Otmar Hilliges

Daoji Huang, Otmar Hilliges, Luc Van Gool et al. · eth-zurich

We present Palm, a solution to the Long-Term Action Anticipation (LTA) task utilizing vision-language and large language models. Given an input video with annotated action periods, the LTA task aims to predict possible future actions. We hypothesize that an optimal solution should capture the interdependency between past and future actions, and be able to infer future actions based on the structure and dependency encoded in the past actions. Large language models have demonstrated remarkable commonsense-based reasoning ability. Inspired by that, Palm chains an image captioning model and a large language model. It predicts future actions based on frame descriptions and action labels extracted from the input videos. Our method outperforms other participants in the EGO4D LTA challenge and achieves the best performance in terms of action prediction. Our code is available at https://github.com/DanDoge/Palm

Yufeng Zheng, Wang Yifan, Gordon Wetzstein et al. · stanford

The ability to create realistic, animatable and relightable head avatars from casual video sequences would open up wide ranging applications in communication and entertainment. Current methods either build on explicit 3D morphable meshes (3DMM) or exploit neural implicit representations. The former are limited by fixed topology, while the latter are non-trivial to deform and inefficient to render. Furthermore, existing approaches entangle lighting in the color estimation, thus they are limited in re-rendering the avatar in new environments. In contrast, we propose PointAvatar, a deformable point-based representation that disentangles the source color into intrinsic albedo and normal-dependent shading. We demonstrate that PointAvatar bridges the gap between existing mesh- and implicit representations, combining high-quality geometry and appearance with topological flexibility, ease of deformation and rendering efficiency. We show that our method is able to generate animatable 3D avatars using monocular videos from multiple sources including hand-held smartphones, laptop webcams and internet videos, achieving state-of-the-art quality in challenging cases where previous methods fail, e.g., thin hair strands, while being significantly more efficient in training than competing methods.

Sammy Christen, Wei Yang, Claudia Pérez-D'Arpino et al. · nvidia

We propose the first framework to learn control policies for vision-based human-to-robot handovers, a critical task for human-robot interaction. While research in Embodied AI has made significant progress in training robot agents in simulated environments, interacting with humans remains challenging due to the difficulties of simulating humans. Fortunately, recent research has developed realistic simulated environments for human-to-robot handovers. Leveraging this result, we introduce a method that is trained with a human-in-the-loop via a two-stage teacher-student framework that uses motion and grasp planning, reinforcement learning, and self-supervision. We show significant performance gains over baselines on a simulation benchmark, sim-to-sim transfer and sim-to-real transfer.

Zicong Fan, Maria Parelli, Maria Eleni Kadoglou et al.

Since humans interact with diverse objects every day, the holistic 3D capture of these interactions is important to understand and model human behaviour. However, most existing methods for hand-object reconstruction from RGB either assume pre-scanned object templates or heavily rely on limited 3D hand-object data, restricting their ability to scale and generalize to more unconstrained interaction settings. To this end, we introduce HOLD -- the first category-agnostic method that reconstructs an articulated hand and object jointly from a monocular interaction video. We develop a compositional articulated implicit model that can reconstruct disentangled 3D hand and object from 2D images. We also further incorporate hand-object constraints to improve hand-object poses and consequently the reconstruction quality. Our method does not rely on 3D hand-object annotations while outperforming fully-supervised baselines in both in-the-lab and challenging in-the-wild settings. Moreover, we qualitatively show its robustness in reconstructing from in-the-wild videos. Code: https://github.com/zc-alexfan/hold

Zicong Fan, Omid Taheri, Dimitrios Tzionas et al.

Humans intuitively understand that inanimate objects do not move by themselves, but that state changes are typically caused by human manipulation (e.g., the opening of a book). This is not yet the case for machines. In part this is because there exist no datasets with ground-truth 3D annotations for the study of physically consistent and synchronised motion of hands and articulated objects. To this end, we introduce ARCTIC -- a dataset of two hands that dexterously manipulate objects, containing 2.1M video frames paired with accurate 3D hand and object meshes and detailed, dynamic contact information. It contains bi-manual articulation of objects such as scissors or laptops, where hand poses and object states evolve jointly in time. We propose two novel articulated hand-object interaction tasks: (1) Consistent motion reconstruction: Given a monocular video, the goal is to reconstruct two hands and articulated objects in 3D, so that their motions are spatio-temporally consistent. (2) Interaction field estimation: Dense relative hand-object distances must be estimated from images. We introduce two baselines ArcticNet and InterField, respectively and evaluate them qualitatively and quantitatively on ARCTIC. Our code and data are available at https://arctic.is.tue.mpg.de.

Artur Grigorev, Bernhard Thomaszewski, Michael J. Black et al.

We propose a method that leverages graph neural networks, multi-level message passing, and unsupervised training to enable real-time prediction of realistic clothing dynamics. Whereas existing methods based on linear blend skinning must be trained for specific garments, our method is agnostic to body shape and applies to tight-fitting garments as well as loose, free-flowing clothing. Our method furthermore handles changes in topology (e.g., garments with buttons or zippers) and material properties at inference time. As one key contribution, we propose a hierarchical message-passing scheme that efficiently propagates stiff stretching modes while preserving local detail. We empirically show that our method outperforms strong baselines quantitatively and that its results are perceived as more realistic than state-of-the-art methods.

Xu Chen, Tianjian Jiang, Jie Song et al.

Neural fields have revolutionized the area of 3D reconstruction and novel view synthesis of rigid scenes. A key challenge in making such methods applicable to articulated objects, such as the human body, is to model the deformation of 3D locations between the rest pose (a canonical space) and the deformed space. We propose a new articulation module for neural fields, Fast-SNARF, which finds accurate correspondences between canonical space and posed space via iterative root finding. Fast-SNARF is a drop-in replacement in functionality to our previous work, SNARF, while significantly improving its computational efficiency. We contribute several algorithmic and implementation improvements over SNARF, yielding a speed-up of $150\times$. These improvements include voxel-based correspondence search, pre-computing the linear blend skinning function, and an efficient software implementation with CUDA kernels. Fast-SNARF enables efficient and simultaneous optimization of shape and skinning weights given deformed observations without correspondences (e.g. 3D meshes). Because learning of deformation maps is a crucial component in many 3D human avatar methods and since Fast-SNARF provides a computationally efficient solution, we believe that this work represents a significant step towards the practical creation of 3D virtual humans.

Xi Wang, Gen Li, Yen-Ling Kuo et al. · eth-zurich

We present a method for inferring diverse 3D models of human-object interactions from images. Reasoning about how humans interact with objects in complex scenes from a single 2D image is a challenging task given ambiguities arising from the loss of information through projection. In addition, modeling 3D interactions requires the generalization ability towards diverse object categories and interaction types. We propose an action-conditioned modeling of interactions that allows us to infer diverse 3D arrangements of humans and objects without supervision on contact regions or 3D scene geometry. Our method extracts high-level commonsense knowledge from large language models (such as GPT-3), and applies them to perform 3D reasoning of human-object interactions. Our key insight is priors extracted from large language models can help in reasoning about human-object contacts from textural prompts only. We quantitatively evaluate the inferred 3D models on a large human-object interaction dataset and show how our method leads to better 3D reconstructions. We further qualitatively evaluate the effectiveness of our method on real images and demonstrate its generalizability towards interaction types and object categories.

Zijian Dong, Chen Guo, Jie Song et al.

We present a novel method to learn Personalized Implicit Neural Avatars (PINA) from a short RGB-D sequence. This allows non-expert users to create a detailed and personalized virtual copy of themselves, which can be animated with realistic clothing deformations. PINA does not require complete scans, nor does it require a prior learned from large datasets of clothed humans. Learning a complete avatar in this setting is challenging, since only few depth observations are available, which are noisy and incomplete (i.e. only partial visibility of the body per frame). We propose a method to learn the shape and non-rigid deformations via a pose-conditioned implicit surface and a deformation field, defined in canonical space. This allows us to fuse all partial observations into a single consistent canonical representation. Fusion is formulated as a global optimization problem over the pose, shape and skinning parameters. The method can learn neural avatars from real noisy RGB-D sequences for a diverse set of people and clothing styles and these avatars can be animated given unseen motion sequences.

Egor Zakharov, Vanessa Sklyarova, Michael Black et al. · eth-zurich

We introduce a new hair modeling method that uses a dual representation of classical hair strands and 3D Gaussians to produce accurate and realistic strand-based reconstructions from multi-view data. In contrast to recent approaches that leverage unstructured Gaussians to model human avatars, our method reconstructs the hair using 3D polylines, or strands. This fundamental difference allows the use of the resulting hairstyles out-of-the-box in modern computer graphics engines for editing, rendering, and simulation. Our 3D lifting method relies on unstructured Gaussians to generate multi-view ground truth data to supervise the fitting of hair strands. The hairstyle itself is represented in the form of the so-called strand-aligned 3D Gaussians. This representation allows us to combine strand-based hair priors, which are essential for realistic modeling of the inner structure of hairstyles, with the differentiable rendering capabilities of 3D Gaussian Splatting. Our method, named Gaussian Haircut, is evaluated on synthetic and real scenes and demonstrates state-of-the-art performance in the task of strand-based hair reconstruction.

Razvan-George Pasca, Alexey Gavryushin, Muhammad Hamza et al. · eth-zurich

We study object interaction anticipation in egocentric videos. This task requires an understanding of the spatio-temporal context formed by past actions on objects, coined action context. We propose TransFusion, a multimodal transformer-based architecture. It exploits the representational power of language by summarizing the action context. TransFusion leverages pre-trained image captioning and vision-language models to extract the action context from past video frames. This action context together with the next video frame is processed by the multimodal fusion module to forecast the next object interaction. Our model enables more efficient end-to-end learning. The large pre-trained language models add common sense and a generalisation capability. Experiments on Ego4D and EPIC-KITCHENS-100 show the effectiveness of our multimodal fusion model. They also highlight the benefits of using language-based context summaries in a task where vision seems to suffice. Our method outperforms state-of-the-art approaches by 40.4% in relative terms in overall mAP on the Ego4D test set. We validate the effectiveness of TransFusion via experiments on EPIC-KITCHENS-100. Video and code are available at https://eth-ait.github.io/transfusion-proj/.

Alessandro Ruzzi, Xiangwei Shi, Xi Wang et al. · eth-zurich

We propose GazeNeRF, a 3D-aware method for the task of gaze redirection. Existing gaze redirection methods operate on 2D images and struggle to generate 3D consistent results. Instead, we build on the intuition that the face region and eyeballs are separate 3D structures that move in a coordinated yet independent fashion. Our method leverages recent advancements in conditional image-based neural radiance fields and proposes a two-stream architecture that predicts volumetric features for the face and eye regions separately. Rigidly transforming the eye features via a 3D rotation matrix provides fine-grained control over the desired gaze angle. The final, redirected image is then attained via differentiable volume compositing. Our experiments show that this architecture outperforms naively conditioned NeRF baselines as well as previous state-of-the-art 2D gaze redirection methods in terms of redirection accuracy and identity preservation.

Tianjian Jiang, Xu Chen, Jie Song et al.

In this paper, we take a significant step towards real-world applicability of monocular neural avatar reconstruction by contributing InstantAvatar, a system that can reconstruct human avatars from a monocular video within seconds, and these avatars can be animated and rendered at an interactive rate. To achieve this efficiency we propose a carefully designed and engineered system, that leverages emerging acceleration structures for neural fields, in combination with an efficient empty space-skipping strategy for dynamic scenes. We also contribute an efficient implementation that we will make available for research purposes. Compared to existing methods, InstantAvatar converges 130x faster and can be trained in minutes instead of hours. It achieves comparable or even better reconstruction quality and novel pose synthesis results. When given the same time budget, our method significantly outperforms SoTA methods. InstantAvatar can yield acceptable visual quality in as little as 10 seconds training time.

Chen Guo, Tianjian Jiang, Xu Chen et al.

We present Vid2Avatar, a method to learn human avatars from monocular in-the-wild videos. Reconstructing humans that move naturally from monocular in-the-wild videos is difficult. Solving it requires accurately separating humans from arbitrary backgrounds. Moreover, it requires reconstructing detailed 3D surface from short video sequences, making it even more challenging. Despite these challenges, our method does not require any groundtruth supervision or priors extracted from large datasets of clothed human scans, nor do we rely on any external segmentation modules. Instead, it solves the tasks of scene decomposition and surface reconstruction directly in 3D by modeling both the human and the background in the scene jointly, parameterized via two separate neural fields. Specifically, we define a temporally consistent human representation in canonical space and formulate a global optimization over the background model, the canonical human shape and texture, and per-frame human pose parameters. A coarse-to-fine sampling strategy for volume rendering and novel objectives are introduced for a clean separation of dynamic human and static background, yielding detailed and robust 3D human geometry reconstructions. We evaluate our methods on publicly available datasets and show improvements over prior art.

Seyedmorteza Sadat, Jakob Buhmann, Derek Bradley et al.

While conditional diffusion models are known to have good coverage of the data distribution, they still face limitations in output diversity, particularly when sampled with a high classifier-free guidance scale for optimal image quality or when trained on small datasets. We attribute this problem to the role of the conditioning signal in inference and offer an improved sampling strategy for diffusion models that can increase generation diversity, especially at high guidance scales, with minimal loss of sample quality. Our sampling strategy anneals the conditioning signal by adding scheduled, monotonically decreasing Gaussian noise to the conditioning vector during inference to balance diversity and condition alignment. Our Condition-Annealed Diffusion Sampler (CADS) can be used with any pretrained model and sampling algorithm, and we show that it boosts the diversity of diffusion models in various conditional generation tasks. Further, using an existing pretrained diffusion model, CADS achieves a new state-of-the-art FID of 1.70 and 2.31 for class-conditional ImageNet generation at 256$\times$256 and 512$\times$512 respectively.

Yifei Yin, Chen Guo, Manuel Kaufmann et al.

We propose Hi4D, a method and dataset for the automatic analysis of physically close human-human interaction under prolonged contact. Robustly disentangling several in-contact subjects is a challenging task due to occlusions and complex shapes. Hence, existing multi-view systems typically fuse 3D surfaces of close subjects into a single, connected mesh. To address this issue we leverage i) individually fitted neural implicit avatars; ii) an alternating optimization scheme that refines pose and surface through periods of close proximity; and iii) thus segment the fused raw scans into individual instances. From these instances we compile Hi4D dataset of 4D textured scans of 20 subject pairs, 100 sequences, and a total of more than 11K frames. Hi4D contains rich interaction-centric annotations in 2D and 3D alongside accurately registered parametric body models. We define varied human pose and shape estimation tasks on this dataset and provide results from state-of-the-art methods on these benchmarks.

Hsuan-I Ho, Jie Song, Otmar Hilliges

A long-standing goal of 3D human reconstruction is to create lifelike and fully detailed 3D humans from single-view images. The main challenge lies in inferring unknown body shapes, appearances, and clothing details in areas not visible in the images. To address this, we propose SiTH, a novel pipeline that uniquely integrates an image-conditioned diffusion model into a 3D mesh reconstruction workflow. At the core of our method lies the decomposition of the challenging single-view reconstruction problem into generative hallucination and reconstruction subproblems. For the former, we employ a powerful generative diffusion model to hallucinate unseen back-view appearance based on the input images. For the latter, we leverage skinned body meshes as guidance to recover full-body texture meshes from the input and back-view images. SiTH requires as few as 500 3D human scans for training while maintaining its generality and robustness to diverse images. Extensive evaluations on two 3D human benchmarks, including our newly created one, highlighted our method's superior accuracy and perceptual quality in 3D textured human reconstruction. Our code and evaluation benchmark are available at https://ait.ethz.ch/sith

Manuel Kaufmann, Jie Song, Chen Guo et al.

We present EMDB, the Electromagnetic Database of Global 3D Human Pose and Shape in the Wild. EMDB is a novel dataset that contains high-quality 3D SMPL pose and shape parameters with global body and camera trajectories for in-the-wild videos. We use body-worn, wireless electromagnetic (EM) sensors and a hand-held iPhone to record a total of 58 minutes of motion data, distributed over 81 indoor and outdoor sequences and 10 participants. Together with accurate body poses and shapes, we also provide global camera poses and body root trajectories. To construct EMDB, we propose a multi-stage optimization procedure, which first fits SMPL to the 6-DoF EM measurements and then refines the poses via image observations. To achieve high-quality results, we leverage a neural implicit avatar model to reconstruct detailed human surface geometry and appearance, which allows for improved alignment and smoothness via a dense pixel-level objective. Our evaluations, conducted with a multi-view volumetric capture system, indicate that EMDB has an expected accuracy of 2.3 cm positional and 10.6 degrees angular error, surpassing the accuracy of previous in-the-wild datasets. We evaluate existing state-of-the-art monocular RGB methods for camera-relative and global pose estimation on EMDB. EMDB is publicly available under https://ait.ethz.ch/emdb

Yufeng Zheng, Xueting Li, Koki Nagano et al.

Large-scale diffusion generative models are greatly simplifying image, video and 3D asset creation from user-provided text prompts and images. However, the challenging problem of text-to-4D dynamic 3D scene generation with diffusion guidance remains largely unexplored. We propose Dream-in-4D, which features a novel two-stage approach for text-to-4D synthesis, leveraging (1) 3D and 2D diffusion guidance to effectively learn a high-quality static 3D asset in the first stage; (2) a deformable neural radiance field that explicitly disentangles the learned static asset from its deformation, preserving quality during motion learning; and (3) a multi-resolution feature grid for the deformation field with a displacement total variation loss to effectively learn motion with video diffusion guidance in the second stage. Through a user preference study, we demonstrate that our approach significantly advances image and motion quality, 3D consistency and text fidelity for text-to-4D generation compared to baseline approaches. Thanks to its motion-disentangled representation, Dream-in-4D can also be easily adapted for controllable generation where appearance is defined by one or multiple images, without the need to modify the motion learning stage. Thus, our method offers, for the first time, a unified approach for text-to-4D, image-to-4D and personalized 4D generation tasks.

Yiming Zhao, Denys Rozumnyi, Jie Song et al.

We propose a method to estimate 3D human poses from substantially blurred images. The key idea is to tackle the inverse problem of image deblurring by modeling the forward problem with a 3D human model, a texture map, and a sequence of poses to describe human motion. The blurring process is then modeled by a temporal image aggregation step. Using a differentiable renderer, we can solve the inverse problem by backpropagating the pixel-wise reprojection error to recover the best human motion representation that explains a single or multiple input images. Since the image reconstruction loss alone is insufficient, we present additional regularization terms. To the best of our knowledge, we present the first method to tackle this problem. Our method consistently outperforms other methods on significantly blurry inputs since they lack one or multiple key functionalities that our method unifies, i.e. image deblurring with sub-frame accuracy and explicit 3D modeling of non-rigid human motion.

Hui Zhang, Sammy Christen, Zicong Fan et al.

We present ArtiGrasp, a novel method to synthesize bi-manual hand-object interactions that include grasping and articulation. This task is challenging due to the diversity of the global wrist motions and the precise finger control that are necessary to articulate objects. ArtiGrasp leverages reinforcement learning and physics simulations to train a policy that controls the global and local hand pose. Our framework unifies grasping and articulation within a single policy guided by a single hand pose reference. Moreover, to facilitate the training of the precise finger control required for articulation, we present a learning curriculum with increasing difficulty. It starts with single-hand manipulation of stationary objects and continues with multi-agent training including both hands and non-stationary objects. To evaluate our method, we introduce Dynamic Object Grasping and Articulation, a task that involves bringing an object into a target articulated pose. This task requires grasping, relocation, and articulation. We show our method's efficacy towards this task. We further demonstrate that our method can generate motions with noisy hand-object pose estimates from an off-the-shelf image-based regressor.

Hsuan-I Ho, Lixin Xue, Jie Song et al.

In this paper, we propose a novel hybrid representation and end-to-end trainable network architecture to model fully editable and customizable neural avatars. At the core of our work lies a representation that combines the modeling power of neural fields with the ease of use and inherent 3D consistency of skinned meshes. To this end, we construct a trainable feature codebook to store local geometry and texture features on the vertices of a deformable body model, thus exploiting its consistent topology under articulation. This representation is then employed in a generative auto-decoder architecture that admits fitting to unseen scans and sampling of realistic avatars with varied appearances and geometries. Furthermore, our representation allows local editing by swapping local features between 3D assets. To verify our method for avatar creation and editing, we contribute a new high-quality dataset, dubbed CustomHumans, for training and evaluation. Our experiments quantitatively and qualitatively show that our method generates diverse detailed avatars and achieves better model fitting performance compared to state-of-the-art methods. Our code and dataset are available at https://custom-humans.github.io/.

Jona Braun, Sammy Christen, Muhammed Kocabas et al.

We propose a physics-based method for synthesizing dexterous hand-object interactions in a full-body setting. While recent advancements have addressed specific facets of human-object interactions, a comprehensive physics-based approach remains a challenge. Existing methods often focus on isolated segments of the interaction process and rely on data-driven techniques that may result in artifacts. In contrast, our proposed method embraces reinforcement learning (RL) and physics simulation to mitigate the limitations of data-driven approaches. Through a hierarchical framework, we first learn skill priors for both body and hand movements in a decoupled setting. The generic skill priors learn to decode a latent skill embedding into the motion of the underlying part. A high-level policy then controls hand-object interactions in these pretrained latent spaces, guided by task objectives of grasping and 3D target trajectory following. It is trained using a novel reward function that combines an adversarial style term with a task reward, encouraging natural motions while fulfilling the task incentives. Our method successfully accomplishes the complete interaction task, from approaching an object to grasping and subsequent manipulation. We compare our approach against kinematics-based baselines and show that it leads to more physically plausible motions.

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.

Shrisha Bharadwaj, Yufeng Zheng, Otmar Hilliges et al.

Our goal is to efficiently learn personalized animatable 3D head avatars from videos that are geometrically accurate, realistic, relightable, and compatible with current rendering systems. While 3D meshes enable efficient processing and are highly portable, they lack realism in terms of shape and appearance. Neural representations, on the other hand, are realistic but lack compatibility and are slow to train and render. Our key insight is that it is possible to efficiently learn high-fidelity 3D mesh representations via differentiable rendering by exploiting highly-optimized methods from traditional computer graphics and approximating some of the components with neural networks. To that end, we introduce FLARE, a technique that enables the creation of animatable and relightable mesh avatars from a single monocular video. First, we learn a canonical geometry using a mesh representation, enabling efficient differentiable rasterization and straightforward animation via learned blendshapes and linear blend skinning weights. Second, we follow physically-based rendering and factor observed colors into intrinsic albedo, roughness, and a neural representation of the illumination, allowing the learned avatars to be relit in novel scenes. Since our input videos are captured on a single device with a narrow field of view, modeling the surrounding environment light is non-trivial. Based on the split-sum approximation for modeling specular reflections, we address this by approximating the pre-filtered environment map with a multi-layer perceptron (MLP) modulated by the surface roughness, eliminating the need to explicitly model the light. We demonstrate that our mesh-based avatar formulation, combined with learned deformation, material, and lighting MLPs, produces avatars with high-quality geometry and appearance, while also being efficient to train and render compared to existing approaches.

Muhammed Kocabas, Ye Yuan, Pavlo Molchanov et al.

We present a method to estimate human motion in a global scene from moving cameras. This is a highly challenging task due to the coupling of human and camera motions in the video. To address this problem, we propose a joint optimization framework that disentangles human and camera motions using both foreground human motion priors and background scene features. Unlike existing methods that use SLAM as initialization, we propose to tightly integrate SLAM and human motion priors in an optimization that is inspired by bundle adjustment. Specifically, we optimize human and camera motions to match both the observed human pose and scene features. This design combines the strengths of SLAM and motion priors, which leads to significant improvements in human and camera motion estimation. We additionally introduce a motion prior that is suitable for batch optimization, making our approach significantly more efficient than existing approaches. Finally, we propose a novel synthetic dataset that enables evaluating camera motion in addition to human motion from dynamic videos. Experiments on the synthetic and real-world RICH datasets demonstrate that our approach substantially outperforms prior art in recovering both human and camera motions.

Seyedmorteza Sadat, Manuel Kansy, Otmar Hilliges et al.

Classifier-free guidance (CFG) has become the standard method for enhancing the quality of conditional diffusion models. However, employing CFG requires either training an unconditional model alongside the main diffusion model or modifying the training procedure by periodically inserting a null condition. There is also no clear extension of CFG to unconditional models. In this paper, we revisit the core principles of CFG and introduce a new method, independent condition guidance (ICG), which provides the benefits of CFG without the need for any special training procedures. Our approach streamlines the training process of conditional diffusion models and can also be applied during inference on any pre-trained conditional model. Additionally, by leveraging the time-step information encoded in all diffusion networks, we propose an extension of CFG, called time-step guidance (TSG), which can be applied to any diffusion model, including unconditional ones. Our guidance techniques are easy to implement and have the same sampling cost as CFG. Through extensive experiments, we demonstrate that ICG matches the performance of standard CFG across various conditional diffusion models. Moreover, we show that TSG improves generation quality in a manner similar to CFG, without relying on any conditional information.

Marcel C. Bühler, Kripasindhu Sarkar, Tanmay Shah et al.

NeRFs have enabled highly realistic synthesis of human faces including complex appearance and reflectance effects of hair and skin. These methods typically require a large number of multi-view input images, making the process hardware intensive and cumbersome, limiting applicability to unconstrained settings. We propose a novel volumetric human face prior that enables the synthesis of ultra high-resolution novel views of subjects that are not part of the prior's training distribution. This prior model consists of an identity-conditioned NeRF, trained on a dataset of low-resolution multi-view images of diverse humans with known camera calibration. A simple sparse landmark-based 3D alignment of the training dataset allows our model to learn a smooth latent space of geometry and appearance despite a limited number of training identities. A high-quality volumetric representation of a novel subject can be obtained by model fitting to 2 or 3 camera views of arbitrary resolution. Importantly, our method requires as few as two views of casually captured images as input at inference time.

Boxiang Rong, Artur Grigorev, Wenbo Wang et al.

We introduce Gaussian Garments, a novel approach for reconstructing realistic simulation-ready garment assets from multi-view videos. Our method represents garments with a combination of a 3D mesh and a Gaussian texture that encodes both the color and high-frequency surface details. This representation enables accurate registration of garment geometries to multi-view videos and helps disentangle albedo textures from lighting effects. Furthermore, we demonstrate how a pre-trained graph neural network (GNN) can be fine-tuned to replicate the real behavior of each garment. The reconstructed Gaussian Garments can be automatically combined into multi-garment outfits and animated with the fine-tuned GNN.

Sanghwan Kim, Daoji Huang, Yongqin Xian et al.

Understanding human activity is a crucial yet intricate task in egocentric vision, a field that focuses on capturing visual perspectives from the camera wearer's viewpoint. Traditional methods heavily rely on representation learning that is trained on a large amount of video data. However, a major challenge arises from the difficulty of obtaining effective video representation. This difficulty stems from the complex and variable nature of human activities, which contrasts with the limited availability of data. In this study, we introduce PALM, an approach that tackles the task of long-term action anticipation, which aims to forecast forthcoming sequences of actions over an extended period. Our method PALM incorporates an action recognition model to track previous action sequences and a vision-language model to articulate relevant environmental details. By leveraging the context provided by these past events, we devise a prompting strategy for action anticipation using large language models (LLMs). Moreover, we implement maximal marginal relevance for example selection to facilitate in-context learning of the LLMs. Our experimental results demonstrate that PALM surpasses the state-of-the-art methods in the task of long-term action anticipation on the Ego4D benchmark. We further validate PALM on two additional benchmarks, affirming its capacity for generalization across intricate activities with different sets of taxonomies.

Sammy Christen, Lan Feng, Wei Yang et al.

Vision-based human-to-robot handover is an important and challenging task in human-robot interaction. Recent work has attempted to train robot policies by interacting with dynamic virtual humans in simulated environments, where the policies can later be transferred to the real world. However, a major bottleneck is the reliance on human motion capture data, which is expensive to acquire and difficult to scale to arbitrary objects and human grasping motions. In this paper, we introduce a framework that can generate plausible human grasping motions suitable for training the robot. To achieve this, we propose a hand-object synthesis method that is designed to generate handover-friendly motions similar to humans. This allows us to generate synthetic training and testing data with 100x more objects than previous work. In our experiments, we show that our method trained purely with synthetic data is competitive with state-of-the-art methods that rely on real human motion data both in simulation and on a real system. In addition, we can perform evaluations on a larger scale compared to prior work. With our newly introduced test set, we show that our model can better scale to a large variety of unseen objects and human motions compared to the baselines. Project page: https://eth-ait.github.io/synthetic-handovers/

Malte Prinzler, Otmar Hilliges, Justus Thies

We present Depth-aware Image-based NEural Radiance fields (DINER). Given a sparse set of RGB input views, we predict depth and feature maps to guide the reconstruction of a volumetric scene representation that allows us to render 3D objects under novel views. Specifically, we propose novel techniques to incorporate depth information into feature fusion and efficient scene sampling. In comparison to the previous state of the art, DINER achieves higher synthesis quality and can process input views with greater disparity. This allows us to capture scenes more completely without changing capturing hardware requirements and ultimately enables larger viewpoint changes during novel view synthesis. We evaluate our method by synthesizing novel views, both for human heads and for general objects, and observe significantly improved qualitative results and increased perceptual metrics compared to the previous state of the art. The code is publicly available for research purposes.

Andrea Ziani, Zicong Fan, Muhammed Kocabas et al.

We introduce TempCLR, a new time-coherent contrastive learning approach for the structured regression task of 3D hand reconstruction. Unlike previous time-contrastive methods for hand pose estimation, our framework considers temporal consistency in its augmentation scheme, and accounts for the differences of hand poses along the temporal direction. Our data-driven method leverages unlabelled videos and a standard CNN, without relying on synthetic data, pseudo-labels, or specialized architectures. Our approach improves the performance of fully-supervised hand reconstruction methods by 15.9% and 7.6% in PA-V2V on the HO-3D and FreiHAND datasets respectively, thus establishing new state-of-the-art performance. Finally, we demonstrate that our approach produces smoother hand reconstructions through time, and is more robust to heavy occlusions compared to the previous state-of-the-art which we show quantitatively and qualitatively. Our code and models will be available at https://eth-ait.github.io/tempclr.

Gengyan Li, Abhimitra Meka, Franziska Müller et al.

A unique challenge in creating high-quality animatable and relightable 3D avatars of people is modeling human eyes. The challenge of synthesizing eyes is multifold as it requires 1) appropriate representations for the various components of the eye and the periocular region for coherent viewpoint synthesis, capable of representing diffuse, refractive and highly reflective surfaces, 2) disentangling skin and eye appearance from environmental illumination such that it may be rendered under novel lighting conditions, and 3) capturing eyeball motion and the deformation of the surrounding skin to enable re-gazing. These challenges have traditionally necessitated the use of expensive and cumbersome capture setups to obtain high-quality results, and even then, modeling of the eye region holistically has remained elusive. We present a novel geometry and appearance representation that enables high-fidelity capture and photorealistic animation, view synthesis and relighting of the eye region using only a sparse set of lights and cameras. Our hybrid representation combines an explicit parametric surface model for the eyeball with implicit deformable volumetric representations for the periocular region and the interior of the eye. This novel hybrid model has been designed to address the various parts of that challenging facial area - the explicit eyeball surface allows modeling refraction and high-frequency specular reflection at the cornea, whereas the implicit representation is well suited to model lower-frequency skin reflection via spherical harmonics and can represent non-surface structures such as hair or diffuse volumetric bodies, both of which are a challenge for explicit surface models. We show that for high-resolution close-ups of the eye, our model can synthesize high-fidelity animated gaze from novel views under unseen illumination conditions.

Chen Guo, Tianjian Jiang, Manuel Kaufmann et al.

While previous years have seen great progress in the 3D reconstruction of humans from monocular videos, few of the state-of-the-art methods are able to handle loose garments that exhibit large non-rigid surface deformations during articulation. This limits the application of such methods to humans that are dressed in standard pants or T-shirts. Our method, ReLoo, overcomes this limitation and reconstructs high-quality 3D models of humans dressed in loose garments from monocular in-the-wild videos. To tackle this problem, we first establish a layered neural human representation that decomposes clothed humans into a neural inner body and outer clothing. On top of the layered neural representation, we further introduce a non-hierarchical virtual bone deformation module for the clothing layer that can freely move, which allows the accurate recovery of non-rigidly deforming loose clothing. A global optimization jointly optimizes the shape, appearance, and deformations of the human body and clothing via multi-layer differentiable volume rendering. To evaluate ReLoo, we record subjects with dynamically deforming garments in a multi-view capture studio. This evaluation, both on existing and our novel dataset, demonstrates ReLoo's clear superiority over prior art on both indoor datasets and in-the-wild videos.

Feichi Lu, Zijian Dong, Jie Song et al.

Despite progress in human motion capture, existing multi-view methods often face challenges in estimating the 3D pose and shape of multiple closely interacting people. This difficulty arises from reliance on accurate 2D joint estimations, which are hard to obtain due to occlusions and body contact when people are in close interaction. To address this, we propose a novel method leveraging the personalized implicit neural avatar of each individual as a prior, which significantly improves the robustness and precision of this challenging pose estimation task. Concretely, the avatars are efficiently reconstructed via layered volume rendering from sparse multi-view videos. The reconstructed avatar prior allows for the direct optimization of 3D poses based on color and silhouette rendering loss, bypassing the issues associated with noisy 2D detections. To handle interpenetration, we propose a collision loss on the overlapping shape regions of avatars to add penetration constraints. Moreover, both 3D poses and avatars are optimized in an alternating manner. Our experimental results demonstrate state-of-the-art performance on several public datasets.

Marco Bagatella, Sammy Christen, Otmar Hilliges

Efficient exploration is a crucial challenge in deep reinforcement learning. Several methods, such as behavioral priors, are able to leverage offline data in order to efficiently accelerate reinforcement learning on complex tasks. However, if the task at hand deviates excessively from the demonstrated task, the effectiveness of such methods is limited. In our work, we propose to learn features from offline data that are shared by a more diverse range of tasks, such as correlation between actions and directedness. Therefore, we introduce state-free priors, which directly model temporal consistency in demonstrated trajectories, and are capable of driving exploration in complex tasks, even when trained on data collected on simpler tasks. Furthermore, we introduce a novel integration scheme for action priors in off-policy reinforcement learning by dynamically sampling actions from a probabilistic mixture of policy and action prior. We compare our approach against strong baselines and provide empirical evidence that it can accelerate reinforcement learning in long-horizon continuous control tasks under sparse reward settings.

Núria Armengol Urpí, Marco Bagatella, Otmar Hilliges et al.

Real-world robotic manipulation tasks remain an elusive challenge, since they involve both fine-grained environment interaction, as well as the ability to plan for long-horizon goals. Although deep reinforcement learning (RL) methods have shown encouraging results when planning end-to-end in high-dimensional environments, they remain fundamentally limited by poor sample efficiency due to inefficient exploration, and by the complexity of credit assignment over long horizons. In this work, we present Efficient Learning of High-Level Plans from Play (ELF-P), a framework for robotic learning that bridges motion planning and deep RL to achieve long-horizon complex manipulation tasks. We leverage task-agnostic play data to learn a discrete behavioral prior over object-centric primitives, modeling their feasibility given the current context. We then design a high-level goal-conditioned policy which (1) uses primitives as building blocks to scaffold complex long-horizon tasks and (2) leverages the behavioral prior to accelerate learning. We demonstrate that ELF-P has significantly better sample efficiency than relevant baselines over multiple realistic manipulation tasks and learns policies that can be easily transferred to physical hardware.

Mengfan Wu, Thomas Langerak, Otmar Hilliges et al.

Tracking passive magnetic markers plays a vital role in advancing healthcare and robotics, offering the potential to significantly improve the precision and efficiency of systems. This technology is key to developing smarter, more responsive tools and devices, such as enhanced surgical instruments, precise diagnostic tools, and robots with improved environmental interaction capabilities. However, traditionally, the tracking of magnetic markers is computationally expensive due to the requirement for iterative optimization procedures. Moreover, these methods depend on the magnetic dipole model for their optimization function, which can yield imprecise outcomes due to the model's significant inaccuracies when dealing with short distances between non-spherical magnet and sensor.Our paper introduces a novel approach that leverages neural networks to bypass these limitations, directly inferring the marker's position and orientation to accurately determine the magnet's 5 DoF in a single step without initial estimation. Although our method demands an extensive supervised training phase, we mitigate this by introducing a computationally more efficient method to generate synthetic, yet realistic data using Finite Element Methods simulations. The benefits of fast and accurate inference significantly outweigh the offline training preparation. In our evaluation, we use different cylindrical magnets, tracked with a square array of 16 sensors. We perform the sensors' reading and position inference on a portable, neural networks-oriented single-board computer, ensuring a compact setup. We benchmark our prototype against vision-based ground truth data, achieving a mean positional error of 4 mm and an orientation error of 8 degrees within a 0.2x0.2x0.15 m working volume. These results showcase our prototype's ability to balance accuracy and compactness effectively in tracking 5 DoF.

Emre Aksan, Shugao Ma, Akin Caliskan et al.

Neural face avatars that are trained from multi-view data captured in camera domes can produce photo-realistic 3D reconstructions. However, at inference time, they must be driven by limited inputs such as partial views recorded by headset-mounted cameras or a front-facing camera, and sparse facial landmarks. To mitigate this asymmetry, we introduce a prior model that is conditioned on the runtime inputs and tie this prior space to the 3D face model via a normalizing flow in the latent space. Our proposed model, LiP-Flow, consists of two encoders that learn representations from the rich training-time and impoverished inference-time observations. A normalizing flow bridges the two representation spaces and transforms latent samples from one domain to another, allowing us to define a latent likelihood objective. We trained our model end-to-end to maximize the similarity of both representation spaces and the reconstruction quality, making the 3D face model aware of the limited driving signals. We conduct extensive evaluations where the latent codes are optimized to reconstruct 3D avatars from partial or sparse observations. We show that our approach leads to an expressive and effective prior, capturing facial dynamics and subtle expressions better.

Kaiyue Shen, Chen Guo, Manuel Kaufmann et al.

We present X-Avatar, a novel avatar model that captures the full expressiveness of digital humans to bring about life-like experiences in telepresence, AR/VR and beyond. Our method models bodies, hands, facial expressions and appearance in a holistic fashion and can be learned from either full 3D scans or RGB-D data. To achieve this, we propose a part-aware learned forward skinning module that can be driven by the parameter space of SMPL-X, allowing for expressive animation of X-Avatars. To efficiently learn the neural shape and deformation fields, we propose novel part-aware sampling and initialization strategies. This leads to higher fidelity results, especially for smaller body parts while maintaining efficient training despite increased number of articulated bones. To capture the appearance of the avatar with high-frequency details, we extend the geometry and deformation fields with a texture network that is conditioned on pose, facial expression, geometry and the normals of the deformed surface. We show experimentally that our method outperforms strong baselines in both data domains both quantitatively and qualitatively on the animation task. To facilitate future research on expressive avatars we contribute a new dataset, called X-Humans, containing 233 sequences of high-quality textured scans from 20 participants, totalling 35,500 data frames.

Emre Aksan, Manuel Kaufmann, Peng Cao et al.

We propose a novel Transformer-based architecture for the task of generative modelling of 3D human motion. Previous work commonly relies on RNN-based models considering shorter forecast horizons reaching a stationary and often implausible state quickly. Recent studies show that implicit temporal representations in the frequency domain are also effective in making predictions for a predetermined horizon. Our focus lies on learning spatio-temporal representations autoregressively and hence generation of plausible future developments over both short and long term. The proposed model learns high dimensional embeddings for skeletal joints and how to compose a temporally coherent pose via a decoupled temporal and spatial self-attention mechanism. Our dual attention concept allows the model to access current and past information directly and to capture both the structural and the temporal dependencies explicitly. We show empirically that this effectively learns the underlying motion dynamics and reduces error accumulation over time observed in auto-regressive models. Our model is able to make accurate short-term predictions and generate plausible motion sequences over long horizons. We make our code publicly available at https://github.com/eth-ait/motion-transformer.

Marcel Bühler, Seonwook Park, Shalini De Mello et al.

Accurately labeled real-world training data can be scarce, and hence recent works adapt, modify or generate images to boost target datasets. However, retaining relevant details from input data in the generated images is challenging and failure could be critical to the performance on the final task. In this work, we synthesize person-specific eye images that satisfy a given semantic segmentation mask (content), while following the style of a specified person from only a few reference images. We introduce two approaches, (a) one used to win the OpenEDS Synthetic Eye Generation Challenge at ICCV 2019, and (b) a principled approach to solving the problem involving simultaneous injection of style and content information at multiple scales. Our implementation is available at https://github.com/mcbuehler/Seg2Eye.

Seonwook Park, Shalini De Mello, Pavlo Molchanov et al.

Inter-personal anatomical differences limit the accuracy of person-independent gaze estimation networks. Yet there is a need to lower gaze errors further to enable applications requiring higher quality. Further gains can be achieved by personalizing gaze networks, ideally with few calibration samples. However, over-parameterized neural networks are not amenable to learning from few examples as they can quickly over-fit. We embrace these challenges and propose a novel framework for Few-shot Adaptive GaZE Estimation (FAZE) for learning person-specific gaze networks with very few (less than or equal to 9) calibration samples. FAZE learns a rotation-aware latent representation of gaze via a disentangling encoder-decoder architecture along with a highly adaptable gaze estimator trained using meta-learning. It is capable of adapting to any new person to yield significant performance gains with as few as 3 samples, yielding state-of-the-art performance of 3.18 degrees on GazeCapture, a 19% improvement over prior art. We open-source our code at https://github.com/NVlabs/few_shot_gaze

Hui Zhang, Sammy Christen, Zicong Fan et al.

Human hands possess the dexterity to interact with diverse objects such as grasping specific parts of the objects and/or approaching them from desired directions. More importantly, humans can grasp objects of any shape without object-specific skills. Recent works synthesize grasping motions following single objectives such as a desired approach heading direction or a grasping area. Moreover, they usually rely on expensive 3D hand-object data during training and inference, which limits their capability to synthesize grasping motions for unseen objects at scale. In this paper, we unify the generation of hand-object grasping motions across multiple motion objectives, diverse object shapes and dexterous hand morphologies in a policy learning framework GraspXL. The objectives are composed of the graspable area, heading direction during approach, wrist rotation, and hand position. Without requiring any 3D hand-object interaction data, our policy trained with 58 objects can robustly synthesize diverse grasping motions for more than 500k unseen objects with a success rate of 82.2%. At the same time, the policy adheres to objectives, which enables the generation of diverse grasps per object. Moreover, we show that our framework can be deployed to different dexterous hands and work with reconstructed or generated objects. We quantitatively and qualitatively evaluate our method to show the efficacy of our approach. Our model, code, and the large-scale generated motions are available at https://eth-ait.github.io/graspxl/.

Wenbo Wang, Hsuan-I Ho, Chen Guo et al.

The studies of human clothing for digital avatars have predominantly relied on synthetic datasets. While easy to collect, synthetic data often fall short in realism and fail to capture authentic clothing dynamics. Addressing this gap, we introduce 4D-DRESS, the first real-world 4D dataset advancing human clothing research with its high-quality 4D textured scans and garment meshes. 4D-DRESS captures 64 outfits in 520 human motion sequences, amounting to 78k textured scans. Creating a real-world clothing dataset is challenging, particularly in annotating and segmenting the extensive and complex 4D human scans. To address this, we develop a semi-automatic 4D human parsing pipeline. We efficiently combine a human-in-the-loop process with automation to accurately label 4D scans in diverse garments and body movements. Leveraging precise annotations and high-quality garment meshes, we establish several benchmarks for clothing simulation and reconstruction. 4D-DRESS offers realistic and challenging data that complements synthetic sources, paving the way for advancements in research of lifelike human clothing. Website: https://ait.ethz.ch/4d-dress.

Zicong Fan, Takehiko Ohkawa, Linlin Yang et al.

We interact with the world with our hands and see it through our own (egocentric) perspective. A holistic 3Dunderstanding of such interactions from egocentric views is important for tasks in robotics, AR/VR, action recognition and motion generation. Accurately reconstructing such interactions in 3D is challenging due to heavy occlusion, viewpoint bias, camera distortion, and motion blur from the head movement. To this end, we designed the HANDS23 challenge based on the AssemblyHands and ARCTIC datasets with carefully designed training and testing splits. Based on the results of the top submitted methods and more recent baselines on the leaderboards, we perform a thorough analysis on 3D hand(-object) reconstruction tasks. Our analysis demonstrates the effectiveness of addressing distortion specific to egocentric cameras, adopting high-capacity transformers to learn complex hand-object interactions, and fusing predictions from different views. Our study further reveals challenging scenarios intractable with state-of-the-art methods, such as fast hand motion, object reconstruction from narrow egocentric views, and close contact between two hands and objects. Our efforts will enrich the community's knowledge foundation and facilitate future hand studies on egocentric hand-object interactions.

Vanessa Sklyarova, Egor Zakharov, Otmar Hilliges et al. · eth-zurich

We present HAAR, a new strand-based generative model for 3D human hairstyles. Specifically, based on textual inputs, HAAR produces 3D hairstyles that could be used as production-level assets in modern computer graphics engines. Current AI-based generative models take advantage of powerful 2D priors to reconstruct 3D content in the form of point clouds, meshes, or volumetric functions. However, by using the 2D priors, they are intrinsically limited to only recovering the visual parts. Highly occluded hair structures can not be reconstructed with those methods, and they only model the ''outer shell'', which is not ready to be used in physics-based rendering or simulation pipelines. In contrast, we propose a first text-guided generative method that uses 3D hair strands as an underlying representation. Leveraging 2D visual question-answering (VQA) systems, we automatically annotate synthetic hair models that are generated from a small set of artist-created hairstyles. This allows us to train a latent diffusion model that operates in a common hairstyle UV space. In qualitative and quantitative studies, we demonstrate the capabilities of the proposed model and compare it to existing hairstyle generation approaches.

Markos Diomataris, Nikos Athanasiou, Omid Taheri et al.

Synthesizing natural human motions that enable a 3D human avatar to walk and reach for arbitrary goals in 3D space remains an unsolved problem with many applications. Existing methods (data-driven or using reinforcement learning) are limited in terms of generalization and motion naturalness. A primary obstacle is the scarcity of training data that combines locomotion with goal reaching. To address this, we introduce WANDR, a data-driven model that takes an avatar's initial pose and a goal's 3D position and generates natural human motions that place the end effector (wrist) on the goal location. To solve this, we introduce novel intention features that drive rich goal-oriented movement. Intention guides the agent to the goal, and interactively adapts the generation to novel situations without needing to define sub-goals or the entire motion path. Crucially, intention allows training on datasets that have goal-oriented motions as well as those that do not. WANDR is a conditional Variational Auto-Encoder (c-VAE), which we train using the AMASS and CIRCLE datasets. We evaluate our method extensively and demonstrate its ability to generate natural and long-term motions that reach 3D goals and generalize to unseen goal locations. Our models and code are available for research purposes at wandr.is.tue.mpg.de.

Artur Grigorev, Giorgio Becherini, Michael J. Black et al.

Learning-based approaches to cloth simulation have started to show their potential in recent years. However, handling collisions and intersections in neural simulations remains a largely unsolved problem. In this work, we present \moniker{}, a learning-based solution for handling intersections in neural cloth simulations. Unlike conventional approaches that critically rely on intersection-free inputs, \moniker{} robustly recovers from intersections introduced through missed collisions, self-penetrating bodies, or errors in manually designed multi-layer outfits. The technical core of \moniker{} is a novel intersection contour loss that penalizes interpenetrations and encourages rapid resolution thereof. We integrate our intersection loss with a collision-avoiding repulsion objective into a neural cloth simulation method based on graph neural networks (GNNs). We demonstrate our method's ability across a challenging set of diverse multi-layer outfits under dynamic human motions. Our extensive analysis indicates that \moniker{} significantly improves collision handling for learned simulation and produces visually compelling results.