FreeFix: Boosting 3D Gaussian Splatting via Fine-Tuning-Free Diffusion Models
This work addresses the problem of improving 3D Gaussian Splatting for novel view synthesis in computer vision, offering an incremental advancement by optimizing the use of diffusion models without fine-tuning.
The paper tackles the trade-off between generalization and fidelity in novel view synthesis by introducing FreeFix, a fine-tuning-free approach that enhances extrapolated rendering using pretrained image diffusion models, achieving performance comparable to or surpassing fine-tuning-based methods while retaining strong generalization ability.
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.