Haiyang Bai

I'm currently a PhD candidate at Nanjing University (NJU), advised by Prof. Jie Guo, Prof. Yanwen Guo, and Prof. Lijun Chen. Before that, I received my bachelor's and master's degrees in 2018 and 2021 from Xi'an Jiaotong University (XJTU) and Northwestern Polytechnical University (NWPU), respectively. My research interests include novel view synthesis, neural rendering, and relighting.

Publications

On the Spectral Differences Between NTK and CNTK and Their Implications for Point Cloud Recognition

Chang Gou, Haiyang Bai, Jia Liu

ICLR, 2026

Paper

ResGaussian: 3D Gaussian Splatting with High-Frequency Residual

Haiyang Bai, Xingyu Hou, Jiaqi Zhu, Songru Jiang, Huanhuan Lv, Lijun Chen

ICASSP, 2026

Paper

ICASSP 2026

OGRA-YOLOv8: Overlapping Gridded and Rhombus Attention for Underwater Object Detection

Huanhuan Lv, Yuanjing Luo, Songru Jiang, Yuhao Bai, Haiyang Bai, Lijun Chen

ICASSP, 2026

Paper Code

GaRe: Relightable 3D Gaussian Splatting for Outdoor Scenes from Unconstrained Photo Collections

Haiyang Bai, Jiaqi Zhu, Songru Jiang, Wei Huang, Tao Lu, Yuanqi Li, Jie Guo, Runze Fu, Yanwen Guo, Lijun Chen

ICCV, 2025

Paper

MixRF: Universal Mixed Radiance Fields with Points and Rays Aggregation

Haiyang Bai, Tao Lu, Jiaqi Zhu, Wei Huang, Chang Gou, Jie Guo, Lijun Chen, Yanwen Guo

TVCG, 2025

Paper

3D Shape Classification by Registration: Neural-Network-Free and Training-Free

Chang Gou, Yuanqu Mou, Wenjie Li, Neetesh Purohit, Suneel Yadav, Haiyang Bai, Xu Zhang, Lijun Chen

ICASSP, 2025

Paper

How Classification Baseline Works for Deep Metric Learning: A Perspective of Metric Space

Yuanqu Mou, Zhengxue Jian, Haiyang Bai, Chang Gou

ACML, 2024

Paper

FVLoc-NeRF: Fast Vision-Only Localization within Neural Radiation Field

Wenzhi Guo, Haiyang Bai, Yuanqu Mou, Jia Liu, Lijun Chen

IROS, 2023

Paper

How Neural Networks With Derivative Labels Work: A Neural Tangent Kernel Perspective

Yuanqu Mou, Chang Gou, Haiyang Bai, Jia Liu

OpenReview

Paper