发表机构
The Chinese University of Hong Kong; Guangdong University of Technology; City University of Hong Kong; Monash University（香港中文大学; 广东工业大学; 香港城市大学; 莫纳什大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有3D生成模型分辨率受限的问题，提出PLSR框架，通过分解局部子任务与流式生成器微调，实现高效高细节的3D超分辨率生成。
AI 中文摘要
高分辨率3D资产生成在各种3D应用中至关重要。现有的最先进的基于扩散的模型仍受限于固定分辨率，限制了其生成细节的能力。在本文中，我们通过引入一个构建于现有3D生成基础模型之上的3D超分辨率（SR）框架，来解决生成更详细、更高分辨率3D物体的挑战。为此，我们设计了PLSR，一种渐进式且局部化的超分辨率解决方案，以有效且内存高效地实现这一目标。在技术上，给定来自预训练3D生成器的粗略几何体，我们通过一种关联输入分解方案将全局SR任务分解为局部子任务，通过低成本微调将基于流的3D生成器适配为局部化超分辨率模型，并将它们统一在一个迭代的逐块去噪流程中，以实现无缝的高分辨率输出。在具有挑战性的物体上的实验表明，我们的方法能够生成具有新的强细节保真度的3D细节，同时显著降低计算成本，为高分辨率3D资产生成提供了一种新的实用解决方案。
英文摘要
High-resolution 3D asset generation is vital in various 3D applications. Existing state-of-the-art diffusion-based models remain constrained by fixed resolutions, limiting their ability to produce details. In this paper, we tackle the challenge of generating more detailed, higher-resolution 3D objects by introducing a 3D super-resolution (SR) framework built on existing 3D generative foundation models. To this end, we design PLSR, a progressive and localized super-resolution solution to achieve this goal effectively and memory efficiently. Technically, given a coarse geometry from a pretrained 3D generator, we decompose the global SR task into localized sub-tasks via an associative input decomposition scheme, adapt a flow-based 3D generator into a localized super-resolution model through low-cost finetuning, and unify them in an iterative patch-wise denoising pipeline for seamless high-resolution output. Experiments on challenging objects show that our approach is able to generate 3D details with new strong fine-detail fidelity while significantly reducing the computational cost, offering a new and practical solution for high-resolution 3D asset generation.
Comments34 pages, 15 figures, including supplementary material. ECCV 2026. Additional evaluation data are provided as ancillary files
Journal refComputer Vision - ECCV 2026, Lecture Notes in Computer Science, vol. 17050, pp. 281-299, Springer, Cham, 2026
DOI：10.1007/978-3-032-37359-5_16
