AI Paper Atlas

Research map / 3D vision / Depth and stereo

Continuous 3D Label Stereo Matching Using Local Expansion Moves

Tatsunori Taniai, Yasuyuki Matsushita, Yoichi Sato, Takeshi Naemura

TPAMI 2017 · 3D vision › Depth and stereo · approach: Learned stereo with specialized sensors · 158 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 RANSAC plane proposer (ablation)LE-GF · Vintage (V3), nonoccbad pixel error rate (%): 13.7 -> 5.65Improved
add RANSAC plane proposer (ablation)LE-GF · Teddy (V2), nonoccbad pixel error rate (%): 4.26 -> 3.98Mixed
add RANSAC proposer on Middlebury V3 training data (ablation)LE-GF · Middlebury V3 trainingbad 2.0 nonocc error: by one pointImproved
add regularization term (ablation)LE-GF · Vintage (V3), nonoccbad pixel error rate (%): 22.8 -> 5.65Improved
add regularization term (ablation)LE-GF · Teddy (V2), nonoccbad pixel error rate (%): 5.47 -> 3.98Improved
use local expansion moves instead of fusion-based optimization (Olsson et al.)Olsson et al. + 3DPM · Teddy (V2), nonoccbad pixel error rate (%): 5.21 -> 3.98Improved
use local expansion moves instead of fusion-based optimization (Olsson et al.)Olsson et al. + 3DPM · Adirondack (V3), nonoccbad pixel error rate (%): 2.74 -> 1.19Improved
use guided-filter cost aggregation (LE-GF) instead of bilateral filtering (LE-BF)LE-BF · Rocks1speedup: about 5.3xImproved
parallelize disjoint local alpha-expansions on four CPU cores instead of oneLE-BF and LE-GF · Rocks1speedup: about 3.5xImproved
compute unary costs on GPULE-BF · Rocks1speedup: about 19xImproved
add GPU+CPUx4 over GPU+CPUx1LE-BF · Rocks1speedup: about 1.7xImproved
use multiple grid-cell sizes (S, M, L) instead of a single size (ablation)LE-GF · Reindeerenergy and error convergenceImproved

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