AI Paper Atlas

Research map / 3D vision / Depth and stereo

Discriminately Treating Motion Components Evolves Joint Depth and Ego-Motion Learning

Mengtan Zhang, Zizhan Guo, Hongbo Zhao, Yi Feng, Zuyi Xiong, Yue Wang, Shaoyi Du, Hanli Wang, Rui Fan

TPAMI 2026 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 4 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
train with DiMoDE discriminative motion-component treatment instead of previous SoTAprevious SoTA learning-based VO · KITTI Odometry Seq. 00ATE: 75.05% reductionImproved
train with DiMoDE instead of previous SoTAprevious SoTA learning-based VO · KITTI Odometry Seq. 02ATE: 65.30% reductionImproved
train with DiMoDE instead of previous SoTAprevious SoTA learning-based VO · KITTI Odometry Seq. 05ATE: 52.11% reductionImproved
train with DiMoDE instead of previous SoTAprevious SoTA learning-based VO · KITTI Odometry Seq. 08ATE: 54.56% reductionImproved
use DiMoDE instead of SCIPaD (finetuned)SCIPaD · KITTI Odometry Seqs. 11-20ATE: 35.78 -> 26.64Improved
use DiMoDE instead of Lite-Mono baseline depth trainingLite-Mono · KITTI depth (640x192)Abs Rel: 0.101 -> 0.097Improved
DiMoDE versus geometry-based ORB-SLAM3DiMoDE · KITTI Odometry Seqs. 11-20ATE: 13.46 -> 26.64Hurt

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