activity
20242026
most citedTransparentGS: Fast Inverse Rendering of Transparent Objects with Gaussians

4 citations · 4 across the 2 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2026

TexSpot: 3D Texture Enhancement with Spatially-uniform Point Latent Representation

Ziteng Lu, Yushuang Wu, Chongjie Ye +7

High-quality 3D texture generation remains a fundamental challenge due to the view-inconsistency inherent in current mainstream multi-view diffusion pipelines. Existing representat…

cs.CV2026

Low-Light Video Enhancement with An Effective Spatial-Temporal Decomposition Paradigm

Xiaogang Xu, Kun Zhou, Tao Hu +4

Low-Light Video Enhancement (LLVE) seeks to restore dynamic or static scenes plagued by severe invisibility and noise. In this paper, we present an innovative video decomposition s…

cs.CV2025

Enhancing Diffusion-based Restoration Models via Difficulty-Adaptive Reinforcement Learning with IQA Reward

Xiaogang Xu, Ruihang Chu, Jian Wang +6

Reinforcement Learning (RL) has recently been incorporated into diffusion models, e.g., tasks such as text-to-image. However, directly applying existing RL methods to diffusion-bas…

cs.CV2024

MaterialPicker: Multi-Modal DiT-Based Material Generation

Xiaohe Ma, Valentin Deschaintre, Miloš Hašan +4

High-quality material generation is key for virtual environment authoring and inverse rendering. We propose MaterialPicker, a multi-modal material generator leveraging a Diffusion…

cs.CV2024

ARM: Appearance Reconstruction Model for Relightable 3D Generation

Xiang Feng, Chang Yu, Zoubin Bi +6

Recent image-to-3D reconstruction models have greatly advanced geometry generation, but they still struggle to faithfully generate realistic appearance. To address this, we introdu…

cs.CV2024

GS^3: Efficient Relighting with Triple Gaussian Splatting

Zoubin Bi, Yixin Zeng, Chong Zeng +4

We present a spatial and angular Gaussian based representation and a triple splatting process, for real-time, high-quality novel lighting-and-view synthesis from multi-view point-l…