AI Paper Atlas

Research map / Point clouds / Point cloud classification

Multiview Stereo with Cascaded Epipolar RAFT

Zeyu Ma, Zachary Teed, Jia Deng

ECCV 2022 · Point clouds › Point cloud classification · approach: Point cloud detection and tracking · 47 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 multiresolution depth fusion (t=0.02) instead of native input only (ablation)CER-MVS · Tanks-and-Temples validationMean F1 (%): 64.38 -> 68.49Improved
add multiresolution depth fusion (t=0.02) instead of 2x native input only (ablation)CER-MVS · Tanks-and-Temples validationMean F1 (%): 68.08 -> 68.49Improved
use threshold fusion instead of simple weighted average (w=0.5) (ablation)CER-MVS · Tanks-and-Temples validationMean F1 (%): 66.55 -> 68.49Improved
use mean instead of max aggregation of neighbor cost volumes (ablation)CER-MVS · Tanks-and-Temples validationMean F1 (%): 57.77 -> 67.36Improved
use mean instead of std aggregation of neighbor cost volumes (ablation)CER-MVS · Tanks-and-Temples validationMean F1 (%): 59.90 -> 67.36Improved
use mean instead of std + mean aggregation (ablation)CER-MVS · Tanks-and-Temples validationMean F1 (%): 66.85 -> 67.36Improved
use adaptive thresholding (p=25%) instead of fixed threshold k=2 (ablation)CER-MVS · Tanks-and-Temples validationMean F1 (%): 66.33 -> 67.36Improved
use proposed dynamic loss instead of L1 disparity loss (ablation)CER-MVS · Tanks-and-Temples validationF1-score: 66.79 -> 67.36Improved
use proposed dynamic loss instead of direct average of the two losses (ablation)CER-MVS · Tanks-and-Temples validationF1-score: 67.32 -> 67.36No clear effect
use truncated L1 depth loss alone (ablation)CER-MVS · Tanks-and-Temples validationF1-scoreHurt
increase neighbor views at native resolution from 5 to 15 (25 views at 2x) (ablation)CER-MVS · Tanks-and-Temples validationMean F1 (%): 62.73 -> 67.36Improved
increase 2x-resolution neighbor views from 5 to 25 (15 views at native) (ablation)CER-MVS · Tanks-and-Temples validationMean F1 (%): 62.73 -> 67.36Improved

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