用局部扩散模型逐步提升3D物体分辨率，更细更省显存。
PLSR: Progressive and Localized Super-Resolution of 3D Objects via Localized Latent Voxel Diffusion
- 分块处理3D几何，逐块细化细节，降低内存压力。
- 在预训练模型上微调，实现高效高分辨率生成。
- 适合需要精细3D资产的影视游戏开发者。
高分辨率3D资产生成在多种3D应用中至关重要。现有基于扩散模型的方法受限于固定分辨率，难以生成精细细节。本文提出一种基于已有3D生成基础模型的3D超分辨率（SR）框架PLSR，通过渐进式、局部化的策略有效提升分辨率并节省内存。技术上，给定预训练3D生成器输出的粗糙几何，采用关联输入分解方案将全局超分辨率任务拆分为局部子任务，通过低成本微调将流模型转换为局部超分辨率模型，并在迭代式块状去噪流水线中统一整合，实现无缝高分辨率输出。在挑战性物体上的实验表明，该方法能生成具有强细粒度保真度的新细节，同时显著降低计算开销，为高分辨率3D资产生成提供了一种新且实用的解决方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。