AI Paper Atlas

Research map / 3D vision / Depth and stereo

Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding

Chenxu Luo, Zhenheng Yang, Peng Wang, Yang Wang, Wei Xu, Ram Nevatia, Alan Yuille

TPAMI 2019 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 316 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 depth consistency fine-tuning (ablation)EPC++ mono · KITTI Eigen depthAbs Rel: 0.151 -> 0.146Improved
add depth consistency fine-tuning (Sq Rel) (ablation)EPC++ mono · KITTI Eigen depthSq Rel: 1.448 -> 1.065Improved
add flow consistency without visibility mask (ablation)EPC++ mono · KITTI Eigen depthAbs Rel: 0.151 -> 0.148No clear effect
add visibility mask to flow consistency (ablation)EPC++ mono · KITTI Eigen depthAbs Rel: 0.148 -> 0.144Improved
joint training of depth and flow networks (ablation)EPC++ mono · KITTI Eigen depthAbs Rel: 0.146 -> 0.156Hurt
two iterations of adaptive depth-flow consistency training (ablation)EPC++ mono · KITTI Eigen depthAbs Rel: 0.144 -> 0.141Improved
add stereo training samplesEPC++ · KITTI Eigen depthAbs Rel: 0.141 -> 0.127Improved
add depth consistency in stereo setting (ablation)EPC++ stereo · KITTI Eigen depthAbs Rel: 0.141 -> 0.134Improved
add depth-flow consistency, masks and adaptive training (ablation)EPC++ mono · MPI-Sintel depthAbs Rel: 0.866 -> 0.524Improved
joint fine-tune flow with depth rather than flow only (ablation)OptFlowNet · KITTI 2015 training flowEPE noc: 3.66 -> 4.00Hurt
finetune flow on all regions with depth-derived flow (ablation)OptFlowNet · KITTI 2015 training flowEPE occ: 23.07 -> 16.20Improved
finetune only on non-visible regions rather than visible-rigid regions (ablation)OptFlowNet · KITTI 2015 training flowEPE all: 7.17 -> 5.84Improved

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