š About me
Hello world! Iām a junior undergraduate student at Xingjian College, Tsinghua University. My research interests lie at the intersection of vision and machine learning. My research objective is to build an embodied system that can independently complete the understanding, planning, and decision-making of 3D scenes, and apply it to fields such as robotics and autonomous driving. Now Iām working closely with Prof.Gao Huang and Prof.Hongsheng Li. If you are also interested in this domain, please feel free to contact me.
š„ News
- [2025.02] One paper is accepted by CVPR 2025. My first article as the first author š„³ ! Please visit our project page and arxiv for details. Welcome to communicate and discuss with me !
- [2025.01] One paper is accepted by ICLR 2025.
- [2024.10] Awarded by National Scholarship. Highest honor for undergraduates in China. š
- [2024.09] Supported by Beijing Natural Science Foundation Undergraduate Research Program. š§āš¬ļø Keep going !
- [2024.06] Outstanding Championship and Innovation Award in the Track on Multi-View 3D Visual Grounding of the Autonomous Grand Chanllenge at CVPR 2024.
- [2023.10] Awarded by Wang Dazhong Scholarship, Tsinghua University. 1 student per maior. š
š Publications
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.
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.