# SSA-3DGS: Unsupervised Removal of Screen-Space Artifacts for 3D Gaussian Splatting

arXiv: https://arxiv.org/abs/2607.05598 · HTML: https://mlsanity.com/paper/2607.05598/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 41 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Builds on (most cited first, 24 of 24)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [gsplat: An Open-Source Library for Gaussian Splatting](https://mlsanity.com/paper/2409.06765/) (2024)
- [Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models](https://mlsanity.com/paper/2503.01774/) (2025)
- [3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors](https://mlsanity.com/paper/2410.16266/) (2024)
- [RobustNeRF: Ignoring Distractors with Robust Losses](https://mlsanity.com/paper/2302.00833/) (2023)
- [Complexity Experts are Task-Discriminative Learners for Any Image Restoration](https://mlsanity.com/paper/2411.18466/) (2024)
- [SpotlessSplats: Ignoring Distractors in 3D Gaussian Splatting](https://mlsanity.com/paper/2406.20055/) (2024)
- [Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collections](https://mlsanity.com/paper/2406.10373/) (2024)
- [GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors](https://mlsanity.com/paper/2508.09667/) (2025)
- [Revisiting Single Image Reflection Removal In the Wild](https://mlsanity.com/paper/2311.17320/) (2023)
- [Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion](https://mlsanity.com/paper/2403.13327/) (2024)
- [3D Gaussian Inpainting with Depth-Guided Cross-View Consistency](https://mlsanity.com/paper/2502.11801/) (2025)
- [Blind Visual Motif Removal from a Single Image](https://mlsanity.com/paper/1904.02756/) (2019)
- [Robust 3D Gaussian Splatting for Novel View Synthesis in Presence of Distractors](https://mlsanity.com/paper/2408.11697/) (2024)
- [DeSplat: Decomposed Gaussian Splatting for Distractor-Free Rendering](https://mlsanity.com/paper/2411.19756/) (2024)
- [Low-Frequency First: Eliminating Floating Artifacts in 3D Gaussian Splatting](https://mlsanity.com/paper/2508.02493/) (2025)
- [High-fidelity 3D Gaussian Inpainting: preserving multi-view consistency and photorealistic details](https://mlsanity.com/paper/2507.18023/) (2025)

## Abstract (arXiv)

Novel View Synthesis (NVS) methods, such as 3D Gaussian Splatting (3DGS), rely on the assumption of clean, multi-view consistent, posed input images. Real-world captures can violate this assumption due to screen-space artifacts---static occlusions fixed to the 2D image plane rather than to the 3D world. Common examples include physical sensor defects, environmental obstructions (such as rain or mud on the lens enclosure), capture obstructions (such as a thumb over the camera sensor or a dashboard visible in dashcam footage), and digital overlays (such as watermarks or UI elements). When present, they are erroneously baked into the 3D geometry as ``floaters'' or near-camera artifacts, degrading the quality of novel-view rendering. In this work, we propose textitSSA-3DGS, an unsupervised framework that jointly optimizes a 3D scene and a learnable 2D overlay to recover a clean 3D scene and the corrupting artifacts. By exploiting geometric consensus across views, our method effectively disentangles static artifacts from the 3D scene geometry without supervision or manual input. Across diverse synthetic corruptions and a self-captured real-world dataset, SSA-3DGS improves reconstruction fidelity by up to ~8~dB PSNR over 3DGS trained on the same corrupted inputs, while faithfully preserving the corrupting artifact.