AI Paper Atlas

Research map / 3D vision / Depth and stereo

Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation

Filippo Aleotti, Fabio Tosi, Li Zhang, Matteo Poggi, Stefano Mattoccia

ECCV 2020 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 51 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
add random input point sampling (R) (ablation)MCN-SGM/L · KITTI 2015 proxy quality (Noc)D1 (%): 6.36 -> 5.28Improved
add consensus mechanism on top of random sampling (ablation)MCN-SGM/L-R · KITTI 2015 proxy quality (Noc)D1 (%): 5.28 -> 2.95Improved
add augmentation to random sampling and consensus (ablation)MCN-SGM/L-RC · KITTI 2015 proxy quality (Noc)D1 (%): 2.95 -> 2.78Improved
add random sampling to MCN with BM/W points (ablation)MCN-BM/W · KITTI 2015 proxy quality (Noc)D1 (%): 11.86 -> 6.79Improved
add consensus to random sampling for BM/W (ablation)MCN-BM/W-R · KITTI 2015 proxy quality (Noc)D1 (%): 6.79 -> 3.79Improved
train PSMNet on MCN-BM/W-ARC proxies instead of photometric lossPSMNet · KITTI 2015D1 Noc (%): 6.62 -> 3.68Improved
use MCN-BM/W-ARC proxies instead of BM/W proxiesPSMNet · KITTI 2015D1 Noc (%): 6.89 -> 3.68Improved
use MCN-BM/W-ARC proxies instead of BM/W proxiesStereodepth · KITTI 2015D1 Noc (%): 5.19 -> 4.21Improved
add hole-filling to SGM/L proxies (ablation)PSMNet · KITTI 2015D1 Noc (%): 5.46 -> 6.06Hurt
add full consensus and augmentation (ARC) to MCN-BM/W-R (ablation)PSMNet · KITTI 2015D1 Noc (%): 4.30 -> 3.68Improved
use MCN-BM/W-ARC proxies instead of LiDAR/SGMPSMNet · KITTI 2015D1 Noc (%): 3.93 -> 3.68Improved
use MCN proxies instead of BM/W on DrivingStereoPSMNet · DrivingStereo (DS->DS)D1 (%): 8.81 -> 1.87Improved

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