AI Paper Atlas

Research map / 3D vision / Depth and stereo

ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo Systems

Yinda Zhang, Sameh Khamis, Christoph Rhemann, Julien Valentin, Adarsh Kowdle, Vladimir Tankovich, Michael Schoenberg, Shahram Izadi, Thomas Funkhouser, Sean Fanello

ECCV 2018 · 3D vision › Depth and stereo · approach: Foundation models for monocular geometry · 124 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 invalidation mask excluding occluded pixels from the reconstruction loss (ablation)ActiveStereoNet · Synthetic active stereo test setpercentage of pixels with disparity error below thresholdImproved
use WLCN reconstruction loss instead of photometric or VGG perceptual loss (ablation)ActiveStereoNet · Synthetic and real active stereopixels with error smaller than 1 disparityImproved
add adaptive support weight window-based loss instead of single-pixel loss (ablation)ActiveStereoNet · Real active stereo scenesthin structure recovery and edge fatteningImproved
train self-supervised instead of supervised (ablation)ActiveStereoNet · Synthetic active stereo test setpixels with error below 5 disparity vs below 2 pixelsMixed
use full resolution inputs instead of half resolution (ablation)ActiveStereoNet · Real active stereo scenesthin structures and boundary detailImproved
use both active and passive illumination instead of either alone (ablation)ActiveStereoNet · Living room scenedisparity qualityImproved
increase training set size from 100 to 10000 images (ablation)ActiveStereoNet · Real unseen scenesdisparity sharpness: 100 -> 10000 imagesImproved
use WLCN self-supervised loss instead of supervised loss on SceneFlow-trained passive stereoPassive stereo network · Kitti 2012 and Kitti 2015 (trained on SceneFlow)EPEImproved

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