# RelightFormer：用于多视角物体重打光的自回归生成式Transformer

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-09-07 08:00
- AIHOT 分数：33
- AIHOT 链接：https://aihot.news/items/cmttv9piz0ocarofpj0o1x1ct
- 原文链接：https://arxiv.org/abs/2609.07414

## AI 摘要

RelightFormer是一种前馈生成式Transformer，可直接对单视角和多视角图像进行重打光，绕过了显式的固有属性估计。该架构从视频基础模型适配而来，通过潜在光照模块和置换不变位置编码处理无序多视角输入。研究团队构建了包含90K物体和39K种独特光照的Laval Objaverse数据集（LOD），实验显示其在单视角、多视角及新视角重打光任务上达到SOTA视觉质量并具备强零样本泛化能力。

## 正文

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.