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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use HITNet XL instead of EdgeStereo | Stereo matching on SceneFlow · SceneFlow finalpass | EPE: 0.74 -> 0.36 | Improved |
| Use HITNet XL instead of StereoNet | Stereo matching on SceneFlow · SceneFlow finalpass | Runtime: 0.015 -> 0.114 | Hurt |
| Use HITNet instead of R-Stereo | Stereo matching on ETH3D · ETH3D stereo | EPE: 0.18 -> 0.20 | Hurt |
| Use HITNet instead of R-Stereo | Stereo matching on ETH3D · ETH3D stereo | Runtime: 0.81 s -> 0.02 s | Improved |
| Use HITNet instead of LEAStereo | Stereo matching on KITTI 2012 · KITTI 2012 | 2-all: 2.39 -> 2.65 | Hurt |
| Use HITNet instead of LEAStereo | Stereo matching on KITTI 2012 · KITTI 2012 | EPE-all: 0.5 -> 0.5 | No clear effect |
| Use HITNet instead of LEAStereo | Stereo matching on KITTI 2015 · KITTI 2015 | D1-all: 1.65 -> 1.98 | Hurt |
| Use HITNet instead of LEAStereo | Stereo matching on KITTI 2015 · KITTI 2015 | Runtime: 0.3s -> 0.02s | Improved |
| Use HITNet instead of LEAStereo | Stereo matching on Middlebury V3 · Middlebury V3 | RMS: 8.11 -> 9.97 | Hurt |
| Use HITNet instead of LEAStereo | Stereo matching on Middlebury V3 · Middlebury V3 | AvgErr: 1.43 -> 1.71 | Hurt |
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.
- EdgeStereo — EdgeStereo: An Effective Multi-task Learning Network for Stereo Matching and Edge Detection (IJCV 2020) · better on 1 of 1 shared result
- StereoNet — StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction (ECCV 2018) · better on 0 of 1 shared result
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
- AANet: Adaptive Aggregation Network for Efficient Stereo Matching (CVPR 2020 · similarity 0.90)
- StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction (ECCV 2018 · similarity 0.89)
- Stereo Matching Using Multi-Level Cost Volume and Multi-Scale Feature Constancy (TPAMI 2019 · similarity 0.89)
- Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches (JMLR 2016 · similarity 0.89)
- IINet: Implicit Intra-inter Information Fusion for Real-Time Stereo Matching (AAAI 2024 · similarity 0.87)
- Any-Stereo: Arbitrary Scale Disparity Estimation for Iterative Stereo Matching (AAAI 2024 · similarity 0.87)
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.
