11 papers
SOLO: Stable Omni-terrain Long-Horizon Perceptive Humanoid Locomotion
Pihai Sun, Gang Han, Jingkai Sun +17
Humans traverse complex terrain over long distances without losing balance, whereas perceptive humanoid policies become fragile as perception and control errors accumulate. We pres…
RobotPan: A 360 Surround-View Robotic Vision System for Embodied Perception
Jiahao Ma, Qiang Zhang, Peiran Liu +11
Surround-view perception is increasingly important for robotic navigation and loco-manipulation, especially in human-in-the-loop settings such as teleoperation, data collection, an…
Heracles: Bridging Precise Tracking and Generative Synthesis for General Humanoid Control
Zelin Tao, Zeran Su, Peiran Liu +13
Achieving general-purpose humanoid control requires a delicate balance between the precise execution of commanded motions and the flexible, anthropomorphic adaptability needed to r…
MeshMimic: Geometry-Aware Humanoid Motion Learning through 3D Scene Reconstruction
Qiang Zhang, Jiahao Ma, Peiran Liu +20
Humanoid motion control has witnessed significant breakthroughs in recent years, with deep reinforcement learning (RL) emerging as a primary catalyst for achieving complex, human-l…
Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots
Wei Cui, Haoyu Wang, Wenkang Qin +19
Humanoid robot technology is advancing rapidly, with manufacturers introducing diverse heterogeneous visual perception modules tailored to specific scenarios. Among various percept…
DCHM: Depth-Consistent Human Modeling for Multiview Detection
Jiahao Ma, Tianyu Wang, Miaomiao Liu +2
Multiview pedestrian detection typically involves two stages: human modeling and pedestrian localization. Human modeling represents pedestrians in 3D space by fusing multiview info…
Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction
Jiahao Ma, Lei Wang, Miaomiao liu +2
Multi-view 3D reconstruction remains a core challenge in computer vision. Recent methods, such as DUST3R and its successors, directly regress pointmaps from image pairs without rel…
SOAF: Scene Occlusion-aware Neural Acoustic Field
Huiyu Gao, Jiahao Ma, David Ahmedt-Aristizabal +2
This paper tackles the problem of novel view audio-visual synthesis along an arbitrary trajectory in an indoor scene, given the audio-video recordings from other known trajectories…
HashPoint: Accelerated Point Searching and Sampling for Neural Rendering
Jiahao Ma, Miaomiao Liu, David Ahmedt-Aristizaba +1
In this paper, we address the problem of efficient point searching and sampling for volume neural rendering. Within this realm, two typical approaches are employed: rasterization a…
Multiview Detection with Cardboard Human Modeling
Jiahao Ma, Zicheng Duan, Liang Zheng +1
Multiview detection uses multiple calibrated cameras with overlapping fields of views to locate occluded pedestrians. In this field, existing methods typically adopt a ``human mode…
Voxelized 3D Feature Aggregation for Multiview Detection
Jiahao Ma, Jinguang Tong, Shan Wang +3
Multi-view detection incorporates multiple camera views to alleviate occlusion in crowded scenes, where the state-of-the-art approaches adopt homography transformations to project…