AI Paper Atlas

Research map / 3D vision / Depth and stereo

Motion-prior Contrast Maximization for Dense Continuous-Time Motion Estimation

Friedhelm Hamann, Ziyun Wang, Ioannis Asmanis, Kenneth Chaney, Guillermo Gallego, Kostas Daniilidis

ECCV 2024 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 27 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
fine-tune a synthetically pretrained BFlow with the self-supervised contrast loss with motion priorBFlow · EVIMO2TEPE: 8.62916088104248 -> 6.14132022857666Improved
self-supervised fine-tuning vs supervised in-domain trainingBFlow · EVIMO2TEPE: 6.14132022857666 vs 3.38006925582885Hurt
use K=32 nearest neighbor trajectories instead of 1 (ablation)Ours (U-Net) · DSECEPE: 4.576 -> 3.2Improved
use K=32 instead of 8 neighbor trajectories (ablation)Ours (U-Net) · DSECEPE: 3.512 -> 3.2Improved
use randomized reference time instead of three fixed reference times (ablation)Ours (U-Net) · DSECEPE: 4.46 -> 3.2 (single reference time 7.264)Improved
use non-linear (higher-degree or learned) motion prior on DSEC (ablation)Ours (U-Net) · DSECEPE: 3.2 vs 3.22 (learned) and 3.28 (polynomial)No clear effect
use Bezier curves (N_c=10) instead of polynomial or learned basis (ablation)Ours (BFlow) · EVIMO2TEPE: 6.77561473846435 / 7.45736408233642 -> 6.14132022857666Improved
use non-linear Bezier prior instead of linear polynomial (N_c=1) on EVIMO2 (ablation)Ours (BFlow) · EVIMO2TEPE: 7.97 -> 6.14Improved
use self-supervised contrast loss on night sequence zurich_city_14 with flickering lightsOurs (U-Net) · DSEC zurich_city_14_cEPE: 1.78 vs E-RAFT 0.713Hurt
replace recurrent or RAFT-style networks with a single-pass U-Net trained with the lossOurs (U-Net) · DSECinference time (ms): 40.1 / 46.331 -> 7.273Improved
Ours vs test-time optimization method on MVSECOurs (U-Net) · MVSECEPE: 0.45 vs Shiba 0.42 (indoor_flying1); 0.71 vs 0.60 (indoor_flying2)Mixed

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