AI Paper Atlas

Research map / 3D vision / Depth and stereo

Unsupervised Adaptation for Deep Stereo

Alessio Tonioni, Matteo Poggi, Stefano Mattoccia, Luigi Di Stefano

ICCV 2017 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 108 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 unsupervised adaptation with AD-CENSUS targets and confidence-guided lossDispNet · KITTI 2015 trainbad 3 (%): 7.46 -> 4.02Improved
add unsupervised adaptation with SGM targets and confidence-guided lossDispNet · KITTI 2015 trainbad 3 (%): 7.46 -> 4.21Improved
add unsupervised adaptation with SGM targetsDispNet · Middlebury 2014 (quarter res)bad 1 (%): 32.82 -> 22.91Improved
add unsupervised adaptation with AD-CENSUS targetsDispNet · Middlebury 2014 (quarter res)bad 1 (%): 32.82 -> 25.38Improved
add supervised fine-tuning on KITTI 2012 ground truthDispNet · Middlebury 2014 (quarter res)bad 1 (%): 32.82 -> 40.21Hurt
add supervised fine-tuning on KITTI 2012 ground truthDispNet · KITTI 2015 trainbad 3 (%): 7.46 -> 4.58Improved
replace supervised KITTI 2012 fine-tuning with unsupervised adaptation (CENSUS) on the same framesDispNet · KITTI 2015 train (generalization)bad 3 (%): 4.58 -> 4.34Improved
replace supervised KITTI 2012 fine-tuning with unsupervised adaptation (CENSUS)DispNet · KITTI 2012 trainbad 3 (%): 2.89 -> 4.29Hurt
raise confidence threshold tau up to 0.99 (ablation)DispNet unsupervised adaptation · KITTI 2012 train / KITTI 2015 (10000 steps)bad 3 (%)Improved
add smoothness term with lambda = 0.1 (ablation)DispNet unsupervised adaptation · KITTI 2015 generalizationbad 3 (%)Improved
increase smoothness weight lambda beyond 0.6 (ablation)DispNet unsupervised adaptation · KITTI 2012 trainbad 3 (%)Hurt
use only stereo pairs with ground truth (000000_10) instead of all KITTI 2015 pairs (ablation)DispNet CENSUS adaptation · KITTI 2015 trainbad 3 (%): 0.09% error rate and 0.04% avg disparity error increaseNo clear effect

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