Research map / 3D vision / Gaussian splatting
EcoSplat: Efficiency-controllable Feed-forward 3D Gaussian Splatting from Multi-view Images
Jongmin Park, Minh-Quan Viet Bui, Juan Luis Gonzalez, Jaeho Moon, Jihyong Oh, Munchurl Kim
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 importance-aware finetuning (IGF) stage (ablation) | EcoSplat · RE10K (24 views, 5% Gaussians) | PSNR: 6.45 -> 24.72 | Improved |
| add pixel-aligned Gaussian training (PGT) stage before finetuning (ablation) | EcoSplat · RE10K (24 views, 5% Gaussians) | PSNR: 22.93 -> 24.72 | Improved |
| add importance-aware opacity loss Lio (ablation) | EcoSplat · RE10K (24 views, 5% Gaussians) | PSNR: 20.58 -> 24.72 | Improved |
| add Lio at 40% Gaussians (ablation) | EcoSplat · RE10K (24 views, 40% Gaussians) | PSNR: 23.81 -> 25.11 | Improved |
| add progressive learning on Gaussian compaction (PLGC) (ablation) | EcoSplat · RE10K (24 views, 5% Gaussians) | PSNR: 21.49 -> 24.72 | Improved |
| add PLGC at 40% Gaussians (ablation) | EcoSplat · RE10K (24 views, 40% Gaussians) | PSNR: 23.84 -> 25.11 | Improved |
| condition on target primitive count instead of voxel-size tuning (vs AnySplat) | feed-forward 3DGS · RE10K (24 views, 5% Gaussians) | PSNR: 8.08 -> 24.72 | Improved |
| apply training-free post-pruning (LightGaussian, PUP 3D-GS) to pixel-aligned feed-forward Gaussians | SPFSplat · RE10K (24 views, 40% Gaussians) | PSNR: 12.01 vs 25.11 for EcoSplat | Hurt |
| use EcoSplat at 40% Gaussians instead of full pixel-aligned SPFSplat on unseen domain | EcoSplat · ACID zero-shot (24 views) | PSNR: 24.40 -> 24.02 | Hurt |
| reduce primitives from 40% to 5% of pixel-aligned Gaussians | EcoSplat · RE10K (24 views) | PSNR: 25.11 -> 24.72 | No clear effect |
Later papers that compared with this method
1 later accepted paper reports EcoSplat as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens (ECCV 2026 · better on 1 of 1 shared result)
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
- CompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene Reconstruction (NeurIPS 2026 · similarity 0.92)
- Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.92)
- MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models (CVPR 2025 · similarity 0.91)
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · similarity 0.91)
- pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction (CVPR 2024 · similarity 0.91)
- GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting (CVPR 2025 · similarity 0.91)
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.
