AI Paper Atlas

Research map / Video / Video segmentation and tracking

SDC-Net: Video prediction using spatially-displaced convolution

Fitsum A. Reda, Guilin Liu, Kevin J. Shih, Robert Kirby, Jon Barker, David Tarjan, Andrew Tao, Bryan Catanzaro

ECCV 2018 · Video › Video segmentation and tracking · approach: Learned optical flow estimation · 142 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 SDC (displaced kernel) instead of vector-based resampling (ablation)SDC-Net · Caltech Pedestrian testSSIM: 0.902 -> 0.918Improved
use SDC instead of vector-based resampling (ablation)SDC-Net · Caltech Pedestrian testL2 (1e-3): 2.47 -> 1.62Improved
use SDC instead of kernel-based resampling (ablation)SDC-Net · Caltech Pedestrian testL2 (1e-3): 2.19 -> 1.62Improved
use SDC instead of kernel-based resampling (ablation)SDC-Net · Caltech Pedestrian testSSIM: 0.896 -> 0.918Improved
use SDC instead of vector-based resampling (ablation)SDC-Net · YouTube-8M (26 HD videos)SSIM: 0.905 -> 0.911Improved
use SDC instead of vector-based resampling (ablation)SDC-Net · YouTube-8M (26 HD videos)L2: 0.00270 -> 0.00240Improved
use SDC instead of kernel-based resampling (ablation)SDC-Net · YouTube-8M (26 HD videos)SSIM: 0.904 -> 0.911Improved
use SDC instead of kernel-based resampling (ablation)SDC-Net · YouTube-8M (26 HD videos)PSNR: 37.33 -> 37.15Hurt
use SDC instead of vector-based resampling (ablation)SDC-Net · YouTube-8M (26 HD videos)PSNR: 37.24 -> 37.15Hurt
use vector-based instead of kernel-based resampling (ablation)SDC-Net variants · Caltech Pedestrian testSSIM: 0.896 -> 0.902Improved
fine-tune with perceptual and style loss after L1 (ablation)SDC-Net · qualitative framessharpnessImproved
train with L1 or L2 loss against estimated optical flow for motion vectors (ablation)SDC-Net · qualitativeaccuracyHurt

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