Research map / 3D vision / Gaussian splatting
S2D: Sparse to Dense Lifting for 3D Reconstruction with Minimal Inputs
Yuzhou Ji, Qijian Tian, He Zhu, Xiaoqi Jiang, Guangzhi Cao, Lizhuang Ma, Yuan Xie, Xin Tan
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 mixing module on input view instead of directly batching point cloud rendering (ablation) | S2D artifact fixer · Artifact fixer guidance ablation | PSNR: 19.0 -> 22.1 | Improved |
| add DINO guidance in the mixing module (ablation) | S2D artifact fixer · Artifact fixer guidance ablation | PSNR: 22.1 -> 23.0 | Improved |
| place mixing on image inputs rather than on VAE latents (ablation) | S2D artifact fixer · Artifact fixer guidance ablation | PSNR: 15.6 -> 23.0 | Improved |
| add reference view to point-cloud-only generation (dual guidance) (ablation) | S2D artifact fixer · Artifact fixer guidance ablation | PSNR: 12.7 -> 23.0 | Improved |
| add SSIM loss (ablation) | S2D artifact fixer · Artifact fixer loss ablation | PSNR: 20.1 -> 21.8 | Improved |
| add DINO loss (ablation) | S2D artifact fixer · Artifact fixer loss ablation | PSNR: 20.1 -> 20.5 | Improved |
| add CLIP loss (ablation) | S2D artifact fixer · Artifact fixer loss ablation | PSNR: 20.1 -> 20.1 | No clear effect |
| add DINO loss on top of SSIM loss (ablation) | S2D artifact fixer · Artifact fixer loss ablation | PSNR: 21.8 -> 22.0 | Improved |
| add S2D on top of 3DGS (ablation) | 3DGS · DL3DV (6 images) | PSNR: 15.26 -> 23.2 | Improved |
| replace DIFIX fixer with S2D | 3DGS reconstruction · 3DOVS (1 image) | PSNR: 14.10 -> 21.41 | Improved |
| replace DIFIX with S2D on lane shift | Waymo reconstruction · Waymo Open Dataset (lane shift 2m) | FID: 60.2 -> 46.1 | Improved |
| add random sample drop (alpha 0.7) to reconstruction (ablation) | S2D reconstruction · DL3DV scenes | qualitative | 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.
- DepthSplat — DepthSplat: Connecting Gaussian Splatting and Depth (CVPR 2025) · better on 3 of 3 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
- D$^2$GS: Depth-and-Density Guided Gaussian Splatting for Stable and Accurate Sparse-View Reconstruction (ICLR 2026 · similarity 0.90)
- S2Gaussian: Sparse-View Super-Resolution 3D Gaussian Splatting (CVPR 2025 · similarity 0.90)
- Confidence-Guided Multi-Scale Aggregation for Sparse-View High-Resolution 3D Gaussian Splatting (CVPR 2026 · similarity 0.90)
- Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views (CVPR 2025 · similarity 0.89)
- Generative Sparse-View Gaussian Splatting (CVPR 2025 · similarity 0.88)
- EAP-GS: Efficient Augmentation of Pointcloud for 3D Gaussian Splatting in Few-shot Scene Reconstruction (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.
