Srinath Sridhar

Aditya Sanghi, Rao Fu, Vivian Liu et al. · stanford

Recent works have demonstrated that natural language can be used to generate and edit 3D shapes. However, these methods generate shapes with limited fidelity and diversity. We introduce CLIP-Sculptor, a method to address these constraints by producing high-fidelity and diverse 3D shapes without the need for (text, shape) pairs during training. CLIP-Sculptor achieves this in a multi-resolution approach that first generates in a low-dimensional latent space and then upscales to a higher resolution for improved shape fidelity. For improved shape diversity, we use a discrete latent space which is modeled using a transformer conditioned on CLIP's image-text embedding space. We also present a novel variant of classifier-free guidance, which improves the accuracy-diversity trade-off. Finally, we perform extensive experiments demonstrating that CLIP-Sculptor outperforms state-of-the-art baselines. The code is available at https://ivl.cs.brown.edu/#/projects/clip-sculptor.

Qiuhong Anna Wei, Sijie Ding, Jeong Joon Park et al. · stanford

Humans universally dislike the task of cleaning up a messy room. If machines were to help us with this task, they must understand human criteria for regular arrangements, such as several types of symmetry, co-linearity or co-circularity, spacing uniformity in linear or circular patterns, and further inter-object relationships that relate to style and functionality. Previous approaches for this task relied on human input to explicitly specify goal state, or synthesized scenes from scratch -- but such methods do not address the rearrangement of existing messy scenes without providing a goal state. In this paper, we present LEGO-Net, a data-driven transformer-based iterative method for LEarning reGular rearrangement of Objects in messy rooms. LEGO-Net is partly inspired by diffusion models -- it starts with an initial messy state and iteratively ''de-noises'' the position and orientation of objects to a regular state while reducing distance traveled. Given randomly perturbed object positions and orientations in an existing dataset of professionally-arranged scenes, our method is trained to recover a regular re-arrangement. Results demonstrate that our method is able to reliably rearrange room scenes and outperform other methods. We additionally propose a metric for evaluating regularity in room arrangements using number-theoretic machinery.

Rao Fu, Xiao Zhan, Yiwen Chen et al. · stanford

We present ShapeCrafter, a neural network for recursive text-conditioned 3D shape generation. Existing methods to generate text-conditioned 3D shapes consume an entire text prompt to generate a 3D shape in a single step. However, humans tend to describe shapes recursively-we may start with an initial description and progressively add details based on intermediate results. To capture this recursive process, we introduce a method to generate a 3D shape distribution, conditioned on an initial phrase, that gradually evolves as more phrases are added. Since existing datasets are insufficient for training this approach, we present Text2Shape++, a large dataset of 369K shape-text pairs that supports recursive shape generation. To capture local details that are often used to refine shape descriptions, we build on top of vector-quantized deep implicit functions that generate a distribution of high-quality shapes. Results show that our method can generate shapes consistent with text descriptions, and shapes evolve gradually as more phrases are added. Our method supports shape editing, extrapolation, and can enable new applications in human-machine collaboration for creative design.

Ankit Dhiman, Srinath R, Harsh Rangwani et al. · stanford

Neural Radiance Field (NeRF) approaches learn the underlying 3D representation of a scene and generate photo-realistic novel views with high fidelity. However, most proposed settings concentrate on modelling a single object or a single level of a scene. However, in the real world, we may capture a scene at multiple levels, resulting in a layered capture. For example, tourists usually capture a monument's exterior structure before capturing the inner structure. Modelling such scenes in 3D with seamless switching between levels can drastically improve immersive experiences. However, most existing techniques struggle in modelling such scenes. We propose Strata-NeRF, a single neural radiance field that implicitly captures a scene with multiple levels. Strata-NeRF achieves this by conditioning the NeRFs on Vector Quantized (VQ) latent representations which allow sudden changes in scene structure. We evaluate the effectiveness of our approach in multi-layered synthetic dataset comprising diverse scenes and then further validate its generalization on the real-world RealEstate10K dataset. We find that Strata-NeRF effectively captures stratified scenes, minimizes artifacts, and synthesizes high-fidelity views compared to existing approaches.

Bipasha Sen, Gaurav Singh, Aditya Agarwal et al. · mila, mit

Neural Radiance Fields (NeRF) have become an increasingly popular representation to capture high-quality appearance and shape of scenes and objects. However, learning generalizable NeRF priors over categories of scenes or objects has been challenging due to the high dimensionality of network weight space. To address the limitations of existing work on generalization, multi-view consistency and to improve quality, we propose HyP-NeRF, a latent conditioning method for learning generalizable category-level NeRF priors using hypernetworks. Rather than using hypernetworks to estimate only the weights of a NeRF, we estimate both the weights and the multi-resolution hash encodings resulting in significant quality gains. To improve quality even further, we incorporate a denoise and finetune strategy that denoises images rendered from NeRFs estimated by the hypernetwork and finetunes it while retaining multiview consistency. These improvements enable us to use HyP-NeRF as a generalizable prior for multiple downstream tasks including NeRF reconstruction from single-view or cluttered scenes and text-to-NeRF. We provide qualitative comparisons and evaluate HyP-NeRF on three tasks: generalization, compression, and retrieval, demonstrating our state-of-the-art results.

Yiqing Liang, Eliot Laidlaw, Alexander Meyerowitz et al. · stanford

From video, we reconstruct a neural volume that captures time-varying color, density, scene flow, semantics, and attention information. The semantics and attention let us identify salient foreground objects separately from the background across spacetime. To mitigate low resolution semantic and attention features, we compute pyramids that trade detail with whole-image context. After optimization, we perform a saliency-aware clustering to decompose the scene. To evaluate real-world scenes, we annotate object masks in the NVIDIA Dynamic Scene and DyCheck datasets. We demonstrate that this method can decompose dynamic scenes in an unsupervised way with competitive performance to a supervised method, and that it improves foreground/background segmentation over recent static/dynamic split methods. Project Webpage: https://visual.cs.brown.edu/saff

Xianghao Xu, Yifan Ruan, Srinath Sridhar et al. · stanford

3D models of manufactured objects are important for populating virtual worlds and for synthetic data generation for vision and robotics. To be most useful, such objects should be articulated: their parts should move when interacted with. While articulated object datasets exist, creating them is labor-intensive. Learning-based prediction of part motions can help, but all existing methods require annotated training data. In this paper, we present an unsupervised approach for discovering articulated motions in a part-segmented 3D shape collection. Our approach is based on a concept we call category closure: any valid articulation of an object's parts should keep the object in the same semantic category (e.g. a chair stays a chair). We operationalize this concept with an algorithm that optimizes a shape's part motion parameters such that it can transform into other shapes in the collection. We evaluate our approach by using it to re-discover part motions from the PartNet-Mobility dataset. For almost all shape categories, our method's predicted motion parameters have low error with respect to ground truth annotations, outperforming two supervised motion prediction methods.

Bipasha Sen, Aditya Agarwal, Gaurav Singh et al. · mila, mit

Recovering full 3D shapes from partial observations is a challenging task that has been extensively addressed in the computer vision community. Many deep learning methods tackle this problem by training 3D shape generation networks to learn a prior over the full 3D shapes. In this training regime, the methods expect the inputs to be in a fixed canonical form, without which they fail to learn a valid prior over the 3D shapes. We propose SCARP, a model that performs Shape Completion in ARbitrary Poses. Given a partial pointcloud of an object, SCARP learns a disentangled feature representation of pose and shape by relying on rotationally equivariant pose features and geometric shape features trained using a multi-tasking objective. Unlike existing methods that depend on an external canonicalization, SCARP performs canonicalization, pose estimation, and shape completion in a single network, improving the performance by 45% over the existing baselines. In this work, we use SCARP for improving grasp proposals on tabletop objects. By completing partial tabletop objects directly in their observed poses, SCARP enables a SOTA grasp proposal network improve their proposals by 71.2% on partial shapes. Project page: https://bipashasen.github.io/scarp

Cheng-You Lu, Peisen Zhou, Angela Xing et al. · stanford

Advances in neural fields are enabling high-fidelity capture of the shape and appearance of dynamic 3D scenes. However, their capabilities lag behind those offered by conventional representations such as 2D videos because of algorithmic challenges and the lack of large-scale multi-view real-world datasets. We address the dataset limitation with DiVa-360, a real-world 360 dynamic visual dataset that contains synchronized high-resolution and long-duration multi-view video sequences of table-scale scenes captured using a customized low-cost system with 53 cameras. It contains 21 object-centric sequences categorized by different motion types, 25 intricate hand-object interaction sequences, and 8 long-duration sequences for a total of 17.4 M image frames. In addition, we provide foreground-background segmentation masks, synchronized audio, and text descriptions. We benchmark the state-of-the-art dynamic neural field methods on DiVa-360 and provide insights about existing methods and future challenges on long-duration neural field capture.

Rohith Agaram, Shaurya Dewan, Rahul Sajnani et al. · stanford

Coordinate-based implicit neural networks, or neural fields, have emerged as useful representations of shape and appearance in 3D computer vision. Despite advances, however, it remains challenging to build neural fields for categories of objects without datasets like ShapeNet that provide "canonicalized" object instances that are consistently aligned for their 3D position and orientation (pose). We present Canonical Field Network (CaFi-Net), a self-supervised method to canonicalize the 3D pose of instances from an object category represented as neural fields, specifically neural radiance fields (NeRFs). CaFi-Net directly learns from continuous and noisy radiance fields using a Siamese network architecture that is designed to extract equivariant field features for category-level canonicalization. During inference, our method takes pre-trained neural radiance fields of novel object instances at arbitrary 3D pose and estimates a canonical field with consistent 3D pose across the entire category. Extensive experiments on a new dataset of 1300 NeRF models across 13 object categories show that our method matches or exceeds the performance of 3D point cloud-based methods.

Trevor Houchens, Cheng-You Lu, Shivam Duggal et al. · stanford

In visual computing, 3D geometry is represented in many different forms including meshes, point clouds, voxel grids, level sets, and depth images. Each representation is suited for different tasks thus making the transformation of one representation into another (forward map) an important and common problem. We propose Omnidirectional Distance Fields (ODFs), a new 3D shape representation that encodes geometry by storing the depth to the object's surface from any 3D position in any viewing direction. Since rays are the fundamental unit of an ODF, it can be used to easily transform to and from common 3D representations like meshes or point clouds. Different from level set methods that are limited to representing closed surfaces, ODFs are unsigned and can thus model open surfaces (e.g., garments). We demonstrate that ODFs can be effectively learned with a neural network (NeuralODF) despite the inherent discontinuities at occlusion boundaries. We also introduce efficient forward mapping algorithms for transforming ODFs to and from common 3D representations. Specifically, we introduce an efficient Jumping Cubes algorithm for generating meshes from ODFs. Experiments demonstrate that NeuralODF can learn to capture high-quality shape by overfitting to a single object, and also learn to generalize on common shape categories.

Xiaoyan Cong, Zekun Li, Zhiyang Dou et al.

Large-scale foundation models (LFMs) have recently made impressive progress in text-to-motion generation by learning strong generative priors from massive 3D human motion datasets and paired text descriptions. However, how to effectively and efficiently leverage such single-purpose motion LFMs, i.e., text-to-motion synthesis, in more diverse cross-modal and in-context motion generation downstream tasks remains largely unclear. Prior work typically adapts pretrained generative priors to individual downstream tasks in a task-specific manner. In contrast, our goal is to unlock such priors to support a broad spectrum of downstream motion generation tasks within a single unified framework. To bridge this gap, we present UMO, a simple yet general unified formulation that casts diverse downstream tasks into compositions of atomic per-frame operations, enabling in-context adaptation to unlock the generative priors of pretrained DiT-based motion LFMs. Specifically, UMO introduces three learnable frame-level meta-operation embeddings to specify per-frame intent and employs lightweight temporal fusion to inject in-context cues into the pretrained backbone, with negligible runtime overhead compared to the base model. With this design, UMO finetunes the pretrained model, originally limited to text-to-motion generation, to support diverse previously unsupported tasks, including temporal inpainting, text-guided motion editing, text-serialized geometric constraints, and multi-identity reaction generation. Experiments demonstrate that UMO consistently outperforms task-specific and training-free baselines across a wide range of benchmarks, despite using a single unified model. Code and model will be publicly available. Project Page: https://oliver-cong02.github.io/UMO.github.io/

Aashish Rai, Angela Xing, Anushka Agarwal et al.

Volumetric videos offer immersive 4D experiences, but remain difficult to reconstruct, store, and stream at scale. Existing Gaussian Splatting based methods achieve high-quality reconstruction but break down on long sequences, temporal inconsistency, and fail under large motions and disocclusions. Moreover, their outputs are typically incompatible with conventional video coding pipelines, preventing practical applications. We introduce PackUV, a novel 4D Gaussian representation that maps all Gaussian attributes into a sequence of structured, multi-scale UV atlas, enabling compact, image-native storage. To fit this representation from multi-view videos, we propose PackUV-GS, a temporally consistent fitting method that directly optimizes Gaussian parameters in the UV domain. A flow-guided Gaussian labeling and video keyframing module identifies dynamic Gaussians, stabilizes static regions, and preserves temporal coherence even under large motions and disocclusions. The resulting UV atlas format is the first unified volumetric video representation compatible with standard video codecs (e.g., FFV1) without losing quality, enabling efficient streaming within existing multimedia infrastructure. To evaluate long-duration volumetric capture, we present PackUV-2B, the largest multi-view video dataset to date, featuring more than 50 synchronized cameras, substantial motion, and frequent disocclusions across 100 sequences and 2B (billion) frames. Extensive experiments demonstrate that our method surpasses existing baselines in rendering fidelity while scaling to sequences up to 30 minutes with consistent quality.

Aashish Rai, Srinath Sridhar

We introduce EgoSonics, a method to generate semantically meaningful and synchronized audio tracks conditioned on silent egocentric videos. Generating audio for silent egocentric videos could open new applications in virtual reality, assistive technologies, or for augmenting existing datasets. Existing work has been limited to domains like speech, music, or impact sounds and cannot capture the broad range of audio frequencies found in egocentric videos. EgoSonics addresses these limitations by building on the strengths of latent diffusion models for conditioned audio synthesis. We first encode and process paired audio-video data to make them suitable for generation. The encoded data is then used to train a model that can generate an audio track that captures the semantics of the input video. Our proposed SyncroNet builds on top of ControlNet to provide control signals that enables generation of temporally synchronized audio. Extensive evaluations and a comprehensive user study show that our model outperforms existing work in audio quality, and in our proposed synchronization evaluation method. Furthermore, we demonstrate downstream applications of our model in improving video summarization.

Zekun Li, Sizhe An, Chengcheng Tang et al.

Recent progress in large models has led to significant advances in unified multimodal generation and understanding. However, the development of models that unify motion-language generation and understanding remains largely underexplored. Existing approaches often fine-tune large language models (LLMs) on paired motion-text data, which can result in catastrophic forgetting of linguistic capabilities due to the limited scale of available text-motion pairs. Furthermore, prior methods typically convert motion into discrete representations via quantization to integrate with language models, introducing substantial jitter artifacts from discrete tokenization. To address these challenges, we propose LLaMo, a unified framework that extends pretrained LLMs through a modality-specific Mixture-of-Transformers (MoT) architecture. This design inherently preserves the language understanding of the base model while enabling scalable multimodal adaptation. We encode human motion into a causal continuous latent space and maintain the next-token prediction paradigm in the decoder-only backbone through a lightweight flow-matching head, allowing for streaming motion generation in real-time (>30 FPS). Leveraging the comprehensive language understanding of pretrained LLMs and large-scale motion-text pretraining, our experiments demonstrate that LLaMo achieves high-fidelity text-to-motion generation and motion-to-text captioning in general settings, especially zero-shot motion generation, marking a significant step towards a general unified motion-language large model.

Rao Fu, Zehao Wen, Zichen Liu et al. · stanford

Inspired by cognitive theories, we introduce AnyHome, a framework that translates any text into well-structured and textured indoor scenes at a house-scale. By prompting Large Language Models (LLMs) with designed templates, our approach converts provided textual narratives into amodal structured representations. These representations guarantee consistent and realistic spatial layouts by directing the synthesis of a geometry mesh within defined constraints. A Score Distillation Sampling process is then employed to refine the geometry, followed by an egocentric inpainting process that adds lifelike textures to it. AnyHome stands out with its editability, customizability, diversity, and realism. The structured representations for scenes allow for extensive editing at varying levels of granularity. Capable of interpreting texts ranging from simple labels to detailed narratives, AnyHome generates detailed geometries and textures that outperform existing methods in both quantitative and qualitative measures.

Chandradeep Pokhariya, Ishaan N Shah, Angela Xing et al.

Understanding how we grasp objects with our hands has important applications in areas like robotics and mixed reality. However, this challenging problem requires accurate modeling of the contact between hands and objects. To capture grasps, existing methods use skeletons, meshes, or parametric models that does not represent hand shape accurately resulting in inaccurate contacts. We present MANUS, a method for Markerless Hand-Object Grasp Capture using Articulated 3D Gaussians. We build a novel articulated 3D Gaussians representation that extends 3D Gaussian splatting for high-fidelity representation of articulating hands. Since our representation uses Gaussian primitives, it enables us to efficiently and accurately estimate contacts between the hand and the object. For the most accurate results, our method requires tens of camera views that current datasets do not provide. We therefore build MANUS-Grasps, a new dataset that contains hand-object grasps viewed from 50+ cameras across 30+ scenes, 3 subjects, and comprising over 7M frames. In addition to extensive qualitative results, we also show that our method outperforms others on a quantitative contact evaluation method that uses paint transfer from the object to the hand.

Rahul Sajnani, Jeroen Vanbaar, Jie Min et al.

The success of image generative models has enabled us to build methods that can edit images based on text or other user input. However, these methods are bespoke, imprecise, require additional information, or are limited to only 2D image edits. We present GeoDiffuser, a zero-shot optimization-based method that unifies common 2D and 3D image-based object editing capabilities into a single method. Our key insight is to view image editing operations as geometric transformations. We show that these transformations can be directly incorporated into the attention layers in diffusion models to implicitly perform editing operations. Our training-free optimization method uses an objective function that seeks to preserve object style but generate plausible images, for instance with accurate lighting and shadows. It also inpaints disoccluded parts of the image where the object was originally located. Given a natural image and user input, we segment the foreground object using SAM and estimate a corresponding transform which is used by our optimization approach for editing. GeoDiffuser can perform common 2D and 3D edits like object translation, 3D rotation, and removal. We present quantitative results, including a perceptual study, that shows how our approach is better than existing methods. Visit https://ivl.cs.brown.edu/research/geodiffuser.html for more information.

Tao Lu, Ankit Dhiman, R Srinath et al.

Novel-view synthesis is an important problem in computer vision with applications in 3D reconstruction, mixed reality, and robotics. Recent methods like 3D Gaussian Splatting (3DGS) have become the preferred method for this task, providing high-quality novel views in real time. However, the training time of a 3DGS model is slow, often taking 30 minutes for a scene with 200 views. In contrast, our goal is to reduce the optimization time by training for fewer steps while maintaining high rendering quality. Specifically, we combine the guidance from both the position error and the appearance error to achieve a more effective densification. To balance the rate between adding new Gaussians and fitting old Gaussians, we develop a convergence-aware budget control mechanism. Moreover, to make the densification process more reliable, we selectively add new Gaussians from mostly visited regions. With these designs, we reduce the Gaussian optimization steps to one-third of the previous approach while achieving a comparable or even better novel view rendering quality. To further facilitate the rapid fitting of 4K resolution images, we introduce a dilation-based rendering technique. Our method, Turbo-GS, speeds up optimization for typical scenes and scales well to high-resolution (4K) scenarios on standard datasets. Through extensive experiments, we show that our method is significantly faster in optimization than other methods while retaining quality. Project page: https://ivl.cs.brown.edu/research/turbo-gs.

Gaurav Singh, Sanket Kalwar, Md Faizal Karim et al. · mit

Efficiently generating grasp poses tailored to specific regions of an object is vital for various robotic manipulation tasks, especially in a dual-arm setup. This scenario presents a significant challenge due to the complex geometries involved, requiring a deep understanding of the local geometry to generate grasps efficiently on the specified constrained regions. Existing methods only explore settings involving table-top/small objects and require augmented datasets to train, limiting their performance on complex objects. We propose CGDF: Constrained Grasp Diffusion Fields, a diffusion-based grasp generative model that generalizes to objects with arbitrary geometries, as well as generates dense grasps on the target regions. CGDF uses a part-guided diffusion approach that enables it to get high sample efficiency in constrained grasping without explicitly training on massive constraint-augmented datasets. We provide qualitative and quantitative comparisons using analytical metrics and in simulation, in both unconstrained and constrained settings to show that our method can generalize to generate stable grasps on complex objects, especially useful for dual-arm manipulation settings, while existing methods struggle to do so.

Rao Fu, Dingxi Zhang, Alex Jiang et al. · stanford

Understanding bimanual human hand activities is a critical problem in AI and robotics. We cannot build large models of bimanual activities because existing datasets lack the scale, coverage of diverse hand activities, and detailed annotations. We introduce GigaHands, a massive annotated dataset capturing 34 hours of bimanual hand activities from 56 subjects and 417 objects, totaling 14k motion clips derived from 183 million frames paired with 84k text annotations. Our markerless capture setup and data acquisition protocol enable fully automatic 3D hand and object estimation while minimizing the effort required for text annotation. The scale and diversity of GigaHands enable broad applications, including text-driven action synthesis, hand motion captioning, and dynamic radiance field reconstruction. Our website are avaliable at https://ivl.cs.brown.edu/research/gigahands.html .

Aashish Rai, Dilin Wang, Mihir Jain et al.

3D Gaussian Splatting (3DGS) has demonstrated superior quality in modeling 3D objects and scenes. However, generating 3DGS remains challenging due to their discrete, unstructured, and permutation-invariant nature. In this work, we present a simple yet effective method to overcome these challenges. We utilize spherical mapping to transform 3DGS into a structured 2D representation, termed UVGS. UVGS can be viewed as multi-channel images, with feature dimensions as a concatenation of Gaussian attributes such as position, scale, color, opacity, and rotation. We further find that these heterogeneous features can be compressed into a lower-dimensional (e.g., 3-channel) shared feature space using a carefully designed multi-branch network. The compressed UVGS can be treated as typical RGB images. Remarkably, we discover that typical VAEs trained with latent diffusion models can directly generalize to this new representation without additional training. Our novel representation makes it effortless to leverage foundational 2D models, such as diffusion models, to directly model 3DGS. Additionally, one can simply increase the 2D UV resolution to accommodate more Gaussians, making UVGS a scalable solution compared to typical 3D backbones. This approach immediately unlocks various novel generation applications of 3DGS by inherently utilizing the already developed superior 2D generation capabilities. In our experiments, we demonstrate various unconditional, conditional generation, and inpainting applications of 3DGS based on diffusion models, which were previously non-trivial.

Kefan Chen, Chaerin Min, Linguang Zhang et al.

Despite remarkable progress in image generation models, generating realistic hands remains a persistent challenge due to their complex articulation, varying viewpoints, and frequent occlusions. We present FoundHand, a large-scale domain-specific diffusion model for synthesizing single and dual hand images. To train our model, we introduce FoundHand-10M, a large-scale hand dataset with 2D keypoints and segmentation mask annotations. Our insight is to use 2D hand keypoints as a universal representation that encodes both hand articulation and camera viewpoint. FoundHand learns from image pairs to capture physically plausible hand articulations, natively enables precise control through 2D keypoints, and supports appearance control. Our model exhibits core capabilities that include the ability to repose hands, transfer hand appearance, and even synthesize novel views. This leads to zero-shot capabilities for fixing malformed hands in previously generated images, or synthesizing hand video sequences. We present extensive experiments and evaluations that demonstrate state-of-the-art performance of our method.

Hongyu Li, Mingxi Jia, Tuluhan Akbulut et al.

Humans naturally integrate vision and haptics for robust object perception during manipulation. The loss of either modality significantly degrades performance. Inspired by this multisensory integration, prior object pose estimation research has attempted to combine visual and haptic/tactile feedback. Although these works demonstrate improvements in controlled environments or synthetic datasets, they often underperform vision-only approaches in real-world settings due to poor generalization across diverse grippers, sensor layouts, or sim-to-real environments. Furthermore, they typically estimate the object pose for each frame independently, resulting in less coherent tracking over sequences in real-world deployments. To address these limitations, we introduce a novel unified haptic representation that effectively handles multiple gripper embodiments. Building on this representation, we introduce a new visuo-haptic transformer-based object pose tracker that seamlessly integrates visual and haptic input. We validate our framework in our dataset and the Feelsight dataset, demonstrating significant performance improvement on challenging sequences. Notably, our method achieves superior generalization and robustness across novel embodiments, objects, and sensor types (both taxel-based and vision-based tactile sensors). In real-world experiments, we demonstrate that our approach outperforms state-of-the-art visual trackers by a large margin. We further show that we can achieve precise manipulation tasks by incorporating our real-time object tracking result into motion plans, underscoring the advantages of visuo-haptic perception. Project website: https://ivl.cs.brown.edu/research/v-hop

Dvij Kalaria, Sudarshan S Harithas, Pushkal Katara et al.

We introduce DreamControl, a novel methodology for learning autonomous whole-body humanoid skills. DreamControl leverages the strengths of diffusion models and Reinforcement Learning (RL): our core innovation is the use of a diffusion prior trained on human motion data, which subsequently guides an RL policy in simulation to complete specific tasks of interest (e.g., opening a drawer or picking up an object). We demonstrate that this human motion-informed prior allows RL to discover solutions unattainable by direct RL, and that diffusion models inherently promote natural looking motions, aiding in sim-to-real transfer. We validate DreamControl's effectiveness on a Unitree G1 robot across a diverse set of challenging tasks involving simultaneous lower and upper body control and object interaction. Project website at https://genrobo.github.io/DreamControl/

Hongyu Li, James Akl, Srinath Sridhar et al.

Object 6D pose estimation is a critical challenge in robotics, particularly for manipulation tasks. While prior research combining visual and tactile (visuotactile) information has shown promise, these approaches often struggle with generalization due to the limited availability of visuotactile data. In this paper, we introduce ViTa-Zero, a zero-shot visuotactile pose estimation framework. Our key innovation lies in leveraging a visual model as its backbone and performing feasibility checking and test-time optimization based on physical constraints derived from tactile and proprioceptive observations. Specifically, we model the gripper-object interaction as a spring-mass system, where tactile sensors induce attractive forces, and proprioception generates repulsive forces. We validate our framework through experiments on a real-world robot setup, demonstrating its effectiveness across representative visual backbones and manipulation scenarios, including grasping, object picking, and bimanual handover. Compared to the visual models, our approach overcomes some drastic failure modes while tracking the in-hand object pose. In our experiments, our approach shows an average increase of 55% in AUC of ADD-S and 60% in ADD, along with an 80% lower position error compared to FoundationPose.

Arnab Dey, Cheng-You Lu, Andrew I. Comport et al.

Recent advancements in radiance field rendering show promising results in 3D scene representation, where Gaussian splatting-based techniques emerge as state-of-the-art due to their quality and efficiency. Gaussian splatting is widely used for various applications, including 3D human representation. However, previous 3D Gaussian splatting methods either use parametric body models as additional information or fail to provide any underlying structure, like human biomechanical features, which are essential for different applications. In this paper, we present a novel approach called HFGaussian that can estimate novel views and human features, such as the 3D skeleton, 3D key points, and dense pose, from sparse input images in real time at 25 FPS. The proposed method leverages generalizable Gaussian splatting technique to represent the human subject and its associated features, enabling efficient and generalizable reconstruction. By incorporating a pose regression network and the feature splatting technique with Gaussian splatting, HFGaussian demonstrates improved capabilities over existing 3D human methods, showcasing the potential of 3D human representations with integrated biomechanics. We thoroughly evaluate our HFGaussian method against the latest state-of-the-art techniques in human Gaussian splatting and pose estimation, demonstrating its real-time, state-of-the-art performance.

Sudarshan Harithas, Sangkyung Kwak, Pushkal Katara et al.

Developing robust autonomous loco-manipulation skills for humanoids remains an open problem in robotics. While RL has been applied successfully to legged locomotion, applying it to complex, interaction-rich manipulation tasks is harder given long-horizon planning challenges for manipulation. A recent approach along these lines is DreamControl, which addresses these issues by leveraging off-the-shelf human motion diffusion models as a generative prior to guide RL policies during training. In this paper, we investigate the impact of DreamControl's motion prior and propose an improved framework that trains a guided diffusion model directly in the humanoid robot's motion space, aggregating diverse human and robot datasets into a unified embodiment space. We demonstrate that our approach captures a wider range of skills due to the larger training data mixture and establishes a more automated pipeline by removing the need for manual filtering interventions. Furthermore, we show that scaling the generation of reference trajectories is important for achieving robust downstream RL policies. We validate our approach through extensive experiments in simulation and on a real Unitree-G1.

Cheng-You Lu, Zhuoli Zhuang, Nguyen Thanh Trung Le et al. · stanford

Advances in 3D reconstruction and novel view synthesis have enabled efficient and photorealistic rendering. However, images for reconstruction are still either largely manual or constrained by simple preplanned trajectories. To address this issue, recent works propose generalizable next-best-view planners that do not require online learning. Nevertheless, robustness and performance remain limited across various shapes. Hence, this study introduces Voxel-Face-Aware Hierarchical Next-Best-View Acquisition for Efficient 3D Reconstruction (Hestia), which addresses the shortcomings of the reinforcement learning-based generalizable approaches for five-degree-of-freedom viewpoint prediction. Hestia systematically improves the planners through four components: a more diverse dataset to promote robustness, a hierarchical structure to manage the high-dimensional continuous action search space, a close-greedy strategy to mitigate spurious correlations, and a face-aware design to avoid overlooking geometry. Experimental results show that Hestia achieves non-marginal improvements, with at least a 4% gain in coverage ratio, while reducing Chamfer Distance by 50% and maintaining real-time inference. In addition, Hestia outperforms prior methods by at least 12% in coverage ratio with a 5-image budget and remains robust to object placement variations. Finally, we demonstrate that Hestia, as a next-best-view planner, is feasible for the real-world application. Our project page is https://johnnylu305.github.io/hestia web.

Zekun Li, Rui Zhou, Rahul Sajnani et al.

Large-scale pre-trained video diffusion models have exhibited remarkable capabilities in diverse video generation. However, existing solutions face several challenges in using these models to generate long movie-like videos with rich human-object interactions that include unrealistic human-scene interaction, lack of subject identity preservation, and require expensive training. We propose GenHSI, a training-free method for controllable generation of long human-scene interaction videos (HSI). Taking inspiration from movie animation, our key insight is to overcome the limitations of previous work by subdividing the long video generation task into three stages: (1) script writing, (2) pre-visualization, and (3) animation. Given an image of a scene, a user description, and multiple images of a person, we use these three stages to generate long-videos that preserve human-identity and provide rich human-scene interactions. Script writing converts complex human tasks into simple atomic tasks that are used in the pre-visualization stage to generate 3D keyframes (storyboards). These 3D keyframes are rendered and animated by off-the-shelf video diffusion models for consistent long video generation with rich contacts in a 3D-aware manner. A key advantage of our work is that we alleviate the need for scanned, accurate scenes and create 3D keyframes from single-view images. We are the first to generate a long video sequence with a consistent camera pose that contains arbitrary numbers of character actions without training. Experiments demonstrate that our method can generate long videos that effectively preserve scene content and character identity with plausible human-scene interaction from a single image scene. Visit our project homepage https://kunkun0w0.github.io/project/GenHSI/ for more information.

Xiaoyan Cong, Angela Xing, Chandradeep Pokhariya et al.

Reconstructing dynamic hand-object contacts is essential for realistic manipulation in AI character animation, XR, and robotics, yet it remains challenging due to heavy occlusions, complex surface details, and limitations in existing capture techniques. In this paper, we introduce DyTact, a markerless capture method for accurately capturing dynamic contact in hand-object manipulations in a non-intrusive manner. Our approach leverages a dynamic, articulated representation based on 2D Gaussian surfels to model complex manipulations. By binding these surfels to MANO meshes, DyTact harnesses the inductive bias of template models to stabilize and accelerate optimization. A refinement module addresses time-dependent high-frequency deformations, while a contact-guided adaptive sampling strategy selectively increases surfel density in contact regions to handle heavy occlusion. Extensive experiments demonstrate that DyTact not only achieves state-of-the-art dynamic contact estimation accuracy but also significantly improves novel view synthesis quality, all while operating with fast optimization and efficient memory usage. Project Page: https://oliver-cong02.github.io/DyTact.github.io/ .

Xiaoyan Cong, Jiayi Shen, Zekun Li et al.

Large-scale pre-trained image-to-3D generative models have exhibited remarkable capabilities in diverse shape generations. However, most of them struggle to synthesize plausible 3D assets when the reference image is flat-colored like hand drawings due to the lack of 3D illusion, which are often the most user-friendly input modalities in art content creation. To this end, we propose Art3D, a training-free method that can lift flat-colored 2D designs into 3D. By leveraging structural and semantic features with pre- trained 2D image generation models and a VLM-based realism evaluation, Art3D successfully enhances the three-dimensional illusion in reference images, thus simplifying the process of generating 3D from 2D, and proves adaptable to a wide range of painting styles. To benchmark the generalization performance of existing image-to-3D models on flat-colored images without 3D feeling, we collect a new dataset, Flat-2D, with over 100 samples. Experimental results demonstrate the performance and robustness of Art3D, exhibiting superior generalizable capacity and promising practical applicability. Our source code and dataset will be publicly available on our project page: https://joy-jy11.github.io/ .

Kefan Chen, Sergiu Oprea, Justin Theiss et al.

With the rising interest from the community in digital avatars coupled with the importance of expressions and gestures in communication, modeling natural avatar behavior remains an important challenge across many industries such as teleconferencing, gaming, and AR/VR. Human hands are the primary tool for interacting with the environment and essential for realistic human behavior modeling, yet existing 3D hand and head avatar models often overlook the crucial aspect of hand-body interactions, such as between hand and face. We present InteracttAvatar, the first model to faithfully capture the photorealistic appearance of dynamic hand and non-rigid hand-face interactions. Our novel Dynamic Gaussian Hand model, combining template model and 3D Gaussian Splatting as well as a dynamic refinement module, captures pose-dependent change, e.g. the fine wrinkles and complex shadows that occur during articulation. Importantly, our hand-face interaction module models the subtle geometry and appearance dynamics that underlie common gestures. Through experiments of novel view synthesis, self reenactment and cross-identity reenactment, we demonstrate that InteracttAvatar can reconstruct hand and hand-face interactions from monocular or multiview videos with high-fidelity details and be animated with novel poses.

Xianghao Xu, Srinath Sridhar, Daniel Ritchie · stanford

We propose a zero-shot text-driven 3D shape deformation system that deforms an input 3D mesh of a manufactured object to fit an input text description. To do this, our system optimizes the parameters of a deformation model to maximize an objective function based on the widely used pre-trained vision language model CLIP. We find that CLIP-based objective functions exhibit many spurious local optima; to circumvent them, we parameterize deformations using a novel deformation model called BoxDefGraph which our system automatically computes from an input mesh, the BoxDefGraph is designed to capture the object aligned rectangular/circular geometry features of most manufactured objects. We then use the CMA-ES global optimization algorithm to maximize our objective, which we find to work better than popular gradient-based optimizers. We demonstrate that our approach produces appealing results and outperforms several baselines.

Chaerin Min, Srinath Sridhar

Grasping is an important human activity that has long been studied in robotics, computer vision, and cognitive science. Most existing works study grasping from the perspective of synthesizing hand poses conditioned on 3D or 2D object representations. We propose GenHeld to address the inverse problem of synthesizing held objects conditioned on 3D hand model or 2D image. Given a 3D model of hand, GenHeld 3D can select a plausible held object from a large dataset using compact object representations called object codes.The selected object is then positioned and oriented to form a plausible grasp without changing hand pose. If only a 2D hand image is available, GenHeld 2D can edit this image to add or replace a held object. GenHeld 2D operates by combining the abilities of GenHeld 3D with diffusion-based image editing. Results and experiments show that we outperform baselines and can generate plausible held objects in both 2D and 3D. Our experiments demonstrate that our method achieves high quality and plausibility of held object synthesis in both 3D and 2D.

Arnab Dey, Di Yang, Rohith Agaram et al.

Recent advances in Neural Radiance Fields (NeRF) have demonstrated promising results in 3D scene representations, including 3D human representations. However, these representations often lack crucial information on the underlying human pose and structure, which is crucial for AR/VR applications and games. In this paper, we introduce a novel approach, termed GHNeRF, designed to address these limitations by learning 2D/3D joint locations of human subjects with NeRF representation. GHNeRF uses a pre-trained 2D encoder streamlined to extract essential human features from 2D images, which are then incorporated into the NeRF framework in order to encode human biomechanic features. This allows our network to simultaneously learn biomechanic features, such as joint locations, along with human geometry and texture. To assess the effectiveness of our method, we conduct a comprehensive comparison with state-of-the-art human NeRF techniques and joint estimation algorithms. Our results show that GHNeRF can achieve state-of-the-art results in near real-time.

Rahul Sajnani, Adrien Poulenard, Jivitesh Jain et al.

Progress in 3D object understanding has relied on manually canonicalized shape datasets that contain instances with consistent position and orientation (3D pose). This has made it hard to generalize these methods to in-the-wild shapes, eg., from internet model collections or depth sensors. ConDor is a self-supervised method that learns to Canonicalize the 3D orientation and position for full and partial 3D point clouds. We build on top of Tensor Field Networks (TFNs), a class of permutation- and rotation-equivariant, and translation-invariant 3D networks. During inference, our method takes an unseen full or partial 3D point cloud at an arbitrary pose and outputs an equivariant canonical pose. During training, this network uses self-supervision losses to learn the canonical pose from an un-canonicalized collection of full and partial 3D point clouds. ConDor can also learn to consistently co-segment object parts without any supervision. Extensive quantitative results on four new metrics show that our approach outperforms existing methods while enabling new applications such as operation on depth images and annotation transfer.

Bryce Blinn, Alexander Ding, R. Kenny Jones et al.

The shape of many objects in the built environment is dictated by their relationships to the human body: how will a person interact with this object? Existing data-driven generative models of 3D shapes produce plausible objects but do not reason about the relationship of those objects to the human body. In this paper, we learn body-aware generative models of 3D shapes. Specifically, we train generative models of chairs, an ubiquitous shape category, which can be conditioned on a given body shape or sitting pose. The body-shape-conditioned models produce chairs which will be comfortable for a person with the given body shape; the pose-conditioned models produce chairs which accommodate the given sitting pose. To train these models, we define a "sitting pose matching" metric and a novel "sitting comfort" metric. Calculating these metrics requires an expensive optimization to sit the body into the chair, which is too slow to be used as a loss function for training a generative model. Thus, we train neural networks to efficiently approximate these metrics. We use our approach to train three body-aware generative shape models: a structured part-based generator, a point cloud generator, and an implicit surface generator. In all cases, our approach produces models which adapt their output chair shapes to input human body specifications.

Yiheng Xie, Towaki Takikawa, Shunsuke Saito et al.

Recent advances in machine learning have created increasing interest in solving visual computing problems using a class of coordinate-based neural networks that parametrize physical properties of scenes or objects across space and time. These methods, which we call neural fields, have seen successful application in the synthesis of 3D shapes and image, animation of human bodies, 3D reconstruction, and pose estimation. However, due to rapid progress in a short time, many papers exist but a comprehensive review and formulation of the problem has not yet emerged. In this report, we address this limitation by providing context, mathematical grounding, and an extensive review of literature on neural fields. This report covers research along two dimensions. In Part I, we focus on techniques in neural fields by identifying common components of neural field methods, including different representations, architectures, forward mapping, and generalization methods. In Part II, we focus on applications of neural fields to different problems in visual computing, and beyond (e.g., robotics, audio). Our review shows the breadth of topics already covered in visual computing, both historically and in current incarnations, demonstrating the improved quality, flexibility, and capability brought by neural fields methods. Finally, we present a companion website that contributes a living version of this review that can be continually updated by the community.

Ge Zhang, Or Litany, Srinath Sridhar et al.

We present StrobeNet, a method for category-level 3D reconstruction of articulating objects from one or more unposed RGB images. Reconstructing general articulating object categories % has important applications, but is challenging since objects can have wide variation in shape, articulation, appearance and topology. We address this by building on the idea of category-level articulation canonicalization -- mapping observations to a canonical articulation which enables correspondence-free multiview aggregation. Our end-to-end trainable neural network estimates feature-enriched canonical 3D point clouds, articulation joints, and part segmentation from one or more unposed images of an object. These intermediate estimates are used to generate a final implicit 3D reconstruction.Our approach reconstructs objects even when they are observed in different articulations in images with large baselines, and animation of reconstructed shapes. Quantitative and qualitative evaluations on different object categories show that our method is able to achieve high reconstruction accuracy, especially as more views are added.

Davis Rempe, Tolga Birdal, Aaron Hertzmann et al.

We introduce HuMoR: a 3D Human Motion Model for Robust Estimation of temporal pose and shape. Though substantial progress has been made in estimating 3D human motion and shape from dynamic observations, recovering plausible pose sequences in the presence of noise and occlusions remains a challenge. For this purpose, we propose an expressive generative model in the form of a conditional variational autoencoder, which learns a distribution of the change in pose at each step of a motion sequence. Furthermore, we introduce a flexible optimization-based approach that leverages HuMoR as a motion prior to robustly estimate plausible pose and shape from ambiguous observations. Through extensive evaluations, we demonstrate that our model generalizes to diverse motions and body shapes after training on a large motion capture dataset, and enables motion reconstruction from multiple input modalities including 3D keypoints and RGB(-D) videos.

Rahul Sajnani, AadilMehdi Sanchawala, Krishna Murthy Jatavallabhula et al.

We present DRACO, a method for Dense Reconstruction And Canonicalization of Object shape from one or more RGB images. Canonical shape reconstruction, estimating 3D object shape in a coordinate space canonicalized for scale, rotation, and translation parameters, is an emerging paradigm that holds promise for a multitude of robotic applications. Prior approaches either rely on painstakingly gathered dense 3D supervision, or produce only sparse canonical representations, limiting real-world applicability. DRACO performs dense canonicalization using only weak supervision in the form of camera poses and semantic keypoints at train time. During inference, DRACO predicts dense object-centric depth maps in a canonical coordinate-space, solely using one or more RGB images of an object. Extensive experiments on canonical shape reconstruction and pose estimation show that DRACO is competitive or superior to fully-supervised methods.

Jiahui Lei, Srinath Sridhar, Paul Guerrero et al.

We investigate the problem of learning to generate 3D parametric surface representations for novel object instances, as seen from one or more views. Previous work on learning shape reconstruction from multiple views uses discrete representations such as point clouds or voxels, while continuous surface generation approaches lack multi-view consistency. We address these issues by designing neural networks capable of generating high-quality parametric 3D surfaces which are also consistent between views. Furthermore, the generated 3D surfaces preserve accurate image pixel to 3D surface point correspondences, allowing us to lift texture information to reconstruct shapes with rich geometry and appearance. Our method is supervised and trained on a public dataset of shapes from common object categories. Quantitative results indicate that our method significantly outperforms previous work, while qualitative results demonstrate the high quality of our reconstructions.

Davis Rempe, Tolga Birdal, Yongheng Zhao et al.

We propose CaSPR, a method to learn object-centric Canonical Spatiotemporal Point Cloud Representations of dynamically moving or evolving objects. Our goal is to enable information aggregation over time and the interrogation of object state at any spatiotemporal neighborhood in the past, observed or not. Different from previous work, CaSPR learns representations that support spacetime continuity, are robust to variable and irregularly spacetime-sampled point clouds, and generalize to unseen object instances. Our approach divides the problem into two subtasks. First, we explicitly encode time by mapping an input point cloud sequence to a spatiotemporally-canonicalized object space. We then leverage this canonicalization to learn a spatiotemporal latent representation using neural ordinary differential equations and a generative model of dynamically evolving shapes using continuous normalizing flows. We demonstrate the effectiveness of our method on several applications including shape reconstruction, camera pose estimation, continuous spatiotemporal sequence reconstruction, and correspondence estimation from irregularly or intermittently sampled observations.

Or Litany, Ari Morcos, Srinath Sridhar et al.

We seek to learn a representation on a large annotated data source that generalizes to a target domain using limited new supervision. Many prior approaches to this problem have focused on learning "disentangled" representations so that as individual factors vary in a new domain, only a portion of the representation need be updated. In this work, we seek the generalization power of disentangled representations, but relax the requirement of explicit latent disentanglement and instead encourage linearity of individual factors of variation by requiring them to be manipulable by learned linear transformations. We dub these transformations latent canonicalizers, as they aim to modify the value of a factor to a pre-determined (but arbitrary) canonical value (e.g., recoloring the image foreground to black). Assuming a source domain with access to meta-labels specifying the factors of variation within an image, we demonstrate experimentally that our method helps reduce the number of observations needed to generalize to a similar target domain when compared to a number of supervised baselines.

Zhangsihao Yang, Or Litany, Tolga Birdal et al.

The majority of descriptor-based methods for geometric processing of non-rigid shape rely on hand-crafted descriptors. Recently, learning-based techniques have been shown effective, achieving state-of-the-art results in a variety of tasks. Yet, even though these methods can in principle work directly on raw data, most methods still rely on hand-crafted descriptors at the input layer. In this work, we wish to challenge this practice and use a neural network to learn descriptors directly from the raw mesh. To this end, we introduce two modules into our neural architecture. The first is a local reference frame (LRF) used to explicitly make the features invariant to rigid transformations. The second is continuous convolution kernels that provide robustness to sampling. We show the efficacy of our proposed network in learning on raw meshes using two cornerstone tasks: shape matching, and human body parts segmentation. Our results show superior results over baseline methods that use hand-crafted descriptors.

Davis Rempe, Srinath Sridhar, He Wang et al.

Machines that can predict the effect of physical interactions on the dynamics of previously unseen object instances are important for creating better robots and interactive virtual worlds. In this work, we focus on predicting the dynamics of 3D objects on a plane that have just been subjected to an impulsive force. In particular, we predict the changes in state - 3D position, rotation, velocities, and stability. Different from previous work, our approach can generalize dynamics predictions to object shapes and initial conditions that were unseen during training. Our method takes the 3D object's shape as a point cloud and its initial linear and angular velocities as input. We extract shape features and use a recurrent neural network to predict the full change in state at each time step. Our model can support training with data from both a physics engine or the real world. Experiments show that we can accurately predict the changes in state for unseen object geometries and initial conditions.

Srinath Sridhar, Davis Rempe, Julien Valentin et al.

We investigate the problem of learning category-specific 3D shape reconstruction from a variable number of RGB views of previously unobserved object instances. Most approaches for multiview shape reconstruction operate on sparse shape representations, or assume a fixed number of views. We present a method that can estimate dense 3D shape, and aggregate shape across multiple and varying number of input views. Given a single input view of an object instance, we propose a representation that encodes the dense shape of the visible object surface as well as the surface behind line of sight occluded by the visible surface. When multiple input views are available, the shape representation is designed to be aggregated into a single 3D shape using an inexpensive union operation. We train a 2D CNN to learn to predict this representation from a variable number of views (1 or more). We further aggregate multiview information by using permutation equivariant layers that promote order-agnostic view information exchange at the feature level. Experiments show that our approach is able to produce dense 3D reconstructions of objects that improve in quality as more views are added.

He Wang, Srinath Sridhar, Jingwei Huang et al.

The goal of this paper is to estimate the 6D pose and dimensions of unseen object instances in an RGB-D image. Contrary to "instance-level" 6D pose estimation tasks, our problem assumes that no exact object CAD models are available during either training or testing time. To handle different and unseen object instances in a given category, we introduce a Normalized Object Coordinate Space (NOCS)---a shared canonical representation for all possible object instances within a category. Our region-based neural network is then trained to directly infer the correspondence from observed pixels to this shared object representation (NOCS) along with other object information such as class label and instance mask. These predictions can be combined with the depth map to jointly estimate the metric 6D pose and dimensions of multiple objects in a cluttered scene. To train our network, we present a new context-aware technique to generate large amounts of fully annotated mixed reality data. To further improve our model and evaluate its performance on real data, we also provide a fully annotated real-world dataset with large environment and instance variation. Extensive experiments demonstrate that the proposed method is able to robustly estimate the pose and size of unseen object instances in real environments while also achieving state-of-the-art performance on standard 6D pose estimation benchmarks.

Davis Rempe, Srinath Sridhar, He Wang et al.

Humans have a remarkable ability to predict the effect of physical interactions on the dynamics of objects. Endowing machines with this ability would allow important applications in areas like robotics and autonomous vehicles. In this work, we focus on predicting the dynamics of 3D rigid objects, in particular an object's final resting position and total rotation when subjected to an impulsive force. Different from previous work, our approach is capable of generalizing to unseen object shapes - an important requirement for real-world applications. To achieve this, we represent object shape as a 3D point cloud that is used as input to a neural network, making our approach agnostic to appearance variation. The design of our network is informed by an understanding of physical laws. We train our model with data from a physics engine that simulates the dynamics of a large number of shapes. Experiments show that we can accurately predict the resting position and total rotation for unseen object geometries.