Research map / 3D vision / Gaussian splatting
Gamba: Marry Gaussian Splatting With Mamba for Single-View 3D Reconstruction
Qiuhong Shen, Zike Wu, Xuanyu Yi, Pan Zhou, Hanwang Zhang, Shuicheng Yan, Xinchao Wang
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 radial mask constraint loss (ablation) | Gamba · G-buffer Objaverse subset | PSNR: 12.72 -> 23.81 | Improved |
| add additive 3DGS tokens (image tokens plus learnable embeddings) (ablation) | Gamba · G-buffer Objaverse subset | PSNR: 20.35 -> 23.81 | Improved |
| add prepending of camera and image tokens (ablation) | Gamba · G-buffer Objaverse subset | PSNR: 22.57 -> 23.81 | Improved |
| add prepending of camera and image tokens (ablation) | Gamba · G-buffer Objaverse subset | LPIPS: 0.10 -> 0.12 | Hurt |
| add Tri-plane branch (Triplane-Gamba) (ablation) | Gamba · G-buffer Objaverse subset | PSNR | Hurt |
| build part of the tokens (12,288) from pure positional embeddings (ablation) | Gamba · G-buffer Objaverse subset | visual quality | Hurt |
| replace Transformer with Mamba backbone to allow 16384 Gaussians (ablation) | Gamba vs Transformer · memory vs token length | memory | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- DreamGaussian — DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation (ICLR 2024) · better on 3 of 3 shared results
- Zero-1-to-3 — Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023) · better on 3 of 3 shared results
- One-2-3-45 — One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization (NeurIPS 2023) · 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
- Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers (CVPR 2024 · similarity 0.89)
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · similarity 0.89)
- Splatter Image: Ultra-Fast Single-View 3D Reconstruction (CVPR 2024 · similarity 0.89)
- GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting (CVPR 2025 · similarity 0.88)
- SfM-Free 3D Gaussian Splatting via Hierarchical Training (CVPR 2025 · similarity 0.88)
- KeyGS: A Keyframe-Centric Gaussian Splatting Method for Monocular Image Sequences (AAAI 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.
