Texture++：使用区域感知扩散模型提升3D资产纹理分辨率

中文摘要 AI 辅助

由于纹理分辨率低，大量3D资产被废弃，而当前超分辨率模型忽略纹理图并专注于自然图像。一个高效且通用的纹理超分辨率模型可使电影和视频游戏等行业中大量老旧但有价值的资产重焕生机。我们提出Texture++，一种新颖的纹理超分辨率框架，可增强资产的低分辨率纹理以产生高分辨率、高质量的结果。具体而言，我们将超分辨率任务在UV空间中重新表述为跨多个渲染视图执行并合并输出。首先，为在视图空间中实现更完整和连续的纹理，我们提出一种自适应视图选择策略来整合分散在UV纹理补丁中的纹理。此外，我们引入一种基于四叉树的纹理区域组织方法来组合来自不同视点的超分辨率纹理，提供掩码以区分需要改进的区域。最后，我们设计一种基于扩散的超分辨率模型，为指定的掩码区域增强纹理分辨率，并与周围区域无缝集成。通过全面评估，我们证明我们的方法比现有方法产生的纹理在细节和连贯性上有显著改进。

英文摘要

Numerous 3D assets are discarded due to low texture resolution, while current super-resolution models ignore texture maps and focus on natural images. An efficient and generalizable texture super-resolution model can revitalize a large corpus of aging yet valuable assets across industries such as film and video games. We present Texture++, a novel framework for texture super-resolution, which enhances the low-resolution textures of assets to produce high-resolution, high-quality results. Specifically, we reformulate the task of super-resolution in UV space into performing it across multiple rendered views and merging the outputs. Firstly, to achieve more complete and continuous textures in the view space, we propose an adaptive view selection strategy to integrate textures dispersed across UV texture patches. Furthermore, we introduce a quadtree-based texture region organization method for combining super-resolved textures from different viewpoints, providing masks to distinguish regions that require improvement. Finally, we design a diffusion-based super-resolution model that enhances the texture resolution for specified masked regions, seamlessly integrating with surrounding regions. Through comprehensive evaluations, we demonstrate that our approach yields textures with substantially improved detail and coherence over existing methods.

发表机构

• State Key Laboratory of CAD&CG, Zhejiang University（浙江大学计算机辅助设计与图形学国家重点实验室）
• North China Electric Power University（华北电力大学）

机构由 AI 辅助整理，请以论文原文为准。