specifically designed to operate on Gaussian splats. SplatFormer takes as input an initial 3DGS set optimized under limited training views and refines it in a single forward pass, effectively removing potential artifacts in OOD test views. To our knowledge, this is the first successful application of point transformers directly on 3DGS sets, surpassing the limitations of previous multi-scene training methods, which could handle only a restricted number of input views during inference. Our model significantly improves rendering quality under extreme novel views, achieving state-of-the-art performance in these challenging scenarios and outperforming various 3DGS regularization techniques, multi-scene models tailored for sparse view synthesis, and diffusion-based frameworks.

Chia-Wen Chen, Yan Wu, Korrawe Karunratanakul et al.

Achieving precise, versatile whole-body character control in physics-based animation remains challenging. Recent diffusion-based policies generate rich and expressive motions but typically rely on gradient-based test-time guidance to satisfy task objectives, which is slow and can reduce robustness. We introduce NaP-Control (Navigating Diffusion Prior for Versatile and Fast Character Control), abbreviated as NaP. Our method uses reinforcement learning to manipulate the latent noise of a task-agnostic diffusion policy prior, steering it toward task-specific behaviors for fast, robust control with high motion fidelity. In contrast to methods that rely solely on offline training, NaP interacts with the environment during training to correct motions and optimize task rewards, improving success rates and enabling adaptation to challenging scenarios. By directly predicting task-optimized diffusion noise, NaP eliminates iterative guidance during denoising and enables efficient inference. Experiments show that NaP attains higher success rates and faster inference while preserving natural motion across diverse tasks.

Rui Wang, Quentin Lohmeyer, Mirko Meboldt et al.

Reconstructing clean, distractor-free 3D scenes from real-world captures remains a significant challenge, particularly in highly dynamic and cluttered settings such as egocentric videos. To tackle this problem, we introduce DeGauss, a simple and robust self-supervised framework for dynamic scene reconstruction based on a decoupled dynamic-static Gaussian Splatting design. DeGauss models dynamic elements with foreground Gaussians and static content with background Gaussians, using a probabilistic mask to coordinate their composition and enable independent yet complementary optimization. DeGauss generalizes robustly across a wide range of real-world scenarios, from casual image collections to long, dynamic egocentric videos, without relying on complex heuristics or extensive supervision. Experiments on benchmarks including NeRF-on-the-go, ADT, AEA, Hot3D, and EPIC-Fields demonstrate that DeGauss consistently outperforms existing methods, establishing a strong baseline for generalizable, distractor-free 3D reconstructionin highly dynamic, interaction-rich environments. Project page: https://batfacewayne.github.io/DeGauss.io/

Zinuo You, Stamatios Georgoulis, Anpei Chen et al.

Video stabilization is pivotal for video processing, as it removes unwanted shakiness while preserving the original user motion intent. Existing approaches, depending on the domain they operate, suffer from several issues (e.g. geometric distortions, excessive cropping, poor generalization) that degrade the user experience. To address these issues, we introduce \textbf{GaVS}, a novel 3D-grounded approach that reformulates video stabilization as a temporally-consistent `local reconstruction and rendering' paradigm. Given 3D camera poses, we augment a reconstruction model to predict Gaussian Splatting primitives, and finetune it at test-time, with multi-view dynamics-aware photometric supervision and cross-frame regularization, to produce temporally-consistent local reconstructions. The model are then used to render each stabilized frame. We utilize a scene extrapolation module to avoid frame cropping. Our method is evaluated on a repurposed dataset, instilled with 3D-grounded information, covering samples with diverse camera motions and scene dynamics. Quantitatively, our method is competitive with or superior to state-of-the-art 2D and 2.5D approaches in terms of conventional task metrics and new geometry consistency. Qualitatively, our method produces noticeably better results compared to alternatives, validated by the user study.

Yiming Wang, Lucy Chai, Xuan Luo et al.

We study the problem of novel view streaming from sparse-view videos, which aims to generate a continuous sequence of high-quality, temporally consistent novel views as new input frames arrive. However, existing novel view synthesis methods struggle with temporal coherence and visual fidelity, leading to flickering and inconsistency. To address these challenges, we introduce history-awareness, leveraging previous frames to reconstruct the scene and improve quality and stability. We propose a hybrid splat-voxel feed-forward scene reconstruction approach that combines Gaussian Splatting to propagate information over time, with a hierarchical voxel grid for temporal fusion. Gaussian primitives are efficiently warped over time using a motion graph that extends 2D tracking models to 3D motion, while a sparse voxel transformer integrates new temporal observations in an error-aware manner. Crucially, our method does not require training on multi-view video datasets, which are currently limited in size and diversity, and can be directly applied to sparse-view video streams in a history-aware manner at inference time. Our approach achieves state-of-the-art performance in both static and streaming scene reconstruction, effectively reducing temporal artifacts and visual artifacts while running at interactive rates (15 fps with 350ms delay) on a single H100 GPU. Project Page: https://19reborn.github.io/SplatVoxel/

Yiming Wang, Shaofei Wang, Marko Mihajlovic et al.

3D Gaussian Splatting (3DGS) has emerged as a leading approach for high-quality novel view synthesis, with numerous variants extending its applicability to a broad spectrum of 3D and 4D scene reconstruction tasks. Despite its success, the representational capacity of 3DGS remains limited by the use of 3D Gaussian kernels to model local variations. Recent works have proposed to augment 3DGS with additional per-primitive capacity, such as per-splat textures, to enhance its expressiveness. However, these per-splat texture approaches primarily target dense novel view synthesis with a reduced number of Gaussian primitives, and their effectiveness tends to diminish when applied to more general reconstruction scenarios. In this paper, we aim to achieve concrete performance improvement over state-of-the-art 3DGS variants across a wide range of reconstruction tasks, including novel view synthesis, geometry and dynamic reconstruction, under both sparse and dense input settings. To this end, we introduce Neural Texture Splatting (NTS). At the core of our approach is a global neural field (represented as a hybrid of a tri-plane and a neural decoder) that predicts local appearance and geometric fields for each primitive. By leveraging this shared global representation that models local texture fields across primitives, we significantly reduce model size and facilitate efficient global information exchange, demonstrating strong generalization across tasks. Furthermore, our neural modeling of local texture fields introduces expressive view- and time-dependent effects, a critical aspect that existing methods fail to account for. Extensive experiments show that Neural Texture Splatting consistently improves models and achieves state-of-the-art results across multiple benchmarks.

Frano Rajič, Haofei Xu, Marko Mihajlovic et al.

We introduce the first data-driven multi-view 3D point tracker, designed to track arbitrary points in dynamic scenes using multiple camera views. Unlike existing monocular trackers, which struggle with depth ambiguities and occlusion, or prior multi-camera methods that require over 20 cameras and tedious per-sequence optimization, our feed-forward model directly predicts 3D correspondences using a practical number of cameras (e.g., four), enabling robust and accurate online tracking. Given known camera poses and either sensor-based or estimated multi-view depth, our tracker fuses multi-view features into a unified point cloud and applies k-nearest-neighbors correlation alongside a transformer-based update to reliably estimate long-range 3D correspondences, even under occlusion. We train on 5K synthetic multi-view Kubric sequences and evaluate on two real-world benchmarks: Panoptic Studio and DexYCB, achieving median trajectory errors of 3.1 cm and 2.0 cm, respectively. Our method generalizes well to diverse camera setups of 1-8 views with varying vantage points and video lengths of 24-150 frames. By releasing our tracker alongside training and evaluation datasets, we aim to set a new standard for multi-view 3D tracking research and provide a practical tool for real-world applications. Project page available at https://ethz-vlg.github.io/mvtracker.