Spackle：利用自适应高斯完成大视角单图像NVS
Spackle: Completing Large View Single Image NVS with Adaptive Gaussians
浏览论文内容
中文总结 AI 辅助
Spackle提出轻量级残差学习框架，通过分阶段预测基础高斯、识别重建不佳区域并学习残差高斯，缓解容量竞争，在大视角偏差单图像NVS中实现最先进性能。
中文摘要 AI 辅助
单图像新视角合成（NVS）能够从单一输入图像实现未观察视角的逼真渲染。实用的NVS系统需要两个关键能力：对遮挡区域的鲁棒重建和高推理效率。尽管结合前馈3D高斯泼溅（3DGS）与扩散模型的混合解耦框架在大视角偏差NVS中展现出潜力，但它们存在容量竞争问题：固定数量的高斯迫使资源从可见区域转移到新暴露的遮挡区域，当目标视角与输入偏差较大时，会降低原始场景保真度。为解决此问题，我们提出Spackle，一种轻量级残差学习框架，在不牺牲效率的情况下缓解容量竞争。Spackle分三个阶段运行：从给定视角预测基础3DGS属性，自动识别重建不佳的区域，并学习仅针对这些区域优化的残差3DGS。推理时，我们结合基线高斯与增强高斯进行NVS。我们进行了全面实验，结果表明Spackle在大视角偏差情况下达到了最先进的性能。
英文摘要
Single-image novel view synthesis (NVS) enables photorealistic rendering of un- observed viewpoints from a single input. Practical NVS systems require two key capabilities: robust reconstruction of occluded regions and high inference effi- ciency. While hybrid decoupled frameworks combining feedforward 3D Gaussian Splatting (3DGS) and diffusion models show promise for large-view-deviation NVS, they suffer from capacity competition: a fixed number of Gaussians forces resource shifts from visible to newly disoccluded areas, degrading original scene fidelity when the target view deviates significantly from the input. To address this, we propose Spackle, a lightweight residual learning framework that mit- igates capacity competition without sacrificing efficiency. Spackle operates in three stages: predicting base 3DGS attributes from given views, automatically identifying poorly reconstructed regions, and learning a residual 3DGS optimized exclusively for these areas. At inference, we combine the baseline and aug- mented Gaussians for NVS. We conduct comprehensive experiments and show that Spackle achieves state-of-the-art performance on large-view-deviation cases.
发表机构
- Shenzhen University of Advanced Technology（深圳先进技术大学）
- HONOR（荣耀）
机构由 AI 辅助整理，请以论文原文为准。
