AI Paper Atlas

Research map / 3D vision / Depth and stereo

NeRF-Supervised Deep Stereo

Fabio Tosi, Alessio Tonioni, Daniele De Gregorio, Matteo Poggi

CVPR 2023 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 49 citations (OpenAlex)

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 changedWhereMeasuredEffect
Train with NeRF-supervised triplets and filtered rendered disparity rather than the MfS pipelineRAFT-Stereo · Midd-A FF (>2px): 24.61 -> 13.12Improved
Train with NeRF-supervised triplets rather than the MfS pipelineCFNet · KITTI-12D1 (>3px): 4.47 -> 4.64Hurt
Train using NeRF supervision rather than synthetic ground-truth trainingRAFT-Stereo · ETH3DAll (>1px): 2.59 -> 2.94Mixed
Add rendered disparity supervision to triplet photometric supervision (ablation)RAFT-Stereo · KITTI-12D1 (>3px): 5.11 -> 4.21Improved
Use triplet rather than pairwise photometric supervision alongside filtered disparity loss (ablation)RAFT-Stereo · Midd-A FF (>2px): 16.11 -> 15.31Improved
Filter NeRF-rendered disparity labels using the AO threshold (ablation)RAFT-Stereo with rendered disparity supervision · KITTI-12D1 (>3px): 5.79 -> 4.49Improved
Add triplet photometric loss to filtered rendered disparity supervision (ablation)RAFT-Stereo · Midd-A FF (>2px): 15.50 -> 15.31Improved
Use rendered disparity supervision alone instead of triplet photometric supervision (ablation)RAFT-Stereo · Midd-A FF (>2px): 28.33 -> 21.71Hurt
Add AO-based weighting to the two loss terms (ablation)RAFT-Stereo with triplet photometric and filtered disparity losses · Midd-21(>2px): 16.26 -> 14.87Improved
Train for 200K rather than 100K steps (ablation)RAFT-Stereo with full NS loss · Midd-21(>2px): 14.87 -> 12.87Improved
Add medium and small baselines to the large baseline (ablation)RAFT-Stereo · Midd-A FF (>2px): 18.71 -> 14.92Improved
Add medium and small baselines to the large baseline (ablation)RAFT-Stereo · KITTI-12D1 (>3px): 3.97 -> 4.31Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy