SplatAnything: Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary Scenes
Paper · https://arxiv.org/abs/2611.08264
We identify a key limitation of existing feed-forward 3DGS methods: Gaussian attributes are typically predicted in a radial-distance-normalized space that canonicalizes a global radial statistic of the reconstructed geometry, while the spacing between neighboring Gaussian centers can still vary substantially across scene scales and camera configurations. This mismatch induces systematic shifts in Gaussian-scale targets, leading to ambiguous supervision. To address this, we propose SplatAnything with Gaussian Spacing Normalization (GSNorm), which canonicalizes a robust scene-level statistic of Gaussian spacing to provide a more consistent spatial reference for Gaussian prediction. To rigorously assess our method, we further establish a systematic benchmark spanning diverse datasets, input sparsity levels, and challenging extrapolated viewpoints. Extensive experiments demonstrate that SplatAnything achieves state-of-the-art performance, with particularly strong gains under substantial variations in scene scale and viewpoint.
First seen by Oriel on .
AI summary
SplatAnything introduces Gaussian Spacing Normalization to improve feed-forward 3DGS across varying scene scales, camera configurations, sparse inputs, and extrapolated viewpoints.
- Existing methods normalize Gaussian attributes by radial distance, but neighboring Gaussian spacing still varies across scene scales and camera configurations.
- GSNorm canonicalizes a robust scene-level statistic of Gaussian spacing, creating a more consistent spatial reference for predicting Gaussian attributes.
- The authors establish a benchmark covering diverse datasets, input sparsity levels, and challenging extrapolated viewpoints.
- Experiments report state-of-the-art performance, with particularly strong gains under substantial scene-scale and viewpoint variation.
#3d gaussian splatting #computer vision #3d reconstruction
Generated by gpt-5.6-sol. Check the original for details.
Metric trends
Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained
Points
Score reported by the source.
- Hugging Face Papers: 70, latest observation ; +11 over observed period since
Comments
Comment count reported by the source.
- Hugging Face Papers: 2, latest observation ; +1 over observed period since
Aliases
| Source | External ID | URL |
|---|---|---|
| Hugging Face Papers | 2611.08264 | https://arxiv.org/abs/2611.08264 Read discussion |