Chun Gu - 顾淳

I'm a first-year Ph.D. student at Fudan University under the supervision of Prof. Li Zhang.

I'm interested in Computer Vision and Graphics, especially in 3D reconstruction.

Email  /  Github  /  Google Scholar

Publications & Projects

code

In this paper, we introduce a spatially and directionally aware importance sampler for the rendering equation to accurately and flexibly capture the unconstrained complexity of a typical scene.

code

In this paper, we introduce inter-reflective Gaussian splatting for inverse rendering. We apply the full rendering equation without simplification and compute incident radiance on the fly using the proposed differentiable 2D Gaussian ray tracing.

code

gstracer backend

An implementation of 3D Gaussian Ray Tracing, inspired by the work 3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes.

code

A novel framework for generating realistic LiDAR point clouds with panoramic Gaussian splatting.

code

A Reflective Gaussian splatting framework characterized with two components: (I) Physically based deferred rendering; (II) Gaussian-grounded inter-reflection.

code

In this paper, we propose to achieve 4D generation from directly sampling the dense multi-view multi-frame observation of dynamic content by composing the estimated score of pretrained video and multi-view diffusion models that have learned strong prior of dynamic and geometry.

Providing a brief introduction to the progress in 3D generation using Score Distillation Sampling (SDS).

code

Integrating surface-based volumetric rendering within a structured tetrahedral grid, utilizing tetrahedra for splatting.

code

A unified representation model for large-scale dynamic urban scene reconstruction.

code

A novel differentiable point-based rendering framework for material and lighting decomposition from multi-view images, enabling editing, ray-tracing, and real-time relighting of the 3D point cloud.

code

An unofficial pytorch implementation of "Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields" based on multinerf.

Combining the (coarse) planar rendering and the (fine) volume rendering to achieve higher rendering quality and better generalizations. A depth teacher net that predicts dense pseudo depth maps is used to supervise the joint rendering mechanism and boost the learning of consistent 3D geometry.

The website template was borrowed from Jon Barron.