SUPRA-TEX: 3D Generation with Super-Aligned Texture
초록
Single image 3D generation aims to dress a given 3D mesh with relightable materials while faithfully preserving the visual details of a reference image. Existing methods either introduce artifacts when fusing inconsistent multi-view predictions or struggle to preserve fine details through implicit image-feature conditioning. To resolve these challenges, we introduce SUPRA-Tex, built on the principle of decoupling visible-material estimation, surface alignment, and observation-guided 3D completion. This division of labor allows the 3D generator, trained on limited 3D data, to focus its capacity on preserving visible evidence and completing unobserved surfaces. Specifically, we first train an MLLM-based image editing model to predict lighting-separated PBR maps in the reference view. We then project these maps onto the visible surface and encode them with the pretrained material VAE encoder into native observation latents that share the generation target's latent space. An interleaved flow transformer holds these latents as fixed, read-only anchors while alternating unobserved-region and full-surface updates to generate complete material latents. This design achieves super-alignment with the reference, delivering What You See Is What You Get fidelity on visible regions and coherent completion on unobserved surfaces. Trained solely on public datasets, SUPRA-Tex achieves SOTA performance in both geometry-conditioned texturing and end-to-end asset generation, matching or even exceeding leading commercial systems on in-the-wild images. Project page: https://supra-3d.github.io/supratex/
저자 (8명)
- Chen Yang — LinkedIn 검색
- Jiemin Fang — LinkedIn 검색
- Fanpeng Meng — LinkedIn 검색
- Zihao Huang — LinkedIn 검색
- Jichen Pang — LinkedIn 검색
- Guanjun Wu — LinkedIn 검색
- Zhikuan Bao — LinkedIn 검색
- Qi Tian — LinkedIn 검색
저자 LinkedIn 변경 추적은 추후 자동화 예정입니다. 현재는 검색 링크를 제공합니다.