Related papers: PhysHMR: Learning Humanoid Control Policies from V…

We focus on the task of estimating a physically plausible articulated human motion from monocular video. Existing approaches that do not consider physics often produce temporally inconsistent output with motion artifacts, while…

Generating realistic human motion is a central yet unsolved challenge in video generation. While reinforcement learning (RL)-based post-training has driven recent gains in general video quality, extending it to human motion remains…

Humanoid loco-manipulation in unstructured environments demands tight integration of egocentric perception and whole-body control. However, existing approaches either depend on external motion capture systems or fail to generalize across…

Humanoid whole-body loco-manipulation promises transformative capabilities for daily service and warehouse tasks. While recent advances in general motion tracking (GMT) have enabled humanoids to reproduce diverse human motions, these…

Estimating human pose and shape from monocular images is a long-standing problem in computer vision. Since the release of statistical body models, 3D human mesh recovery has been drawing broader attention. With the same goal of obtaining…

From an image of a person, we can easily infer the natural 3D pose and shape of the person even if ambiguity exists. This is because we have a mental model that allows us to imagine a person's appearance at different viewing directions from…

Existing multi-person human reconstruction approaches mainly focus on recovering accurate poses or avoiding penetration, but overlook the modeling of close interactions. In this work, we tackle the task of reconstructing closely interactive…

Extracting physically plausible 3D human motion from videos is a critical task. Although existing simulation-based motion imitation methods can enhance the physical quality of daily motions estimated from monocular video capture, extending…

While recent advances in humanoid locomotion have achieved stable walking on varied terrains, capturing the agility and adaptivity of highly dynamic human motions remains an open challenge. In particular, agile parkour in complex…

Deploying humanoid robots to interact with real-world environments--such as carrying objects or sitting on chairs--requires generalizable, lifelike motions and robust scene perception. Although prior approaches have advanced each capability…

Human Mesh Recovery (HMR) is an important yet challenging problem with applications across various domains including motion capture, augmented reality, and biomechanics. Accurately predicting human pose parameters from a single image…

Holistic 3D human-scene reconstruction is a crucial and emerging research area in robot perception. A key challenge in holistic 3D human-scene reconstruction is to generate a physically plausible 3D scene from a single monocular RGB image.…

While current methods have shown promising progress on estimating 3D human motion from monocular videos, their motion estimates are often physically unrealistic because they mainly consider kinematics. In this paper, we introduce…

Motion mimicking, i.e., encouraging the control policy to mimic human motion, facilitates the learning of complex tasks via reinforcement learning (RL) for humanoid robots. Although standard RL frameworks demonstrate impressive locomotion…

Monocular video human mesh recovery is essential for digital humans, avatar animation, and embodied simulation, where both temporal stability and expressive whole-body motion are required. Existing video HMR methods produce coherent body…

Human Mesh Recovery (HMR) is fundamentally ambiguous: under occlusion or weak depth cues, multiple 3D bodies can explain the same image evidence. This ambiguity is not uniform across the body, as torso pose and root structure are often…

How can we teach humanoids to climb staircases and sit on chairs using the surrounding environment context? Arguably, the simplest way is to just show them-casually capture a human motion video and feed it to humanoids. We introduce…

We introduce CRISP, a method that recovers simulatable human motion and scene geometry from monocular video. Prior work on joint human-scene reconstruction relies on data-driven priors and joint optimization with no physics in the loop, or…

Recovering 4D human-object interaction (HOI) from monocular video is a key step toward scalable 3D content creation, embodied AI, and simulation-based learning. Recent methods can reconstruct temporally coherent human and object…

Video generation models nowadays are capable of generating visually realistic videos, but often fail to adhere to physical laws, limiting their ability to generate physically plausible videos and serve as ''world models''. To address this…