AI Paper Atlas

Research map / 3D vision / Depth and stereo

HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching

Vladimir Tankovich, Christian Hane, Yinda Zhang, Adarsh Kowdle, Sean Fanello, Sofien Bouaziz

CVPR 2021 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 310 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 HITNet XL instead of EdgeStereoStereo matching on SceneFlow · SceneFlow finalpassEPE: 0.74 -> 0.36Improved
Use HITNet XL instead of StereoNetStereo matching on SceneFlow · SceneFlow finalpassRuntime: 0.015 -> 0.114Hurt
Use HITNet instead of R-StereoStereo matching on ETH3D · ETH3D stereoEPE: 0.18 -> 0.20Hurt
Use HITNet instead of R-StereoStereo matching on ETH3D · ETH3D stereoRuntime: 0.81 s -> 0.02 sImproved
Use HITNet instead of LEAStereoStereo matching on KITTI 2012 · KITTI 20122-all: 2.39 -> 2.65Hurt
Use HITNet instead of LEAStereoStereo matching on KITTI 2012 · KITTI 2012EPE-all: 0.5 -> 0.5No clear effect
Use HITNet instead of LEAStereoStereo matching on KITTI 2015 · KITTI 2015D1-all: 1.65 -> 1.98Hurt
Use HITNet instead of LEAStereoStereo matching on KITTI 2015 · KITTI 2015Runtime: 0.3s -> 0.02sImproved
Use HITNet instead of LEAStereoStereo matching on Middlebury V3 · Middlebury V3RMS: 8.11 -> 9.97Hurt
Use HITNet instead of LEAStereoStereo matching on Middlebury V3 · Middlebury V3AvgErr: 1.43 -> 1.71Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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