Research map / 3D vision / NeRF and radiance fields
RANRAC: Robust Neural Scene Representations via Random Ray Consensus
Benno Buschmann, Andreea Dogaru, Elmar Eisemann, Michael Weinmann, Bernhard Egger
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 |
|---|---|---|---|
| apply RANRAC random-ray consensus to a pretrained LFN for occluded single-shot reconstruction | LFN · ShapeNet classes with 25% object occlusion | PSNR: Boat 19.2 -> 22.92; Rifle 18.46 -> 21.35 | Improved |
| apply RANRAC to LFN on the Display class | LFN · ShapeNet Display | PSNR: 18.85 -> 17.65 | Hurt |
| apply RANRAC to LFN on clean (unoccluded) images | LFN · clean ShapeNet images | reconstruction quality | Hurt |
| increase image occlusion amount | RANRAC vs LFN · ShapeNet plane/car/chair | PSNR: up to 8dB gain | Improved |
| replace robust-loss NeRF with RANRAC consensus filtering for occluded views | NeRF (instant-nsr) · Watering Pot strong occlusion | PSNR average: RobustNeRF 25.93 -> RANRAC 26.12 | Improved |
| apply RANRAC to NeRF with noisy camera parameters | NeRF (instant-nsr) · Noisy camera parameters, Lego | PSNR average: 24.67 -> 34.95 | Improved |
| apply RANRAC to NeRF with blurred perspectives on Ship scene | NeRF (instant-nsr) · Blurred perspectives, Ship | PSNR 5th percentile: 20.35 -> 16.14 | Hurt |
| use RANRAC on NeRF with blurred Ship scene (average PSNR) | NeRF (instant-nsr) · Blurred perspectives, Ship | PSNR average: 28.48 -> 29.76 | Improved |
Closest papers by meaning
- Latent RANSAC (CVPR 2018 · similarity 0.87)
- BANSAC: A Dynamic BAyesian Network for Adaptive SAmple Consensus (ICCV 2023 · similarity 0.86)
- Learning To Find Good Models in RANSAC (CVPR 2022 · similarity 0.86)
- On the Instability of Relative Pose Estimation and RANSAC's Role (CVPR 2022 · similarity 0.86)
- ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Field (NeurIPS 2024 · similarity 0.85)
- CRAYM: Neural Field Optimization via Camera RAY Matching (NeurIPS 2024 · similarity 0.85)
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.
