Research map / 3D vision / Gaussian splatting
MLP Splatting: Object-Centric Neural Fields
Shinjeong Kim, Yuzhou Cheng, Xin Kong, Paul Kelly, Andrew Davison
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 |
|---|---|---|---|
| co-train semantic feature embeddings with RGB (ablation) | MLP-Splatting · Replica | PSNR: 35.57 -> 36.25 | Improved |
| use 4 feature slots instead of 1 (ablation) | MLP-Splatting · Replica | mIoU: 76.5 -> 77.7 | Improved |
| use 8 feature slots instead of 4 (ablation) | MLP-Splatting · Replica | mIoU: 77.7 -> 78.2 | No clear effect |
| use more primitives (octree m=5 versus m=20) (ablation) | MLP-Splatting · Replica room0 | PSNR: 35.88 -> 36.42 | Improved |
| use 8x8 tile-center sorting instead of per-pixel sorting (ablation) | MLP-Splatting · ScanNet room0 | PSNR: 36.58 -> 36.23 | Hurt |
| use independent MLP primitives instead of Feature-3DGS Gaussians (ablation) | MLP-Splatting · Replica | memory: 629.7 -> 32.0 MB | Improved |
| use independent MLP primitives instead of Feature-3DGS on ScanNet (ablation) | MLP-Splatting · ScanNet | PSNR: 23.32 -> 25.35 | Improved |
| use independent MLP primitives instead of Feature-3DGS on Replica (ablation) | MLP-Splatting · Replica | LPIPS: 0.079 -> 0.090 | Hurt |
| use MLP primitives versus Feature-3DGS for semantics on Replica | MLP-Splatting · Replica | mIoU: 78.9 -> 77.7 | Mixed |
Closest papers by meaning
- Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields (CVPR 2024 · similarity 0.91)
- Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis (NeurIPS 2024 · similarity 0.90)
- FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training (NeurIPS 2024 · similarity 0.90)
- Compact 3D Gaussian Representation for Radiance Field (CVPR 2024 · similarity 0.90)
- HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis (NeurIPS 2025 · similarity 0.90)
- COLMAP-Free 3D Gaussian Splatting (CVPR 2024 · similarity 0.90)
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.
