Neural Radiance Fields and 3D Gaussian Splatting have advanced novel view synthesis, yet still rely on dense inputs and often degrade at extrapolated views. Recent approaches leverage generative models, such as diffusion models, to provide additional supervision, but face a trade-off between generalization and fidelity: fine-tuning diffusion models for artifact removal improves fidelity but risks overfitting, while fine-tuning-free methods preserve generalization but often yield lower fidelity. We introduce FreeFix, a fine-tuning-free approach that pushes the boundary of this trade-off by enhancing extrapolated rendering with pretrained image diffusion models. We present an interleaved 2D-3D refinement strategy, showing that image diffusion models can be leveraged for consistent refinement without relying on costly video diffusion models. Furthermore, we take a closer look at the guidance signal for 2D refinement and propose a per-pixel confidence mask to identify uncertain regions for targeted improvement. Experiments across multiple datasets show that FreeFix improves multi-frame consistency and achieves performance comparable to or surpassing fine-tuning-based methods, while retaining strong generalization ability.

翻译：神经辐射场与3D高斯溅射技术虽已推动新视角合成领域的发展，但仍依赖密集输入数据且在视角外推时易出现质量退化。现有方法利用扩散模型等生成模型提供额外监督，但面临泛化性与保真度的权衡：为消除伪影而对扩散模型进行微调虽能提升保真度，却可能引发过拟合；而免微调方法虽保持泛化能力，却常导致保真度降低。本文提出FreeFix——一种免微调方法，通过预训练图像扩散模型增强外推渲染效果，突破该权衡关系的边界。我们提出交错式2D-3D优化策略，证明无需依赖高成本的视频扩散模型，图像扩散模型即可实现一致性优化。此外，我们深入分析2D优化的引导信号，提出基于逐像素置信度的掩码机制以定位需针对性改进的不确定区域。跨数据集实验表明，FreeFix在保持强泛化能力的同时，提升了多帧一致性，其性能达到甚至超越基于微调的方法。