Research map / 3D vision / Gaussian splatting
ExploreGS: Explorable 3D Scene Reconstruction with Virtual Camera Samplings and Diffusion Priors
Minsu Kim, Subin Jeon, In Cho, Mijin Yoo, Seon Joo Kim
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 |
|---|---|---|---|
| use GS view coverage instead of grid view coverage for information gain (ablation) | ExploreGS · Curated Nerfbusters | PSNR: 15.82 -> 16.29 | Improved |
| use GS view coverage instead of FisherRF uncertainty (ablation) | ExploreGS · Curated Nerfbusters | PSNR: 15.77 -> 16.29 | Improved |
| select top-K instead of bottom-K candidate views (ablation) | ExploreGS · Garbage scene | PSNR: 14.22 -> 15.45 | Improved |
| bottom-K selection versus plain 3DGS (ablation) | ExploreGS bottom-K · Garbage scene | PSNR: 14.42 -> 14.22 | No clear effect |
| add GS-IOU image-level and pixelLPIPS pixel-level confidence versus distance and scale (ablation) | ExploreGS finetuning · Curated Nerfbusters | PSNR: 15.27 -> 16.29 | Improved |
| add GS-IOU image-level confidence to pixelLPIPS (ablation) | ExploreGS finetuning · Curated Nerfbusters | LPIPS: 0.441 -> 0.434 | Improved |
| add pixelLPIPS to GS-IOU (ablation) | ExploreGS finetuning · Curated Nerfbusters | LPIPS: 0.439 -> 0.434 | Improved |
| add confidence terms versus no confidence (ablation) | ExploreGS finetuning · Curated Nerfbusters | PSNR: 16.30 -> 16.29 | No clear effect |
| add image-level distance confidence to scale pixel confidence (ablation) | ExploreGS finetuning · Curated Nerfbusters | PSNR: 16.18 -> 15.27 | Hurt |
| use ExploreGS instead of ViewExtrapolator (ablation) | ExploreGS · WildExplore | PSNR: 16.02 -> 16.96 | Improved |
Closest papers by meaning
- 3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors (NeurIPS 2024 · similarity 0.92)
- Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputs (CVPR 2025 · similarity 0.92)
- Wonderland: Navigating 3D Scenes from a Single Image (CVPR 2025 · similarity 0.91)
- Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting (NeurIPS 2025 · similarity 0.91)
- GaussianPro: 3D Gaussian Splatting with Progressive Propagation (ICML 2024 · similarity 0.90)
- LP-3DGS: Learning to Prune 3D Gaussian Splatting (NeurIPS 2024 · 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.
