arXiv cs.AI· Yanhao Ge, Shanyan Guan, Weihao Wang, Ying Tai, Mingyu You·· 12 小时前AI 评分38
RaPD：基于语义增强隐式表示的分辨率无关像素扩散模型
RaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit Representations
AI 导读
RaPD 提出在连续神经图像场（NIF）隐式空间中进行扩散，实现分辨率无关的图像生成。它通过语义表示引导让隐空间具备生成感知能力，并用坐标查询注意力渲染器支持任意分辨率渲染，仅改变查询坐标即可输出不同尺寸图像，扩散成本保持固定。论文已被 NeurIPS 2026 接收，实验显示其在生成质量与分辨率可扩展性上均优于现有方法。
正文 · 原文
Abstract:Natural images are continuous, yet most generative models synthesize them on discrete grids, limiting resolution-flexible generation. Continuous neural fields enable resolution-free rendering, but prior methods introduce continuity only at the decoding stage as an interpolation module, leaving the generative latent space discretized and reconstruction-oriented. We propose RaPD (Resolution-agnostic Pixel Diffusion), which performs diffusion in a continuous Neural Image Field (NIF) latent space. RaPD bridges this reconstruction generation gap with Semantic Representation Guidance for generation-aware latent learning and a Coordinate-Queried Attention Renderer for coordinate-conditioned, scale-aware rendering. A single denoised latent can be rendered at arbitrary resolutions by changing only the query coordinates, keeping diffusion cost fixed. Experiments demonstrate superior generation quality and resolution scalability.
| Comments: | The Fortieth Annual Conference on Neural Information Processing Systems (NeuIPS2026) |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.15908 [cs.CV] |
| (or arXiv:2605.15908v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2605.15908 arXiv-issued DOI via DataCite |
Submission history
From: Yanhao Ge [view email]
[v1]
Fri, 15 May 2026 12:45:17 UTC (17,798 KB)
[v2]
Fri, 16 Oct 2026 09:35:08 UTC (11,256 KB)
来源：arXiv cs.AI · arxiv.org