AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

ActiveZero: Mixed Domain Learning for Active Stereovision With Zero Annotation

Isabella Liu, Edward Yang, Jianyu Tao, Rui Chen, Xiaoshuai Zhang, Qing Ran, Zhu Liu, Hao Su

CVPR 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Pretext-task visual pre-training · 13 citations (OpenAlex)

Check 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
Use patch size 15 instead of patch size 11 (ablation)ActiveZero patch-wise reprojection loss · Testing datasetAbs depth err (mm): 5.115 -> 5.114Improved
Use patch size 21 instead of patch size 11 (ablation)ActiveZero patch-wise reprojection loss · Testing dataset> 4mm: 0.393 -> 0.385Improved
Use patch size 7 instead of patch size 11 (ablation)ActiveZero patch-wise reprojection loss · Testing datasetAbs depth err (mm): 5.115 -> 5.507Hurt
Set λs=1 and λr=0.5 instead of λs=0.01 and λr=2 (ablation)ActiveZero · Testing datasetAbs depth err (mm): 4.377 -> 7.578Hurt
Set λs=1 and λr=1 instead of λs=0.01 and λr=2 (ablation)ActiveZero · Testing datasetAbs depth err (mm): 4.377 -> 6.064Hurt
Set λs=1 and λr=2 instead of λs=0.01 and λr=2 (ablation)ActiveZero · Testing datasetAbs depth err (mm): 4.377 -> 5.672Hurt
Set λs=0.05 and λr=2 instead of λs=0.01 and λr=2 (ablation)ActiveZero · Testing datasetAbs depth err (mm): 4.377 -> 5.543Hurt
Set λs=0.002 and λr=2 instead of λs=0.01 and λr=2 (ablation)ActiveZero · Testing datasetAbs depth err (mm): 4.377 -> 4.683Hurt
Add the 6-layer filter (ablation)ActiveZero · Testing datasetAbs depth err (mm): 4.592 -> 4.377Improved
Add the 6-layer filter (ablation)ActiveZero · Testing dataset> 4mm: 0.356 -> 0.335Improved
Use simulation disparity loss (ablation)ActiveZero · Simulation trainingConvergence rateImproved
Use ActiveZero instead of StereoGAN+PSMStereo inference · Inference, 960×540 image pairInference Time(s): 0.303 -> 0.256Improved

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