Lihe Ding

I am a first-year Ph.D. student from MMLab, The Chinese University of Hong Kong, and my advisor is Prof. Tianfan Xue.

I received both my Bachelor's and Master's degrees from Beijing Institute of Technology, supervised by Prof. Jianan Li. I spent a wonderful time in Qcraft and SenseTime as a research intern, mentored by Boyin Zhang and Dr. Zhanpeng Huang, respectively. I was a research assistant at Tsinghua University with Prof. Li Yi.

CV  /  Google Scholar  /  Twitter  /  Github
Email: dean.dinglihe at outlook dot com

profile photo
Research

I have been working on Neural Rendering and Diffusion Model for 3D generation. My previous work also included 3D perception on Point Clouds. (*: Equal Contribution †: Corresponding Author)

Interactive3D: Create What You Want by Interactive 3D Generation
Shaocong Dong*, Lihe Ding*, Zhanpeng Huang, Zibin Wang, Tianfan Xue†, Dan Xu†
CVPR, 2024
project page / paper / video

Interactive3D grants users precise control over the generative process through extensive 3D interaction capabilities.

Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors
Lihe Ding*, Shaocong Dong*, Zhanpeng Huang, Zibin Wang†, Yiyuan Zhang, Kaixiong Gong, Dan Xu, Tianfan Xue†
CVPR, 2024
project page / paper / video

We intergrate both 3D and 2D diffusion models with powerful priors into a unified framework with bidirectional guidance.

Obj-NeRF: Extracting Object NeRFs from Multi-view Images
Zhiyi Li, Lihe Ding, Tianfan Xue
arXiv, 2023
project page / paper / video

We propose Obj-NeRF, a novel comprehensive pipeline to extract object NeRFs from multi-view images, which can be used for NeRF editing tasks.

Sample-adaptive Augmentation for Point Cloud Recognition Against Real-world Corruptions
Jie Wang, Lihe Ding, Tingfa Xu, Shaocong Dong, Xinli Xu, Long Bai, Jianan Li
ICCV, 2023
paper / code

we propose an alternative to make sample-adaptive transformations based on the structure of the sample to cope with potential corruption via an auto-augmentation framework.

FH-Net: A Fast Hierarchical Network for Scene Flow Estimation on Real-world Point Clouds
Lihe Ding*, Shaocong Dong*, Tingfa Xu†, Xinli Xu, Jie Wang, Jianan Li
ECCV, 2022   (Oral Presentation)
project page / paper / video

We establish new lidar-scanned scene flow datasets and propose a fast and hierarchical network for real-world scene flow estimation.

CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds
Haiyang Wang*, Lihe Ding*, Shaocong Dong, Shaoshuai Shi†, Aoxue Li, Jianan Li, Zhenguo Li, Liwei Wang
NeurIPS, 2022
paper / code

We propose a novel class-aware 3D proposal generation strategy and an efficient fully sparse convolutional 3D refinement module for vote-based Indoor 3D Detection.

MsSVT: Mixed-scale Sparse Voxel Transformer for 3D Object Detection on Point Clouds
Shaocong Dong*, Lihe Ding*, Haiyang Wang, Tingfa Xu†, Xinli Xu, Jie Wang, Ziyang Bian, Ying Wang, Jianan Li
NeurIPS, 2022
paper / code

We propose the first powerful 3D window-based transformer backbone on sparse 3D voxels leveraging mixed-scale information.

FusionRCNN: LiDAR-Camera Fusion for Two-stage 3D Object Detection
Xinli Xu, Shaocong Dong, Lihe Ding, Jie Wang, Tingfa Xu, Jianan Li
arXiv, 2022
paper / code

We propose a novel multi-modality two-stage approach to effectively and efficiently fuse point clouds and camera images in the Regions of Interest(RoI).

PAPooling: Graph-based Position Adaptive Aggregation of Local Geometry in Point Clouds
Jie Wang, Jianan Li†, Lihe Ding, Ying Wang, Tingfa Xu†
arXiv, 2021
paper

The dynamic graph constructing strategy can well capture the fine-grained geometry ignored by previous aggregation operations.

Education
PhD in Multimedia Lab (MMLab) @ The Chinese University of Hong Kong
Sep. 2023 - Now
Advisor: Prof.Tianfan Xue
MSc in Opt-Electronics information Science and Engineeering @ Beijing Institute of Technology
Sep. 2020 - Jun. 2023
Advisor: Prof.Jianan Li
BSc in Opt-Electronics information Science and Engineeering @ Beijing Institute of Technology
Sep. 2016 - Jun. 2020
GPA: 90.2/100
Experience
Metaverse Video R&D at SenseTime
Research Intern
Text-to-3D Generation using both 2D and 3D priors
May, 2023 - Sep, 2023
Mentor: Dr. Zhanpeng Huang
3DAR Group
Institute for Interdisciplinary Information Sciences (IIIS) at Tsinghua University
Research Assistant
3D Generation with diffusion model and implicit fuction
May, 2022 - Sep, 2022
Advisor: Prof. Li Yi
3D Visual Computing and Machine Intelligence (3DVICI) Lab
Qcraft
Research Intern
Beijing, China
May, 2021 - June, 2022
Mentor: Boyin Zhang
Perception & Machine Learning Group

Template from JonBarron