AI Paper Atlas

Research map / 3D vision / Depth and stereo

EDNet: Efficient Disparity Estimation With Cost Volume Combination and Attention-Based Spatial Residual

Songyan Zhang, Zhicheng Wang, Qiang Wang, Jinshuo Zhang, Gang Wei, Xiaowen Chu

CVPR 2021 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 20 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
combine correlation and squeezed concatenation volumes (ablation)EDNet · Scene FlowEPE: 1.07 -> 1.00Improved
add the squeezed concatenation volume to correlation-only matching (ablation)EDNet · Scene FlowEPE: 1.67 -> 1.63Improved
add the correlation volume to squeezed-concatenation-only matching (ablation)EDNet · Scene FlowEPE: 1.89 -> 1.63Improved
add residual learning (ablation)EDNet with combined volume · Scene FlowEPE: 1.63 -> 1.04Improved
use attention-based rather than normal residual learning (ablation)EDNet · Scene FlowEPE: 1.04 -> 1.00Improved
provide error maps at multiple corresponding scales (ablation)EDNet residual module · Scene FlowEPEImproved
use EDNet rather than AANet+Scene Flow · Scene FlowEPE: 0.72 -> 0.63Improved
use EDNet rather than GANetKITTI 2015 · KITTI 2015inference time (s): 0.36 -> 0.05Improved
use EDNet rather than GANetKITTI runtime comparison · KITTI runtime comparisonmemory (GB): 6.53 -> 2.52Improved
use EDNet rather than GANetKITTI runtime comparison · KITTI runtime comparisonGFLOPs: 1936.98 -> 162.92Improved
use EDNet rather than AANetKITTI 2012 · KITTI 2012Out All (%): 3.60 -> 3.67Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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