Publications
You can also find my articles on my Google Scholar profile.
CVPR 2025
ProxyTransformation : Preshaping Point Cloud Manifold With Proxy Attention For 3D Visual Grounding
Qihang Peng, Henry Zheng, Gao Huang
- Make full use of multimodal information in ego-centric 3D visual grounding for point enhancement.
- State-of-the-art on EmbodiedScan benchmark.
ICLR 2025
DenseGrounding: Improving Dense Language-Vision Semantics for Ego-centric 3D Visual Grounding
Henry Zheng*, Shi Hao*, Qihang Peng, et al.
- Use LLM and Ground Truth to enhance semantic details in prompt to reduce the ambiguity during training.
- Extract individual view semantics and enriches visual representation with global scene-level semantic.