Research map / 3D vision / Gaussian splatting
R3RECON: Radiance-Field-Free Active Reconstruction via Renderability
Xiaofeng Jin, Matteo Frosi, Yiran Guo, Matteo Matteucci
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 |
|---|---|---|---|
| replace Active-GS view utility with renderability-based information gain | Active-GS · Replica-Dense Office1 (time budget) | PSNR (dB): 31.39 -> 37.14 | Improved |
| replace Active-GS view utility with renderability-based information gain | Active-GS · Replica-Dense (time budget, 9 scenes) | PSNR (dB): about 3--5 dB | Improved |
| replace Active-GS view utility with renderability-based information gain | Active-GS · Replica-Dense Office3 (view budget) | PSNR (dB): 29.57 -> 27.69 | Hurt |
| replace Active-GS view utility with renderability-based information gain | Active-GS · Replica-Dense Room2 (time budget) | PSNR (dB): 25.07 -> 31.24 | Improved |
| add panoramic 360 degree pose-level utility (ablation) | Ours · Replica-Dense Office3 (time budget) | PSNR (dB): 28.93 -> 30.91 | Improved |
| add panoramic 360 degree pose-level utility (ablation) | Ours · Replica-Dense Office3 (view budget) | PSNR (dB): 27.69 -> 31.26 | Improved |
| add panoramic 360 degree pose-level utility (ablation) | Ours · Replica-Dense Room0 (time budget) | PSNR (dB): 27.85 -> 29.41 | Improved |
| add panoramic 360 degree pose-level utility (ablation) | Ours · Replica-Dense Hotel0 (time budget) | PSNR (dB): 26.93 -> 25.95 | Hurt |
| add panoramic 360 degree pose-level utility (ablation) | Ours · Replica-Dense Room2 (time budget) | PSNR (dB): 31.24 -> 29.23 | Hurt |
| add panoramic 360 degree pose-level utility (ablation) | Ours · Replica-Dense Office1 (view budget) | PSNR (dB): 36.01 -> 36.50 | Mixed |
| use renderability voxel map instead of accumulating a radiance field for planning | Active-GS · peak GPU memory | PSNR (dB): below 300 MB | 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.
- ActiveGAMER — ActiveGAMER: Active GAussian Mapping through Efficient Rendering (CVPR 2025) · better on 1 of 1 shared result
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
- GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction (CVPR 2024 · similarity 0.90)
- Omni-Recon: Harnessing Image-based Rendering for General-Purpose Neural Radiance Fields (ECCV 2024 · similarity 0.88)
- ActivePolicy: Active Gaussian Reconstruction and Optimization Strategy Based on Global-Local Information Gain (CVPR 2026 · similarity 0.88)
- pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction (CVPR 2024 · similarity 0.87)
- Learning with Unreliability: Fast Few-shot Voxel Radiance Fields with Relative Geometric Consistency (CVPR 2024 · similarity 0.86)
- FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors (CVPR 2025 · similarity 0.86)
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.
