Research map / 3D vision / 3D generation
GSV3D: Gaussian Splatting-based Geometric Distillation with Stable Video Diffusion for Single-Image 3D Object Generation
Ye Tao, Jiawei Zhang, Yahao Shi, Dongqing Zou, Bin Zhou
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 RGB loss in geometric distillation (ablation) | GSV3D · GSO (100 objects) | PSNR: 19.551 -> 20.390 | Improved |
| add depth loss in geometric distillation (ablation) | GSV3D · GSO (100 objects) | PSNR: 19.826 -> 20.390 | Improved |
| use 16 frames instead of 8 in multi-view latents (ablation) | GSV3D · GSO (100 objects) | PSNR: 19.733 -> 20.390 | Improved |
| use 16 frames instead of 4 in multi-view latents (ablation) | GSV3D · GSO (100 objects) | PSNR: 19.548 -> 20.390 | Improved |
| add DINO encoder cross-attention to Gaussian Splatting Decoder (ablation) | GSV3D · GSO (100 objects) | PSNR: 19.508 -> 20.390 | Improved |
| use 16 frames instead of 4 (ablation) | GSV3D · GSO (100 objects) | FID: 57.85 -> 50.79 | Improved |
| add RGB loss (ablation) | GSV3D · GSO (100 objects) | FID: 53.89 -> 50.79 | Improved |
| add depth loss (ablation) | GSV3D · GSO (100 objects) | FID: 53.20 -> 50.79 | Improved |
| add DINO encoder (ablation) | GSV3D · GSO (100 objects) | FID: 55.20 -> 50.79 | Improved |
| add Gaussian Splatting geometric distillation to SV3D | SV3D · GSO (100 objects) | PSNR: 17.772 -> 20.390 | Improved |
| add Gaussian Splatting geometric distillation to SV3D | SV3D · GSO (100 objects) | FID: 74.86 -> 50.79 | Improved |
| add Gaussian Splatting geometric distillation to SV3D | SV3D · GSO (100 objects) | Chamfer Distance: 0.200 -> 0.100 | Improved |
Closest papers by meaning
- DirectTriGS: Triplane-based Gaussian Splatting Field Representation for 3D Generation (CVPR 2025 · similarity 0.91)
- GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting (CVPR 2025 · similarity 0.91)
- Generative Sparse-View Gaussian Splatting (CVPR 2025 · similarity 0.91)
- DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation (ICLR 2025 · similarity 0.90)
- SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis (CVPR 2025 · similarity 0.90)
- VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment (NeurIPS 2025 · similarity 0.90)
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.
