SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Yang, Tan, Hao, Zhang, Kai, Wang, Peng, Guibas, Leonidas, Wetzstein, Gordon, Yifan, Wang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908694816489472
author Zheng, Yang
Tan, Hao
Zhang, Kai
Wang, Peng
Guibas, Leonidas
Wetzstein, Gordon
Yifan, Wang
author_facet Zheng, Yang
Tan, Hao
Zhang, Kai
Wang, Peng
Guibas, Leonidas
Wetzstein, Gordon
Yifan, Wang
contents The rise of 3D Gaussian Splatting has revolutionized photorealistic 3D asset creation, yet a critical gap remains for their interactive refinement and editing. Existing approaches based on diffusion or optimization are ill-suited for this task, as they are often prohibitively slow, destructive to the original asset's identity, or lack the precision for fine-grained control. To address this, we introduce \ourmethod, a state-aware feedforward model that enables continuous editing of 3D Gaussian assets from user-provided 2D view(s). Our method directly predicts updates to the attributes of a compact, feature-rich Gaussian representation and leverages Test-Time Training to create a state-aware, iterative workflow. The versatility of our approach allows a single architecture to perform diverse tasks, including high-fidelity local detail refinement, local paint-over, and consistent global recoloring, all at interactive speeds, paving the way for fluid and intuitive 3D content authoring.
format Preprint
id arxiv_https___arxiv_org_abs_2512_05354
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training
Zheng, Yang
Tan, Hao
Zhang, Kai
Wang, Peng
Guibas, Leonidas
Wetzstein, Gordon
Yifan, Wang
Computer Vision and Pattern Recognition
Graphics
The rise of 3D Gaussian Splatting has revolutionized photorealistic 3D asset creation, yet a critical gap remains for their interactive refinement and editing. Existing approaches based on diffusion or optimization are ill-suited for this task, as they are often prohibitively slow, destructive to the original asset's identity, or lack the precision for fine-grained control. To address this, we introduce \ourmethod, a state-aware feedforward model that enables continuous editing of 3D Gaussian assets from user-provided 2D view(s). Our method directly predicts updates to the attributes of a compact, feature-rich Gaussian representation and leverages Test-Time Training to create a state-aware, iterative workflow. The versatility of our approach allows a single architecture to perform diverse tasks, including high-fidelity local detail refinement, local paint-over, and consistent global recoloring, all at interactive speeds, paving the way for fluid and intuitive 3D content authoring.
title SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2512.05354