AI Paper Atlas

Research map / 3D vision / Depth and stereo

Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry

Nan Yang, Rui Wang, Jorg Stuckler, Daniel Cremers

ECCV 2018 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 356 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 the virtual stereo term to windowed bundle adjustment (ablation)DVSO (in) · KITTI odometry overall meant_rel: 10.76 -> 1.08Improved
add left-right disparity consistency check for point selection (ablation)DVSO (in,vs) · KITTI odometry overall meant_rel: 1.08 -> 1.06No clear effect
add tuned virtual stereo baseline (ablation)DVSO (in,vs,lr) · KITTI odometry overall meant_rel: 1.06 -> 0.77Improved
use StackNet depth instead of Godard et al. depth (ablation)DVSO · KITTI odometry overall meant_rel: 1.51 -> 0.77Improved
add StackNet (cascaded ResidualNet) to SimpleNet (ablation)depth network · KITTI Eigen 0-80mRMSE: 4.785 -> 4.442Improved
add ResidualNet stackingdepth network · KITTI Eigen 1-50mRMSE vs Kuznietsov: 3.518 -> 3.390Improved
train SimpleNet on Ko then Kr (self-supervised) (ablation)SimpleNet · KITTI Eigen 0-80mRMSE: 4.886 -> 4.817Improved
train SimpleNet on Kr then Ko only (ablation)SimpleNet · KITTI Eigen 0-80mRMSE: 4.886 -> 4.890No clear effect
add final fine-tuning on Ko after Ko->Kr (ablation)SimpleNet · KITTI Eigen 0-80mRMSE: 4.817 -> 4.785Improved
use semi-supervised sparse Stereo DSO depth plus self-supervision vs self-supervised Godarddepth network · KITTI Eigen 0-80mRMSE: 4.935 -> 4.442Improved
use monocular DVSO instead of monocular DSO with Sim(3) alignmentodometry · KITTI odometry overall meant_rel: 65.64 -> 0.77Improved
use DVSO instead of Stereo DSOodometry · KITTI odometry overall meant_rel: 0.84 -> 0.77Improved

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