Kaiqiang Xiong

I am about to join AGIBOT to engage in research on 3D vision-related algorithms in the field of embodied intelligence. My research interests include 3D representation, neural rendering (NeRF, 3D Gaussian Splatting), and multi-view stereo(MVS).

Previously, I completed my PhD in Computer Science and Technology from Peking University, advised by Prof. Ronggang Wang. Before that, I received my Bachelor’s degree from Hunan University.

Research

Published papers are listed below.

Intrinsic Geometry-Appearance Consistency Optimization for Sparse-View Gaussian Splatting
IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR) 2026
Kaiqiang Xiong, Rui Peng, Jiahao Wu, Zhanke Wang, Jie Liang, Xiaoyun Zheng, Feng Gao, Ronggang Wang
paper arxiv project page code

CL-MVSNet: Unsupervised Multi-view Stereo with Dual-level Contrastive Learning
IEEE/CVF International Conference on Computer Vision(ICCV) 2023
Kaiqiang Xiong, Rui Peng, Zhe Zhang, Tianxing Feng, Jianbo Jiao, Feng Gao, Ronggang Wang
paper arxiv project page code

Multimodal-Prior-Guided Importance Sampling For Hierarchical Gaussian Splatting In Sparse-View Novel View Synthesis
IEEE International Conference on Acoustics, Speech, and Signal Processing(ICASSP) 2026
Kaiqiang Xiong, Zhanke Wang, Ronggang Wang
paper arxiv project page code

MVD-HuGaS: Human Gaussians from a Single Image via 3D Human Multi-view Diffusion Prior
Chinese Conference on Pattern Recognition and Computer Vision (PRCV) 2025
Kaiqiang Xiong, Ying Feng, Qi Zhang, Jianbo Jiao, Yang Zhao, Zhihao Liang, Huachen Gao, Ronggang Wang
arxiv project page

Swift4D: Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene
IEEE/CVF International Conference on Learning Representations (ICLR), 2025
Jiahao Wu, Rui Peng, Zhiyan Wang, Lu Xiao, Luyang Tang, Jinbo Yan, Kaiqiang Xiong, Ronggang Wang
paper

LocalDyGS: Multi-view Global Dynamic Scene Modeling via Adaptive Local Implicit Feature Decoupling
IEEE/CVF International Conference on Computer Vision (ICCV), 2025
Jiahao Wu, Rui Peng, Jianbo Jiao, Jiayu Yang, Luyang Tang, Kaiqiang Xiong, Jie Liang, Jinbo Yan, Runling Liu, Ronggang Wang paper

Surface-Centric Modeling for High-Fidelity Generalizable Neural Surface Reconstruction
The 18th European Conference on Computer Vision (ECCV), 2024
Rui Peng, Shihe Shen, Kaiqiang Xiong, Huachen Gao, Jianbo Jiao, Xiaodong Gu, Ronggang Wang
arxiv code

Disentangled Generation and Aggregation for Robust Radiance Fields
The 18th European Conference on Computer Vision (ECCV), 2024
Shihe Shen, Huachen Gao, Wangze Xu, Rui Peng, Luyang Tang, Kaiqiang Xiong, Jianbo Jiao, Ronggang Wang
arxiv project page code

FDC-NeRF: Learning Pose-Free Neural Radiance Fields With Flow-Depth Consistency (Oral Presentation)
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024
Huachen Gao, Shihe Shen, Zhe Zhang, Kaiqiang Xiong, Rui Peng, Zhirui Gao, Qi Wang, Yugui Xie, Ronggang Wang
paper slide

High Fidelity Aggregated Planar Prior Assisted PatchMatch Multi-View Stereo
Proceedings of the 32nd ACM International Conference on Multimedia (ACM MM), 2024
Jie Liang, Rongjie Wang, Rui Peng, Zhe Zhang, Kaiqiang Xiong, Ronggang Wang
paper

Context-Guided Multi-view Stereo with Depth Back-Projection
MultiMedia Modeling (ACM MMM), 2023
Tianxing Feng, Zhe Zhang, Kaiqiang Xiong, and Ronggang Wang
paper

HDRGS: High Dynamic Range Gaussian Splatting
Jiahao Wu, Lu Xiao,Rui Peng, Kaiqiang Xiong, Ronggang Wang
paper