AI Paper Atlas

Research map / Video / Action recognition

EPIC Fields: Marrying 3D Geometry and Video Understanding

Vadim Tschernezki, Ahmad Darkhalil, Zhifan Zhu, David Fouhey, Iro Laina, Diane Larlus, Dima Damen, Andrea Vedaldi

NeurIPS 2023 · Video › Action recognition · approach: Action anticipation and latent actions · 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
Use overlap-based homography filtering instead of uniform frame sampling (ablation)EPIC Fields camera reconstruction · 30-video reconstruction comparisonSuccessful reconstructions: 27/30 -> 30/30Improved
Use overlap-based homography filtering instead of uniform frame sampling (ablation)EPIC Fields camera reconstruction · 30-video reconstruction comparisonAvg. #3D Points: 23,142 -> 27,763Improved
Use overlap-based homography filtering instead of uniform frame sampling (ablation)EPIC Fields camera reconstruction · 30-video reconstruction comparisonAvg. Reprojection Error: 0.836 -> 0.798Improved
Use overlap-based homography filtering instead of uniform frame sampling (ablation)EPIC Fields camera reconstruction · 30-video reconstruction comparisonAvg. Registration Rate: 89.0% -> 98.6%Improved
Represent reference objects in 3D and reproject masks using camera poses rather than keeping pixels fixed in 2D (ablation)Fixed-mask VOS baseline · VISOR VOS StaticJ&F: 17.8 -> 48.4Improved
Represent reference objects in 3D and reproject masks using camera poses rather than keeping pixels fixed in 2D (ablation)Fixed-mask VOS baseline · VISOR VOS SS + DynJ&F: 12.0 -> 29.6Improved
Use 3D neural rendering rather than 2D motion groupingUnsupervised object segmentation · EPIC Fields UDOS SSmAP: 12.78 -> 25.55Improved
Use 2D optical-flow-based Motion Grouping rather than NeuralDiffUnsupervised object segmentation · EPIC Fields UDOS DynamicmAP: 55.58 -> 64.27Improved
Evaluate frames during actions with substantial object motion rather than easier out-of-action framesNeural rendering baselines · EPIC Fields D-NVSPSNR: 22.14 -> 19.88 -> 18.36Hurt

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