Research map / 3D vision / Gaussian splatting
GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction
Yuxuan Mu, Xinxin Zuo, Chuan Guo, Yilin Wang, Juwei Lu, Xiaofei Wu, Songcen Xu, Peng Dai, Youliang Yan, Li Cheng
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 iterative polishing and re-using with an auxiliary 2D diffusion model (ablation) | GSD · CO3D single-view, all categories | PSNR: 18.07 -> 18.49 | Improved |
| add iterative polishing and re-using (ablation) | GSD · CO3D single-view, all categories | LPIPS: 0.303 -> 0.288 | Improved |
| use view-guided sampling via splatting gradients instead of forward point projection conditioning with classifier-free guidance (ablation) | GSD · CO3D | view quality | Improved |
| use transformer backbone instead of PVCNN for the GS denoiser (ablation) | GSD · CO3D / unconditional generation | generation quality | Improved |
| use GSD instead of ViewFormer for single-view reconstruction | CO3D single-view · CO3D all categories | PSNR: 16.87 -> 18.49 | Improved |
| use GSD instead of SparseFusion for two-view reconstruction | CO3D two-view · CO3D core-10 categories | PSNR: Bench 16.7 -> 18.4; Plant 20.0 -> 19.0 | Mixed |
| use L1 loss instead of MSE for GS denoiser training (ablation) | GSD · CO3D | training quality | 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.
- ViewFormer — ViewFormer: NeRF-Free Neural Rendering from Few Images Using Transformers (ECCV 2022) · 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
- Generative Sparse-View Gaussian Splatting (CVPR 2025 · similarity 0.94)
- DiffGS: Functional Gaussian Splatting Diffusion (NeurIPS 2024 · similarity 0.92)
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · similarity 0.92)
- DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation (ICLR 2025 · similarity 0.91)
- SplatFormer: Point Transformer for Robust 3D Gaussian Splatting (ICLR 2025 · 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.
