Lune

CVPR2025顶会

ReCap: Better Gaussian Relighting with Cross-Environment Captures

Jingzhi Li, Zongwei Wu, Eduard Zamfir, Radu Timofte

2025年份
4顶会引用

摘要

3DGS-DR GS-IR GShader R3DG ReCap (ours) 3DGS-DR GS-IR R3DG GShader ReCap (ours) GT Learned Env. Map Relight (fireplace) Relight (forest) (a) Visual comparison of learned environment maps and relighting quality. (b) Average relighting PSNR across unseen environment maps. Figure 1. ReCap shows a significant advantage in reconstructing environment maps with accurate tones and color fidelity. Both qualitative and quantitative assessments show that ReCap achieves more realistic and consistent relighting results under a range of unseen lighting conditions.

问问这篇 Paper

智能体会读完全文。

Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。

可以从这些问题问起

智能体调用

Luneget_paper_fulltext

在 Lune 里问

免费开始,无需绑卡

引用它的顶会 Paper4

问问它们各自怎么用它

它引用的顶会 Paper22

相关 Paper

黄昏的海面,两侧是细线勾勒的悬崖