RelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting
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 positiona...
| Authors | Hejun Wang, Jinxi Li, Junwei Jiang et al. |
|---|---|
| Primary category | cs.CV |
| Published | 7 September 2026 |
| Last updated at source | 7 September 2026 |
Connected in the knowledge graph
- vLAR/LavalObjaverseDatasetDataset · cited by
Models and datasets referencing this paper
- vLAR/LavalObjaverseDatasetDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.