papers

Publications (9)

cs.LG2020

Learning Generative Models using Denoising Density Estimators

Siavash A. Bigdeli, Geng Lin, Tiziano Portenier +2

Learning probabilistic models that can estimate the density of a given set of samples, and generate samples from that density, is one of the fundamental challenges in unsupervised…

cs.CV2025

Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives

Alex Hanson, Allen Tu, Geng Lin +3

3D Gaussian Splatting (3D-GS) is a recent 3D scene reconstruction technique that enables real-time rendering of novel views by modeling scenes as parametric point clouds of differe…

cs.CV2023

OmnimatteRF: Robust Omnimatte with 3D Background Modeling

Geng Lin, Chen Gao, Jia-Bin Huang +4

Video matting has broad applications, from adding interesting effects to casually captured movies to assisting video production professionals. Matting with associated effects such…

cs.CV2025

GLOW: Global Illumination-Aware Inverse Rendering of Indoor Scenes Captured with Dynamic Co-Located Light & Camera

Jiaye Wu, Saeed Hadadan, Geng Lin +4

Inverse rendering of indoor scenes remains challenging due to the ambiguity between reflectance and lighting, exacerbated by inter-reflections among multiple objects. While natural…

cs.CV2023

Inverse Global Illumination using a Neural Radiometric Prior

Saeed Hadadan, Geng Lin, Jan Novák +2

Inverse rendering methods that account for global illumination are becoming more popular, but current methods require evaluating and automatically differentiating millions of path…

cs.CV2026

Rotated Lights for Consistent and Efficient 2D Gaussians Inverse Rendering

Geng Lin, Matthias Zwicker

Inverse rendering aims to decompose a scene into its geometry, material properties and light conditions under a certain rendering model. It has wide applications like view synthesi…