6 papers · 1 filter
LoDA: A Level of Detection Aware Method and a Multimodal Sensing Benchmark for Object Level Change Detection
Haitian Wang, Xinyu Wang, Sheldon Fung +2
High-definition 3D LiDAR maps are important for autonomous driving and smart-city services, which require reliable detection of object-level changes in multi-temporal urban LiDAR t…
ARMFlow: AutoRegressive MeanFlow for Online 3D Human Reaction Generation
Zichen Geng, Zeeshan Hayder, Wei Liu +2
3D human reaction generation faces three main challenges:(1) high motion fidelity, (2) real-time inference, and (3) autoregressive adaptability for online scenarios. Existing metho…
Disentangled Hierarchical VAE for 3D Human-Human Interaction Generation
Zichen Geng, Zeeshan Hayder, Bo Miao +3
Generating realistic 3D Human-Human Interaction (HHI) requires coherent modeling of the physical plausibility of the agents and their interaction semantics. Existing methods compre…
FLaTEC: Frequency-Disentangled Latent Triplanes for Efficient Compression of LiDAR Point Clouds
Xiaoge Zhang, Zijie Wu, Mingtao Feng +4
Point cloud compression methods jointly optimize bitrates and reconstruction distortion. However, balancing compression ratio and reconstruction quality is difficult because low-fr…
MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Model
Jian Liu, Wei Sun, Hui Yang +4
Object pose estimation is a core means for robots to understand and interact with their environment. For this task, monocular category-level methods are attractive as they require…
Text-guided 3D Human Motion Generation with Keyframe-based Parallel Skip Transformer
Zichen Geng, Caren Han, Zeeshan Hayder +3
Text-driven human motion generation is an emerging task in animation and humanoid robot design. Existing algorithms directly generate the full sequence which is computationally exp…