English

Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models

Computer Vision and Pattern Recognition 2026-07-01 v1

Abstract

Recent 3D generative models can synthesize high-quality geometry but often struggle to reproduce intricate textures from reference images, largely due to the scarcity of large-scale 3D training data with rich surface appearance. In contrast, visual generative models are trained on datasets several orders of magnitude larger and excel at modeling complex visual patterns. Motivated by this gap, we introduce Ink3D, a framework that bridges 3D generation with large-scale video generative models to synthesize extremely complex textures. Ink3D first reconstructs a white-mesh geometry using an off-the-shelf 3D generation model. It then employs OrbitPainter, a conditional video generative model, to produce dense orbit-scan videos capturing object appearance across viewpoints. To convert these views into coherent textures, we introduce TextureOptimizer, a neural baking module that integrates dense multi-view observations while mitigating geometry inconsistencies arising from video generation. By decoupling geometry and texture synthesis and leveraging large-scale pretrained video priors, Ink3D enables significantly richer and more faithful texture generation than prior approaches.

Cite

@article{arxiv.2607.01222,
  title  = {Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models},
  author = {Yue Han and Chong Li and Zhening Liu and Cong Huang and Fang Deng and Yong Liu and Fangyun Wei and Yan Lu},
  journal= {arXiv preprint arXiv:2607.01222},
  year   = {2026}
}

Comments

Accepted to ECCV 2026. Project page: https://yuehan99.github.io/Ink3D-TextureGen/