PaperScope
LIVE · 2026-09-09 05:40 UTC

RelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting

Hejun Wang, Jinxi Li, Junwei Jiang, Shiwei Mao, Hu Cheng, Shouwang Huang, Bo Yang

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.07414 v1
Submitted
2026-09-07

Abstract

Image relighting is traditionally tackled via complex inverse rendering pipelines, which suffer from ill-posed optimization, or single-image generative models that ignore crucial multi-view cues necessary for understanding 3D geometry and material interactions. To address these limitations, we introduce a feed-forward generative Transformer for direct single- and multi-view image relighting that entirely bypasses explicit intrinsic property estimation. Adapted from a video foundation model, our architecture features a latent illumination module that dynamically injects target environment maps into spatial features via cross-attention. Furthermore, we employ permutation-invariant positional encodings to symmetrically process unordered multi-view inputs without sequential bias. To train this robust data-driven model, we construct the massive Laval Objaverse Dataset (LOD), comprising 90K objects and 39K unique illuminations. Extensive experiments demonstrate state-of-the-art visual quality, photorealistic relighting quality, and strong zero-shot generalization across single-view, multi-view, and novel-view relighting tasks.

Comment: SIGGRAPH Asia 2026. Hejun and Jinxi are co-first authors. Code and data are available at: https://github.com/vLAR-group/RelightFormer

arXiv abs page · PDF · same-day batch