AI Paper Atlas

Research map / 3D vision / Depth and stereo

Upgrading Optical Flow to 3D Scene Flow Through Optical Expansion

Gengshan Yang, Deva Ramanan

CVPR 2020 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 84 citations (OpenAlex)

Check 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
use optical expansion with optical flow and camera intrinsics to estimate normalized 3D motionmonocular scene flow · KITTI-15 validationMiD: 623 -> 75Improved
use optical expansion with optical flow and camera intrinsics to estimate normalized 3D motionmonocular scene flow · KITTI-15 benchmark foregroundSF: 39.57 -> 36.67Improved
use optical expansion to estimate depth change from monocular imagesstereo scene flow · KITTI-15 benchmark foregroundSF: 15.94 -> 13.44Improved
use monocular optical flow and expansion with LiDAR depthLiDAR scene flow · KITTI-15 LiDAR validationEPE (m): 0.116 -> 0.119Mixed
use optical expansion-derived motion-in-depth for collision predictiontime-to-collision estimation · KITTIErr-1s: 5.91 -> 4.21Improved
add scale-aware expansion supervision to census loss (ablation)self-supervised optical flow · KITTI-15 validationFl EPE: 7.000 -> 6.564Improved
add residual prediction to the optical expansion network (ablation)optical expansion estimation · KITTIlog-L1: 255 -> 245Improved
add residual prediction to the optical expansion network (ablation)optical expansion estimation · Sintellog-L1: 83 -> 78Improved
use initial expansion from a local affine transform instead of optical flow as the network input (ablation)optical expansion estimation · KITTIlog-L1: 383 -> 245Improved
use initial expansion from a local affine transform instead of optical flow as the network input (ablation)optical expansion estimation · Sintellog-L1: 116 -> 78Improved
use initial local affine expansion rather than warped image features as the network input (ablation)optical expansion estimation · KITTIlog-L1: 450 -> 245Improved
use initial local affine expansion rather than warped image features as the network input (ablation)optical expansion estimation · Sintellog-L1: 174 -> 78Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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