Research map / 3D vision / Gaussian splatting
Splatent: Splatting Diffusion Latents for Novel View Synthesis
Or Hirschorn, Omer Sela, Inbar Huberman-Spiegelglas, Netalee Efrat, Eli Alshan, Ianir Ideses, Frederic Devernay, Yochai Zvik, Lior Fritz
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add diffusion-based multi-view refinement of rendered latents | latent 3DGS (vs LRF) · DL3DV-10K dense | PSNR: 20.19 -> 21.94 | Improved |
| add diffusion-based multi-view refinement of rendered latents | latent 3DGS (vs LRF) · DL3DV-10K sparse | FID: 204.36 -> 86.12 | Improved |
| apply Splatent trained only on DL3DV-10K to unseen datasets | Splatent · LLFF/Mip-NeRF360 dense | PSNR: LLFF 17.98 -> 19.57; Mip-NeRF360 19.08 -> 20.42 (vs LRF) | Improved |
| use Splatent refinement for 3D consistency | latent radiance field · DL3DV-10K | MEt3R: 0.1082 -> 0.0774 (dense) | Improved |
| add reference views to the diffusion input grid (0 -> 1) (ablation) | Splatent · DL3DV-10K dense | PSNR: 19.47 -> 21.61 | Improved |
| increase reference views from 3 to 5 (ablation) | Splatent · DL3DV-10K dense | PSNR: 21.94 -> 21.96 | No clear effect |
| increase reference views from 1 to 3 (ablation) | Splatent · DL3DV-10K dense | LPIPS/FID: FID 38.04 -> 35.60 | Improved |
| integrate Splatent into feed-forward MVSplat360 | MVSplat360 · DL3DV-10K 5 views | PSNR: 16.691 -> 17.976 | Improved |
| integrate Splatent into feed-forward MVSplat360 | MVSplat360 · DL3DV-10K 5 views | FID: 13.462 -> 11.097 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MVSplat360 — MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views (NeurIPS 2024) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Generative Sparse-View Gaussian Splatting (CVPR 2025 · similarity 0.91)
- DIFIX3D+: Improving 3D Reconstructions with Single-Step Diffusion Models (CVPR 2025 · similarity 0.91)
- Wonderland: Navigating 3D Scenes from a Single Image (CVPR 2025 · similarity 0.91)
- 3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors (NeurIPS 2024 · similarity 0.90)
- 3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes (CVPR 2025 · similarity 0.89)
- SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis (CVPR 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
