14 papers
CLLAP: Contrastive Learning-based LiDAR-Augmented Pretraining for Enhanced Radar-Camera Fusion
Bingyi Liu, Chuanhui Zhu, Hongfei Xue +5
Accurate 3D object detection is critical for autonomous driving, necessitating reliable, cost-effective sensors capable of operating in adverse weather conditions. Camera and milli…
LiveGesture Streamable Co-Speech Gesture Generation Model
Muhammad Usama Saleem, Mayur Jagdishbhai Patel, Ekkasit Pinyoanuntapong +6
We propose LiveGesture, the first fully streamable, speech-driven full-body gesture generation framework that operates with zero look-ahead and supports arbitrary sequence length.…
Monocular Models are Strong Learners for Multi-View Human Mesh Recovery
Haoyu Xie, Shengkai Xu, Cheng Guo +6
Multi-view human mesh recovery (HMR) is broadly deployed in diverse domains where high accuracy and strong generalization are essential. Existing approaches can be broadly grouped…
KHMP: Frequency-Domain Kalman Refinement for High-Fidelity Human Motion Prediction
Wenhan Wu, Zhishuai Guo, Chen Chen +4
Stochastic human motion prediction aims to generate diverse, plausible futures from observed sequences. Despite advances in generative modeling, existing methods often produce pred…
Send Less, Perceive More: Masked Quantized Point Cloud Communication for Loss-Tolerant Collaborative Perception
Sheng Xu, Enshu Wang, Hongfei Xue +6
Collaborative perception allows connected vehicles to overcome occlusions and limited viewpoints by sharing sensory information. However, existing approaches struggle to achieve hi…
Lifelong Domain Adaptive 3D Human Pose Estimation
Qucheng Peng, Hongfei Xue, Pu Wang +1
3D Human Pose Estimation (3D HPE) is vital in various applications, from person re-identification and action recognition to virtual reality. However, the reliance on annotated 3D d…
MonoMSK: Monocular 3D Musculoskeletal Dynamics Estimation
Farnoosh Koleini, Hongfei Xue, Ahmed Helmy +1
Reconstructing biomechanically realistic 3D human motion - recovering both kinematics (motion) and kinetics (forces) - is a critical challenge. While marker-based systems are lab-b…
Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognition
Wenhan Wu, Zhishuai Guo, Chen Chen +2
Zero-shot skeleton-based action recognition aims to develop models capable of identifying actions beyond the categories encountered during training. Previous approaches have primar…
Walk Before You Dance: High-fidelity and Editable Dance Synthesis via Generative Masked Motion Prior
Foram N Shah, Parshwa Shah, Muhammad Usama Saleem +4
Recent advances in dance generation have enabled the automatic synthesis of 3D dance motions. However, existing methods still face significant challenges in simultaneously achievin…
BioPose: Biomechanically-accurate 3D Pose Estimation from Monocular Videos
Farnoosh Koleini, Muhammad Usama Saleem, Pu Wang +3
Recent advancements in 3D human pose estimation from single-camera images and videos have relied on parametric models, like SMPL. However, these models oversimplify anatomical stru…
mmCooper: A Multi-agent Multi-stage Communication-efficient and Collaboration-robust Cooperative Perception Framework
Bingyi Liu, Jian Teng, Hongfei Xue +4
Collaborative perception significantly enhances individual vehicle perception performance through the exchange of sensory information among agents. However, real-world deployment f…
GenHMR: Generative Human Mesh Recovery
Muhammad Usama Saleem, Ekkasit Pinyoanuntapong, Pu Wang +3
Human mesh recovery (HMR) is crucial in many computer vision applications; from health to arts and entertainment. HMR from monocular images has predominantly been addressed by dete…
MaskHand: Generative Masked Modeling for Robust Hand Mesh Reconstruction in the Wild
Muhammad Usama Saleem, Ekkasit Pinyoanuntapong, Mayur Jagdishbhai Patel +4
Reconstructing a 3D hand mesh from a single RGB image is challenging due to complex articulations, self-occlusions, and depth ambiguities. Traditional discriminative methods, which…
MaskControl: Spatio-Temporal Control for Masked Motion Synthesis
Ekkasit Pinyoanuntapong, Muhammad Usama Saleem, Korrawe Karunratanakul +7
Recent advances in motion diffusion models have enabled spatially controllable text-to-motion generation. However, these models struggle to achieve high-precision control while mai…