FreeFix: Boosting 3D Gaussian Splatting via Fine-Tuning-Free Diffusion Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Hongyu, Shao, Zisen, Miao, Sheng, Wang, Pan, Bai, Dongfeng, Liu, Bingbing, Liao, Yiyi
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915759912910848
author Zhou, Hongyu
Shao, Zisen
Miao, Sheng
Wang, Pan
Bai, Dongfeng
Liu, Bingbing
Liao, Yiyi
author_facet Zhou, Hongyu
Shao, Zisen
Miao, Sheng
Wang, Pan
Bai, Dongfeng
Liu, Bingbing
Liao, Yiyi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_20857
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FreeFix: Boosting 3D Gaussian Splatting via Fine-Tuning-Free Diffusion Models
Zhou, Hongyu
Shao, Zisen
Miao, Sheng
Wang, Pan
Bai, Dongfeng
Liu, Bingbing
Liao, Yiyi
Computer Vision and Pattern Recognition
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.
title FreeFix: Boosting 3D Gaussian Splatting via Fine-Tuning-Free Diffusion Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.20857