We introduce Dream, Lift, Animate (DLA), a novel framework that reconstructs animatable 3D human avatars from a single image. This is achieved by leveraging multiview generation, 3D Gaussian lifting, and pose-aware UVspace mapping of 3D Gaussians. Given an image, we first dream plausible multi-views using a video diffusion model, capturing rich geometric and appearance details. These views are then lifted into unstructured 3D Gaussians. To enable animation, we propose a transformer-based encoder that models global spatial relationships and projects these Gaussians into a structured latent representation aligned with the UV space of a parametric body model. This latent code is decoded into UV-space Gaussians that can be animated via body-driven deformation and rendered conditioned on pose and viewpoint. By anchoring Gaussians to the UV manifold, our method ensures consistency during animation while preserving fine visual details. DLA enables real-time rendering and intuitive editing without requiring post-processing. Our method outperforms state-of-the-art approaches on the ActorsHQ and 4D-Dress datasets in both perceptual quality and photometric accuracy. By combining the generative strengths of video diffusion models with a pose-aware UV-space Gaussian mapping, DLA bridges the gap between unstructured 3D representations and highfidelity, animation-ready avatars.

Despite transformative advances in generative motion synthesis, real-time interactive motion control remains dominated by traditional techniques. In this work, we identify two key challenges in bridging research and production: 1) Real-time scalability : Industry applications demand real-time generation of a vast repertoire of motion skills, while generative methods exhibit significant degradation in quality and scalability under real-time computation constraints, and 2) Integration : Industry applications demand fine-grained multi-modal control involving velocity commands, style selection, and precise keyframes, a need largely unmet by existing text- or tag-driven models. Moreover, a systematic motion design interface for generative models remains absent. To overcome these limitations, we introduce MotionBricks: a large-scale, real-time generative framework with a two-fold solution. First, we propose a large-scale modular latent generative backbone tailored for robust real-time motion generation, effectively modeling a dataset of over 350,000 motion clips with a single model. Second, we introduce smart primitives that provide a unified, robust, and intuitive interface for authoring both navigation and object interaction. Notably, MotionBricks applies to new downstream tasks in a zero-shot manner, where no fine-tuning or task-specific tagging is required. Applications can be designed in a plug-and-play manner like assembling bricks without expert animation knowledge, enabling an accessible interface for applications in animation and robotics. Quantitatively, we show that MotionBricks produces state-of-the-art motion quality on open-source and proprietary datasets of various scales, while also achieving a real-time throughput of 15,000 FPS with 2ms latency. We demonstrate the flexibility and robustness of MotionBricks in a complete production-level animation demo, covering navigation and object-scene interaction across various styles with a unified model. To showcase our framework's application beyond animation, we deploy MotionBricks on the Unitree G1 humanoid robot to demonstrate its flexibility and generalization for real-time robotic control.

Single-Image human mesh recovery is a challenging task due to the ill-posed nature of simultaneous body shape, pose, and camera estimation. Existing estimators work well on images taken from afar, but they break down as the person moves close to the camera. Moreover, current methods fail to achieve both accurate 3D pose and 2D alignment at the same time. Error is mainly introduced by inaccurate perspective projection heuristically derived from orthographic parameters. To resolve this long-standing challenge, we present our method BLADE which accurately recovers perspective parameters from a single image without heuristic assumptions. We start from the inverse relationship between perspective distortion and the person’s Z-translation Tz, and we show that Tzcan be reliably estimated from the image. We then discuss the important role of Tzfor accurate human mesh recovery estimated from closerange images. Finally, we show that, once Tzand the 3D human mesh are estimated, one can accurately recover the focal length and full 3D translation. Extensive experiments on standard benchmarks and real-world close-range images show that our method accurately recovers projection parameters from a single image, and consequently attains state-of-the-art accuracy on both 3D pose estimation and 2D alignment for a wide range of images.

We introduce SimAvatar, a framework designed to generate simulation-ready clothed 3D human avatars from a text prompt. Current text-driven human avatar generation methods either model hair, clothing, and the human body using a unified geometry or produce hair and garments that are not easily adaptable for simulation within existing simulation pipelines. The primary challenge lies in representing the hair and garment geometry in a way that allows leveraging established prior knowledge from foundational image diffusion models (e.g., Stable Diffusion) while being simulation-ready using either physics or neural simulators. To address this task, we propose a two-stage framework that combines the flexibility of 3D Gaussians with simulation-ready hair strands and garment meshes. Specifically, we first employ three text-conditioned 3D generative models to generate garment mesh, body shape and hair strands from the given text prompt. To leverage prior knowledge from foundational diffusion models, we attach 3D Gaussians to the body mesh, garment mesh, as well as hair strands and learn the avatar appearance through optimization. To drive the avatar given a pose sequence, we first apply physics simulators onto the garment meshes and hair strands. We then transfer the motion onto 3D Gaussians through carefully designed mechanisms for each body part. As a result, our synthesized avatars have vivid texture and realistic dynamic motion. To the best of our knowledge, our method is the first to produce highly realistic, fully simulation-ready 3D avatars, surpassing the capabilities of current approaches. Project page: https://research.nvidia.com/labs/dair/simavatar/

Human motion modeling traditionally separates motion generation and estimation into distinct tasks with specialized models. Motion generation models focus on creating diverse, realistic motions from inputs like text, audio, or keyframes, while motion estimation models aim to reconstruct accurate motion trajectories from observations like videos. Despite sharing underlying representations of temporal dynamics and kinematics, this separation limits knowledge transfer between tasks and requires maintaining separate models. We present GENMO, a unified Generalist Model for Human Motion that bridges motion estimation and generation in a single framework. Our key insight is to reformulate motion estimation as constrained motion generation, where the output motion must precisely satisfy observed conditioning signals. Leveraging the synergy between regression and diffusion, GENMO achieves accurate global motion estimation while enabling diverse motion generation. We also introduce an estimation-guided training objective that exploits in-the-wild videos with 2D annotations and text descriptions to enhance generative diversity. Furthermore, our novel architecture handles variable-length motions and mixed multimodal conditions (text, audio, video) at different time intervals, offering flexible control. This unified approach creates synergistic benefits: generative priors improve estimated motions under challenging conditions like occlusions, while diverse video data enhances generation capabilities. Extensive experiments demonstrate GENMO's effectiveness as a generalist framework that successfully handles multiple human motion tasks within a single model.

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.

We address the challenge of content diversity and controllability in pedestrian simulation for driving scenarios. Recent pedestrian animation frameworks have a significant limitation wherein they primarily focus on either following trajectory [48] or the content of the reference video [60], consequently overlooking the potential diversity of human motion within such scenarios. This limitation restricts the ability to generate pedestrian behaviors that exhibit a wider range of variations and realistic motions and therefore re-stricts its usage to provide rich motion content for other components in the driving simulation system, e.g., suddenly changed motion to which the autonomous vehicle should respond. In our approach, we strive to surpass the limitation by showcasing diverse human motions obtained from various sources, such as generated human motions, in ad-dition to following the given trajectory. The fundamental contribution of our framework lies in combining the motion tracking task with trajectory following, which enables the tracking of specific motion parts (e.g., upper body) while simultaneously following the given trajectory by a single policy. This way, we significantly enhance both the diver-sity of simulated human motion within the given scenario and the controllability of the content, including language-based control. Our framework facilitates the generation of a wide range of human motions, contributing to greater re-alism and adaptability in pedestrian simulations for driving scenarios.

Gaussian splatting has emerged as a powerful 3D representation that harnesses the advantages of both explicit (mesh) and implicit (NeRF) 3D representations. In this paper, we seek to leverage Gaussian splatting to generate realistic animatable avatars from textual descriptions, addressing the limitations (e.g., flexibility and efficiency) imposed by mesh or NeRF-based representations. However, a naive application of Gaussian splatting cannot generate high-quality animatable avatars and suffers from learning instability; it also cannot capture fine avatar geometries and often leads to degenerate body parts. To tackle these problems, we first propose a primitive-based 3D Gaussian representation where Gaussians are defined inside pose-driven primitives to facilitate animation. Second, to stabilize and amortize the learning of millions of Gaussians, we propose to use neural implicit fields to predict the Gaussian attributes (e.g., colors). Finally, to capture fine avatar geometries and extract detailed meshes, we propose a novel SDF-based implicit mesh learning approach for 3D Gaussians that regularizes the underlying geometries and extracts highly detailed textured meshes. Our proposed method, GAvatar, enables the large-scale generation of diverse animatable avatars using only text prompts. GAvatar significantly surpasses existing methods in terms of both appearance and geometry quality, and achieves extremely fast rendering (100 fps) at 1K resolution.

We introduce a method for generating realistic pedestrian trajectories and full-body animations that can be controlled to meet user-defined goals. We draw on recent advances in guided diffusion modeling to achieve test-time controllability of trajectories, which is normally only associated with rule-based systems. Our guided diffusion model allows users to constrain trajectories through target waypoints, speed, and specified social groups while accounting for the surrounding environment context. This trajectory diffusion model is integrated with a novel physics-based humanoid controller to form a closed-loop, full-body pedestrian animation system capable of placing large crowds in a simulated environment with varying terrains. We further propose utilizing the value function learned during RL training of the animation controller to guide diffusion to produce trajectories better suited for particular scenarios such as collision avoidance and traversing uneven terrain. Video results are available on the project page.

Denoising diffusion models hold great promise for generating diverse and realistic human motions. However, existing motion diffusion models largely disregard the laws of physics in the diffusion process and often generate physically-implausible motions with pronounced artifacts such as floating, foot sliding, and ground penetration. This seriously impacts the quality of generated motions and limits their real-world application. To address this issue, we present a novel physics-guided motion diffusion model (PhysDiff), which incorporates physical constraints into the diffusion process. Specifically, we propose a physics-based motion projection module that uses motion imitation in a physics simulator to project the denoised motion of a diffusion step to a physically-plausible motion. The projected motion is further used in the next diffusion step to guide the denoising diffusion process. Intuitively, the use of physics in our model iteratively pulls the motion toward a physically-plausible space, which cannot be achieved by simple post-processing. Experiments on large-scale human motion datasets show that our approach achieves state-of-the-art motion quality and improves physical plausibility drastically (>78% for all datasets).

Simulation has emerged as an indispensable tool for scaling and accelerating the development of self-driving systems. A critical aspect of this is simulating realistic and diverse human behavior and intent. In this work, we propose a holistic framework for learning physically plausible human dynamics from real driving scenarios, narrowing the gap between real and simulated human behavior in safety-critical applications. We show that state-of-the-art methods underperform in driving scenarios where video data is recorded from moving vehicles, and humans are frequently partially or fully occluded. Furthermore, existing methods often disregard the global scene where humans are situated, resulting in various motion artifacts like foot sliding, floating, or ground penetration. To address this challenge, we propose an approach that incorporates physics with a reinforcement learning-based motion controller to learn human dynamics for driving scenarios. Our framework can simulate physically plausible human dynamics that accurately match observed human motions and infill motions for occluded body parts, while improving the physical plausibility of the entire motion sequence. Experiments on the challenging Waymo Open Dataset show that our method outperforms state-of-the-art motion capture approaches significantly in recovering high-quality, physically plausible, and scene-aware human dynamics.

We present a system that learns diverse, physically simulated tennis skills from large-scale demonstrations of tennis play harvested from broadcast videos. Our approach is built upon hierarchical models, combining a low-level imitation policy and a high-level motion planning policy to steer the character in a motion embedding learned from broadcast videos. When deployed at scale on large video collections that encompass a vast set of examples of real-world tennis play, our approach can learn complex tennis shotmaking skills and realistically chain together multiple shots into extended rallies, using only simple rewards and without explicit annotations of stroke types. To address the low quality of motions extracted from broadcast videos, we correct estimated motion with physics-based imitation, and use a hybrid control policy that overrides erroneous aspects of the learned motion embedding with corrections predicted by the high-level policy. We demonstrate that our system produces controllers for physically-simulated tennis players that can hit the incoming ball to target positions accurately using a diverse array of strokes (serves, forehands, and backhands), spins (topspins and slices), and playing styles (one/two-handed backhands, left/right-handed play). Overall, our system can synthesize two physically simulated characters playing extended tennis rallies with simulated racket and ball dynamics. Code and data for this work is available at https://research.nvidia.com/labs/toronto-ai/vid2player3d/.

We present an approach for 3D global human mesh recovery from monocular videos recorded with dynamic cameras. Our approach is robust to severe and long-term occlusions and tracks human bodies even when they go outside the camera's field of view. To achieve this, we first propose a deep generative motion infiller, which autoregressively infills the body motions of occluded humans based on visible motions. Additionally, in contrast to prior work, our approach reconstructs human meshes in consistent global coordinates even with dynamic cameras. Since the joint reconstruction of human motions and camera poses is underconstrained, we propose a global trajectory predictor that generates global human trajectories based on local body movements. Using the predicted trajectories as anchors, we present a global optimization framework that refines the predicted trajectories and optimizes the camera poses to match the video evidence such as 2D keypoints. Experiments on challenging indoor and in-the-wild datasets with dynamic cameras demonstrate that the proposed approach outperforms prior methods significantly in terms of motion infilling and global mesh recovery.

We propose embodied scene-aware human pose estimation where we estimate 3D poses based on a simulated agent's proprioception and scene awareness, along with external third-person observations. Unlike prior methods that often resort to multistage optimization, non-causal inference, and complex contact modeling to estimate human pose and human scene interactions, our method is one-stage, causal, and recovers global 3D human poses in a simulated environment. Since 2D third-person observations are coupled with the camera pose, we propose to disentangle the camera pose and use a multi-step projection gradient defined in the global coordinate frame as the movement cue for our embodied agent. Leveraging a physics simulation and prescanned scenes (e.g., 3D mesh), we simulate our agent in everyday environments (library, office, bedroom, etc.) and equip our agent with environmental sensors to intelligently navigate and interact with the geometries of the scene. Our method also relies only on 2D keypoints and can be trained on synthetic datasets derived from popular human motion databases. To evaluate, we use the popular H36M and PROX datasets and achieve high quality pose estimation on the challenging PROX dataset without ever using PROX motion sequences for training. Code and videos are available on the project page.

Accurate estimation of 3D human motion from monocular video requires modeling both kinematics (body motion without physical forces) and dynamics (motion with physical forces). To demonstrate this, we present SimPoE, a Simulation-based approach for 3D human Pose Estimation, which integrates image-based kinematic inference and physics-based dynamics modeling. SimPoE learns a policy that takes as input the current-frame pose estimate and the next image frame to control a physically-simulated character to output the next-frame pose estimate. The policy contains a learnable kinematic pose refinement unit that uses 2D keypoints to iteratively refine its kinematic pose estimate of the next frame. Based on this refined kinematic pose, the policy learns to compute dynamics-based control (e.g., joint torques) of the character to advance the current-frame pose estimate to the pose estimate of the next frame. This design couples the kinematic pose refinement unit with the dynamics-based control generation unit, which are learned jointly with reinforcement learning to achieve accurate and physically-plausible pose estimation. Furthermore, we propose a meta-control mechanism that dynamically adjusts the character’s dynamics parameters based on the character state to attain more accurate pose estimates. Experiments on large-scale motion datasets demonstrate that our approach establishes the new state of the art in pose accuracy while ensuring physical plausibility.

Predicting accurate future trajectories of multiple agents is essential for autonomous systems but is challenging due to the complex interaction between agents and the uncertainty in each agent’s future behavior. Forecasting multi-agent trajectories requires modeling two key dimensions: (1) time dimension, where we model the influence of past agent states over future states; (2) social dimension, where we model how the state of each agent affects others. Most prior methods model these two dimensions separately, e.g., first using a temporal model to summarize features over time for each agent independently and then modeling the interaction of the summarized features with a social model. This approach is suboptimal since independent feature encoding over either the time or social dimension can result in a loss of information. Instead, we would prefer a method that allows an agent’s state at one time to directly affect another agent’s state at a future time. To this end, we propose a new Transformer, termed AgentFormer, that simultaneously models the time and social dimensions. The model leverages a sequence representation of multi-agent trajectories by flattening trajectory features across time and agents. Since standard attention operations disregard the agent identity of each element in the sequence, AgentFormer uses a novel agent-aware attention mechanism that preserves agent identities by attending to elements of the same agent differently than elements of other agents. Based on AgentFormer, we propose a stochastic multi-agent trajectory prediction model that can attend to features of any agent at any previous timestep when inferring an agent’s future position. The latent intent of all agents is also jointly modeled, allowing the stochasticity in one agent’s behavior to affect other agents. Extensive experiments show that our method significantly improves the state of the art on well-established pedestrian and autonomous driving datasets.

We propose a method for object-aware 3D egocentric pose estimation that tightly integrates kinematics modeling, dynamics modeling, and scene object information. Unlike prior kinematics or dynamics-based approaches where the two components are used disjointly, we synergize the two approaches via dynamics-regulated training. At each timestep, a kinematic model is used to provide a target pose using video evidence and simulation state. Then, a prelearned dynamics model attempts to mimic the kinematic pose in a physics simulator. By comparing the pose instructed by the kinematic model against the pose generated by the dynamics model, we can use their misalignment to further improve the kinematic model. By factoring in the 6DoF pose of objects (e.g., chairs, boxes) in the scene, we demonstrate for the first time, the ability to estimate physically-plausible 3D human-object interactions using a single wearable camera. We evaluate our egocentric pose estimation method in both controlled laboratory settings and real-world scenarios.

Automatically reasoning about future human behaviors is a difficult problem but has significant practical applications to assistive systems. Part of this difficulty stems from learning systems' inability to represent all kinds of behaviors. Some behaviors, such as motion, are best described with continuous representations, whereas others, such as picking up a cup, are best described with discrete representations. Furthermore, human behavior is generally not fixed: people can change their habits and routines. This suggests these systems must be able to learn and adapt continuously. In this work, we develop an efficient deep generative model to jointly forecast a person's future discrete actions and continuous motions. On a large-scale egocentric dataset, EPIC-KITCHENS, we observe our method generates high-quality and diverse samples while exhibiting better generalization than related generative models. Finally, we propose a variant to continually learn our model from streaming data, observe its practical effectiveness, and theoretically justify its learning efficiency.

We describe a method for 3D human pose estimation from transient images (i.e., a 3D spatio-temporal histogram of photons) acquired by an optical non-line-of-sight (NLOS) imaging system. Our method can perceive 3D human pose by 'looking around corners' through the use of light indirectly reflected by the environment. We bring together a diverse set of technologies from NLOS imaging, human pose estimation and deep reinforcement learning to construct an end-to-end data processing pipeline that converts a raw stream of photon measurements into a full 3D human pose sequence estimate. Our contributions are the design of data representation process which includes (1) a learnable inverse point spread function (PSF) to convert raw transient images into a deep feature vector; (2) a neural humanoid control policy conditioned on the transient image feature and learned from interactions with a physics simulator; and (3) a data synthesis and augmentation strategy based on depth data that can be transferred to a real-world NLOS imaging system. Our preliminary experiments suggest that our method is able to generalize to real-world NLOS measurement to estimate physically-valid 3D human poses.

Reinforcement learning has shown great promise for synthesizing realistic human behaviors by learning humanoid control policies from motion capture data. However, it is still very challenging to reproduce sophisticated human skills like ballet dance, or to stably imitate long-term human behaviors with complex transitions. The main difficulty lies in the dynamics mismatch between the humanoid model and real humans. That is, motions of real humans may not be physically possible for the humanoid model. To overcome the dynamics mismatch, we propose a novel approach, residual force control (RFC), that augments a humanoid control policy by adding external residual forces into the action space. During training, the RFC-based policy learns to apply residual forces to the humanoid to compensate for the dynamics mismatch and better imitate the reference motion. Experiments on a wide range of dynamic motions demonstrate that our approach outperforms state-of-the-art methods in terms of convergence speed and the quality of learned motions. Notably, we showcase a physics-based virtual character empowered by RFC that can perform highly agile ballet dance moves such as pirouette, arabesque and jeté. Furthermore, we propose a dual-policy control framework, where a kinematic policy and an RFC-based policy work in tandem to synthesize multi-modal infinite-horizon human motions without any task guidance or user input. Our approach is the first humanoid control method that successfully learns from a large-scale human motion dataset (Human3.6M) and generates diverse long-term motions. Code and videos are available at https://www.ye-yuan.com/rfc.

We present MonoEye, a multimodal human motion capture system using a single RGB camera with an ultra-wide fisheye lens, mounted on the user's chest. Existing optical motion capture systems use multiple cameras, which are synchronized and require camera calibration. These systems also have usability constraints that limit the user's movement and operating space. Since the MonoEye system is based on a wearable single RGB camera, the wearer's 3D body pose can be captured without space and environment limitations. The body pose, captured with our system, is aware of the camera orientation and therefore it is possible to recognize various motions that existing egocentric motion capture systems cannot recognize. Furthermore, the proposed system captures not only the wearer's body motion but also their viewport using the head pose estimation and an ultra-wide image. To implement robust multimodal motion capture, we design three deep neural networks: BodyPoseNet, HeadPoseNet, and CameraPoseNet, that estimate 3D body pose, head pose, and camera pose in real-time, respectively. We train these networks with our new extensive synthetic dataset providing 680K frames of renderings of people with a wide range of body shapes, clothing, actions, backgrounds, and lighting conditions. To demonstrate the interactive potential of the MonoEye system, we present several application examples from common body gestural to context-aware interactions.

The automatic recognition of how people use their hands and fingers in natural settings -- without instrumenting the fingers -- can be useful for many mobile computing applications. To achieve such an interface, we propose a vision-based 3D hand pose estimation framework using a wrist-worn camera. The main challenge is the oblique angle of the wrist-worn camera, which makes the fingers scarcely visible. To address this, a special network that observes deformations on the back of the hand is required. We introduce DorsalNet, a two-stream convolutional neural network to regress finger joint angles from spatio-temporal features of the dorsal hand region (the movement of bones, muscle, and tendons). This work is the first vision-based real-time 3D hand pose estimator using visual features from the dorsal hand region. Our system achieves a mean joint-angle error of 8.81 degree for user-specific models and 9.77 degree for a general model. Further evaluation shows that our system outperforms previous work with an average of 20% higher accuracy in recognizing dynamic gestures, and achieves a 75% accuracy of detecting 11 different grasp types. We also demonstrate 3 applications which employ our system as a control device, an input device, and a grasped object recognizer.

We propose the use of a proportional-derivative (PD) control based policy learned via reinforcement learning (RL) to estimate and forecast 3D human pose from egocentric videos. The method learns directly from unsegmented egocentric videos and motion capture data consisting of various complex human motions (e.g., crouching, hopping, bending, and motion transitions). We propose a video-conditioned recurrent control technique to forecast physically-valid and stable future motions of arbitrary length. We also introduce a value function based fail-safe mechanism which enables our method to run as a single pass algorithm over the video data. Experiments with both controlled and in-the-wild data show that our approach outperforms previous art in both quantitative metrics and visual quality of the motions, and is also robust enough to transfer directly to real-world scenarios. Additionally, our time analysis shows that the combined use of our pose estimation and forecasting can run at 30 FPS, making it suitable for real-time applications.