Research map / 3D vision / Gaussian splatting
Hi-Gaussian: Hierarchical Gaussians under Normalized Spherical Projection for Single-View 3D Reconstruction
Binjian Xie, Pengju Zhang, Hao Wei, Yihong Wu
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 Normalized Spherical Projection (ablation) | Hi-Gaussian · SemanticKITTI | PSNR: 16.47 -> 16.78 | Improved |
| add Normalized Spherical Projection (ablation) | Hi-Gaussian · SemanticKITTI | LPIPS: 0.364 -> 0.358 | Improved |
| add Normalized Spherical Projection (ablation) | Hi-Gaussian · BundleFusion | PSNR: 25.69 -> 25.50 | Hurt |
| add Normalized Spherical Projection (ablation) | Hi-Gaussian · BundleFusion | LPIPS: 0.187 -> 0.179 | Improved |
| add Hierarchical Gaussian Sampling (ablation) | Hi-Gaussian · SemanticKITTI | PSNR: 16.33 -> 16.78 | Improved |
| add Hierarchical Gaussian Sampling (ablation) | Hi-Gaussian · SemanticKITTI | SSIM: 0.491 -> 0.518 | Improved |
| add Hierarchical Gaussian Sampling (ablation) | Hi-Gaussian · BundleFusion | PSNR: 25.57 -> 25.50 | Hurt |
| add Hierarchical Gaussian Sampling (ablation) | Hi-Gaussian · BundleFusion | LPIPS: 0.189 -> 0.179 | Improved |
| normalize coordinates before spherical projection (vs un-normalized from SceneRF) (ablation) | Hi-Gaussian · SemanticKITTI | SSIM: 0.512 -> 0.518 | Improved |
| normalize coordinates before spherical projection (vs un-normalized from SceneRF) (ablation) | Hi-Gaussian · SemanticKITTI | PSNR: 16.76 -> 16.78 | No clear effect |
| normalize coordinates before spherical projection (vs un-normalized from SceneRF) (ablation) | Hi-Gaussian · SemanticKITTI | LPIPS: 0.370 -> 0.358 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Splatter Image — Splatter Image: Ultra-Fast Single-View 3D Reconstruction (CVPR 2024) · better on 6 of 6 shared results
- SceneRF — SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields (ICCV 2023) · better on 6 of 6 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
- Generalizable Human Gaussians from Single-View Image (ICLR 2025 · similarity 0.89)
- No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images (ICLR 2025 · similarity 0.88)
- 3D Gaussian Flats: Hybrid 2D/3D Photometric Scene Reconstruction (NeurIPS 2025 · similarity 0.88)
- HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction (ICLR 2025 · similarity 0.88)
- Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction (CVPR 2024 · similarity 0.88)
- ODG: Occupancy Prediction Using Dual Gaussians (NeurIPS 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.
