Oriel — AI & technology worth noticing, every day.

SUPRA-TEX: 3D Generation with Super-Aligned Texture

Paper · https://arxiv.org/abs/2610.22352

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/

First seen by Oriel on .

AI summary

SUPRA-Tex generates relightable 3D materials from a single reference image, preserving visible details while completing unobserved surfaces.

  • An MLLM-based image editing model predicts lighting-separated PBR maps in the reference view.
  • The maps are projected onto visible mesh surfaces and encoded as observation latents in the generation target's latent space.
  • An interleaved flow transformer keeps visible-region latents fixed as read-only anchors while updating unobserved regions and the full surface.
  • Trained solely on public datasets, SUPRA-Tex reports state-of-the-art results in geometry-conditioned texturing and end-to-end asset generation, matching or exceeding leading commercial systems on in-the-wild images.

#3d generation #pbr materials #flow transformers #computer vision

Generated by gpt-5.6-sol. Check the original for details.

Metric trends

Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained

Points

Score reported by the source.

  • Hugging Face Papers: 14, latest observation ; 0 over observed period since

Comments

Comment count reported by the source.

  • Hugging Face Papers: 2, latest observation ; 0 over observed period since

Aliases

SourceExternal IDURL
Hugging Face Papers2610.22352https://arxiv.org/abs/2610.22352 Read discussion