Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models
2026-07-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created Ink3D, a method that improves 3D object looks by focusing separately on shape and texture. They start with a basic 3D shape from existing tools, then use a video model called OrbitPainter to generate detailed views of how the object looks from different angles. Another tool, TextureOptimizer, combines these views into a smooth, realistic surface texture while fixing small errors. This approach uses large video data to make textures more detailed than previous 3D methods.
3D generative modelstexture synthesisvideo generative modelsmulti-view reconstructionneural bakinggeometry inconsistencysurface appearanceOrbitPainterTextureOptimizerlarge-scale pretraining
Authors
Yue Han, Chong Li, Zhening Liu, Cong Huang, Fang Deng, Yong Liu, Fangyun Wei, Yan Lu
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.