cd /news/computer-vision/4dgs-fixer-generative-sparse-view-4d… · home topics computer-vision article
[ARTICLE · art-135568] src=arxiv.org ↗ pub= topic=computer-vision verified=true sentiment=↑ positive

4DGS-Fixer: Generative Sparse-View 4D Gaussian Splatting with Iterative Refinement Guided by Video Diffusion Priors

Researchers proposed 4DGS-Fixer, an iterative refinement framework that uses a pretrained video diffusion model to improve dynamic 4D Gaussian Splatting from sparse-view videos, according to a new arXiv paper (arXiv:2609.21176v1). The method fuses multi-view depth maps into dense point clouds for geometric initialization and uses a video restoration model to refine rendered sequences as pseudo-supervision, achieving nearly a 2 dB PSNR improvement over the previous best-performing method on a widely used benchmark dataset.

by read1 min views1 publishedSep 21, 2026

arXiv:2609.21176v1 Announce Type: new Abstract: This paper addresses the challenges of dynamic scene synthesis from sparse-view videos. Existing methods employ geometric priors, adaptive optimization, or density-control strategies to improve 4D Gaussian modeling under sparse observations. However, they cannot fundamentally resolve the ill-posed problem caused by insufficient observations and missing scene information. Moreover, sparse-view 4D Gaussian Splatting (4DGS) often suffers from poor geometric initialization: with only a few input views, COLMAP typically reconstructs sparse and incomplete point clouds, leaving large scene regions without sufficient Gaussian support and making them difficult to recover through subsequent optimization. To address these limitations, we propose a novel iterative refinement framework based on a video diffusion model to improve the completeness and consistency of dynamic 4D scenes. Specifically, we first estimate multi-view depth maps and fuse them into dense point clouds to provide more complete geometric initialization for a dynamic 4DGS representation. We then employ a pretrained video restoration model to refine sequences rendered along novel camera trajectories at different time steps. The restored sequences serve as pseudo-supervision to regularize and iteratively refine the 4DGS representation. Experiments on a widely used benchmark dataset demonstrate that our method substantially outperforms existing baselines, achieving nearly a 2 dB PSNR improvement over the previous best-performing method.

── more in #computer-vision 4 stories · sorted by recency
── more on @4dgs-fixer 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/4dgs-fixer-generativ…] indexed:0 read:1min 2026-09-21 ·