4 papers
M4Human: A Large-Scale Multimodal mmWave Radar Benchmark for Human Mesh Reconstruction
Junqiao Fan, Yunjiao Zhou, Yizhuo Yang +6
Human mesh reconstruction (HMR) provides direct insights into body-environment interaction, which enables various immersive applications. While existing large-scale HMR datasets re…
Physion-Eval: Evaluating Physical Realism in Generated Video via Human Reasoning
Qin Zhang, Peiyu Jing, Hong-Xing Yu +7
Video generation models are increasingly used as world simulators for storytelling, simulation, and embodied AI. As these models advance, a key question arises: do generated videos…
ThermoHands: A Benchmark for 3D Hand Pose Estimation from Egocentric Thermal Images
Fangqiang Ding, Yunzhou Zhu, Xiangyu Wen +2
Designing egocentric 3D hand pose estimation systems that can perform reliably in complex, real-world scenarios is crucial for downstream applications. Previous approaches using RG…
RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar
Fangqiang Ding, Xiangyu Wen, Yunzhou Zhu +2
3D occupancy-based perception pipeline has significantly advanced autonomous driving by capturing detailed scene descriptions and demonstrating strong generalizability across vario…