AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

The Right Spin: Learning Object Motion from Rotation-Compensated Flow Fields

Pia Bideau, Erik G. Miller, Cordelia Schmid, Karteek Alahari

IJCV 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Unsupervised object and part discovery · 6 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 rotation compensation to ground-truth flow input (ablation)motion segmentation network · FT3D testIoU: 90.68 -> 93.23Improved
add rotation compensation to estimated PWC flow input (ablation)motion segmentation network · FT3D testIoU: 77.18 -> 78.69Improved
add flow magnitude to angle input (GT t-flow) (ablation)motion segmentation network · FT3D testIoU: 77.47 -> 93.23Improved
add flow magnitude to angle input (PWC t-flow) (ablation)motion segmentation network · FT3D testIoU: 77.79 -> 78.69Improved
test GT-trained network on estimated PWC t-flow instead of GT t-flow (ablation)motion segmentation network · FT3D testIoU: 93.23 -> 24.44Hurt
use likelihood maximization instead of TMM for rotation estimation (GT flow) (ablation)camera rotation estimator · Sintelyaw/pitch/roll error (deg): 0.08 / 0.22 / 0.02 -> 0.03 / 0.06 / 0.01Improved
use likelihood maximization instead of TMM for rotation estimation (PWC flow) (ablation)camera rotation estimator · Sintelyaw/pitch/roll error (deg): 0.13 / 0.34 / 0.04 -> 0.05 / 0.11 / 0.03Improved
add 3D Gaussian filtering and dense CRF post-processing (ablation)Ours · MoCA locomotionJ mean: 58.3 -> 65.8Improved
add appearance cues to flow-only modelOurs · DAVIS2016J mean: 59.7 -> 73.5Improved
mask moving objects with GT segments for camera motion estimation (ablation)Ours · DAVIS2016 (flow only)J mean: 59.7 -> 62.5Improved
add rotation compensation and geometry vs flow-only LMP networkOurs vs LMP · DAVIS2016 (flow only)J mean: 58.4 -> 59.7Improved

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