Research map / 3D vision / Gaussian splatting
IDESplat: Iterative Depth Probability Estimation for Generalizable 3D Gaussian Splatting
Wei Long, Haifeng Wu, Shiyin Jiang, Jinhua Zhang, Xinchun Ji, Shuhang Gu
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 Gaussian Focused Module (ablation) | IDESplat baseline · RealEstate10K (20k-iter) | PSNR: 26.31 -> 26.63 | Improved |
| add 3 iterations of depth probability boosting units (ablation) | IDESplat baseline · RealEstate10K (20k-iter) | PSNR: 26.31 -> 26.88 | Improved |
| add depth probability boosting strategy to the iterative process (ablation) | IDESplat (IDE(3)) · RealEstate10K (20k-iter) | PSNR: 26.88 -> 27.34 | Improved |
| add GFM to IDE(3)+DPBS (ablation) | IDESplat · RealEstate10K (20k-iter) | PSNR: 27.34 -> 27.56 | Improved |
| go from single warp to 1 iteration (ablation) | IDESplat · RealEstate10K (20k-iter) | PSNR: 26.63 -> 27.08 | Improved |
| increase iterations from 3 to 4 (ablation) | IDESplat · RealEstate10K (20k-iter) | PSNR: 27.56 -> 27.64 | Improved |
| increase iterations from 3 to 4 (ablation) | IDESplat · RealEstate10K (20k-iter) | Time (s): 0.110 -> 0.132 | Hurt |
| IDESplat versus DepthSplat in model size | IDESplat · RealEstate10K | Params (M): 354 -> 37.6 | Improved |
| IDESplat versus DepthSplat in inference time | IDESplat · RealEstate10K | Time (s): 0.082 -> 0.110 | Hurt |
| IDESplat versus DepthSplat zero-shot transfer | IDESplat · RE10K->DTU | PSNR: 15.38 -> 18.33 | Improved |
| IDESplat versus DepthSplat depth estimation | IDESplat · ScanNet depth | Abs Rel: 0.045 -> 0.039 | Improved |
| IDESplat versus MonoSplat on ACID (in-domain) | IDESplat · ACID | SSIM: 0.864 -> 0.866 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- DepthSplat — DepthSplat: Connecting Gaussian Splatting and Depth (CVPR 2025) · better on 8 of 8 shared results
- MonoSplat — MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models (CVPR 2025) · better on 5 of 5 shared results
- pixelSplat — pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction (CVPR 2024) · better on 2 of 2 shared results
- MVSplat — MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images (ECCV 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
- DepthSplat: Connecting Gaussian Splatting and Depth (CVPR 2025 · similarity 0.92)
- TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers (AAAI 2025 · similarity 0.90)
- MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models (CVPR 2025 · similarity 0.89)
- HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction (ICLR 2025 · similarity 0.89)
- PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting for Novel View Synthesis (ICML 2025 · similarity 0.88)
- EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis (CVPR 2025 · similarity 0.88)
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.
