AI Paper Atlas

Research map / 3D vision / Depth and stereo

Fast Light-Field Disparity Estimation With Multi-Disparity-Scale Cost Aggregation

Zhicong Huang, Xuemei Hu, Zhou Xue, Weizhu Xu, Tao Yue

ICCV 2021 · 3D vision › Depth and stereo · approach: Photometric stereo · 58 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 edge guidance sub-network (ablation)FastLFnet · 4D Light Field (HCI)MSE x100: 1.844 -> 1.218Improved
add BAM attention module (ablation)FastLFnet · 4D Light Field (HCI)MSE x100: 1.492 -> 1.218Improved
use multi-disparity-scale cost aggregation instead of one scale (ablation)FastLFnet · 4D Light Field (HCI)MSE x100: 1.650 -> 1.218Improved
add edge guidance sub-network (cropped evaluation) (ablation)FastLFnet · 4D Light Field (Training+Stratified, 11px crop), averageMSE x100: 1.928 -> 1.291Improved
add vertical stream to horizontal-only input (16 channels) (ablation)FastLFnet · 4D Light Field (HCI)MSE x100: 2.068 -> 1.218Improved
add diagonal streams to 2-streams input (16 channels) (ablation)FastLFnet · 4D Light Field (HCI)MSE x100: 1.218 -> 1.437Hurt
raise feature channels from 16 to 32 (2-streams) (ablation)FastLFnet · 4D Light Field (HCI)MSE x100: 1.218 -> 1.653Hurt
raise feature channels from 4 to 16 (2-streams) (ablation)FastLFnet · 4D Light Field (HCI)MSE x100: 1.756 -> 1.218Improved
raise feature channels from 16 to 32 on running time (2-streams) (ablation)FastLFnet · 4D Light Field (HCI)running time (s): 0.593 -> 1.438Hurt
use FastLFnet instead of LFattNet on efficiencyFastLFnet vs LFattNet · 4D Light Field (Training+Stratified, 11px crop)running time (s): 5.862 -> 0.624Improved
FastLFnet versus LFattNet on accuracyFastLFnet vs LFattNet · 4D Light Field (Training+Stratified, 11px crop), averageMSE x100: 0.955 -> 1.291Hurt
FastLFnet versus DslfNet on sparse light fieldsFastLFnet vs DslfNet · Sparse Light Field dataset (4 test scenes), averageMSE: 0.32 -> 0.12Improved

Earlier methods this paper compares with

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