AI Paper Atlas

Research map / Video / Video segmentation and tracking

MotionDeltaCNN: Sparse CNN Inference of Frame Differences in Moving Camera Videos with Spherical Buffers and Padded Convolutions

Mathias Parger, Chengcheng Tang, Thomas Neff, Christopher D. Twigg, Cem Keskin, Robert Wang, Markus Steinberger

ICCV 2023 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 5 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 dynamic initialization of newly unveiled tiles (ablation)MotionDeltaCNN · DAVIS 2017 moving-camera, 1080 Ti b=5FPS: 56.4 -> 75.1 FPSImproved
add dynamic initialization of newly unveiled tiles (ablation)MotionDeltaCNN · DAVIS 2017 moving-cameraIoU: 79.63 -> 79.43Mixed
add padded convolutions (ablation)MotionDeltaCNN · DAVIS 2017 moving-cameraIoU: 77.89 -> 79.43Improved
add ROI-focused sensing (ablation)MotionDeltaCNN · DAVIS 2017 moving-cameraFPS: 63.6 -> 75.1 FPSImproved
add noise suppression and ROI scaling (ablation)MotionDeltaCNN · DAVIS 2017 moving-cameraFPS: 50.9 -> 75.1 FPSImproved
add moving-camera support (spherical buffers, padded convs) to DeltaCNNDeltaCNN sparse · DAVIS 2017 moving-camera videos, 1080 Ti b=5FPS: 44.1 -> 75.1 FPSImproved
use MotionDeltaCNN instead of DeltaCNN on static camera Human3.6MHRNet pose estimation · Human3.6M, 1080 Ti b=16FPS: 202 -> 228 FPSImproved
run MotionDeltaCNN on RTX 3090 with small batch sizeMotionDeltaCNN · DAVIS 2017, RTX 3090 b=1speedup over cuDNN: 1.44 (MotionDeltaCNN) vs 1.54 (DeltaCNN)Mixed
enable moving-camera support in dense modeDeltaCNN (dense) · DAVIS 2017 all videos, 1080 Ti b=5speedup over cuDNN: 1.01 -> 0.99No clear effect

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