Blended tile conditioning improves 3D generation from detailed images
BTC3D: Blended Tile Conditioning for Detail-Enhancing Image-to-3D Generation
Computer Vision and Pattern Recognition
Summary
Generating 3D models from detailed 2D images is hard because current methods lose fine details. The authors studied how models combine image parts and created a way to feed smaller image patches into the 3D generation process. This lets the model hold on to tiny details better. They also designed a way to balance overall and local image signals during generation. Their method works without retraining models and produces clearer, more detailed 3D textures.
What this means in practice
- •For 3d content creators: Enhance the detail and texture quality of 3D models generated from single images without retraining complex diffusion models.
- •For game developers: Improve the visual fidelity of automatically generated 3D assets from concept art or photographs to speed up asset creation.
Authors
Junyu Li, Qiuyu Chen, Pengcheng Wang, Shiqi Yang, Alexandra Gomez-Villa, Joost van de Weijer, Ruilin Li, Kai Wang
Abstract
Recent diffusion-based pipelines have achieved promising progress in image-to-3D synthesis. However, generating high-fidelity details remains challenging, especially when the input image contains rich details. Existing approaches often rely on globally encoded conditioning features, which compress spatial information and limit the model to reproduce fine-grained details. This common design often leads to a phenomenon we term detail attenuation. Moreover, improving image-to-3D synthesis quality typically requires retraining or fine-tuning large diffusion models, which can be computationally expensive and impractical for complex 3D pipelines. In this work, we present Blended Tile Conditioning for image-to-3D generation (BTC3D), a training-free inference time framework that enhances fine-grained detail preservation in image-to-3D diffusion pipelines. To alleviate detail attenuation, we first examine the image feature additivity in image-to-3D models. Based on this property, we introduce a blended tile embedding that extracts local conditioning signals from split image regional patches, allowing the diffusion model to better preserve fine-grained visual details. To integrate the global and local conditioning guidance stably, we propose a dynamic conditioning schedule that gradually increases the influence of tile-level conditioning during later low-noise stages of diffusion. Our proposed method BTC3D operates entirely at inference time and can be seamlessly integrated into existing image-to-3D diffusion pipelines. Experimental results demonstrate that the proposed approach significantly improves texture quality and visual fidelity of the base model while maintaining global structural consistency in a training-free manner.