AI Paper Atlas

Research map / Video / Video segmentation and tracking

Spatio-temporal Transformer Network for Video Restoration

Tae Hyun Kim, Mehdi S. M. Sajjadi, Michael Hirsch, Bernhard Scholkopf

ECCV 2018 · Video › Video segmentation and tracking · approach: Real-world video super-resolution · 167 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 the reference frame as an extra sampling target in the spatio-temporal sampler (ablation)STTN · Video SR reconstruction (2 input frames)MSE: 17.34 -> 13.01Improved
add the reference frame as an extra sampling target (ablation)STTN · Video deblurring reconstruction (2 input frames)MSE: 8.7 -> 5.51Improved
add the reference frame as an extra sampling target (ablation)STTN · Video SR reconstruction (5 input frames)MSE: 14.39 -> 12.38Improved
increase the number of input frames from 2 to 5 (with reference frame) (ablation)STTN · Video SR reconstructionMSE: 13.01 -> 12.38Improved
increase the number of input frames from 2 to 5 (with reference frame) (ablation)STTN · Video deblurring reconstructionMSE: 5.51 -> 5.42Mixed
add STTN with one spatio-temporal transformer to VDSRVDSR · Video SR (own YouTube dataset, x4)PSNR (dB): 28.63 -> 28.94Improved
use two spatio-temporal transformers instead of oneSTTN+VDSR · Video SR (own YouTube dataset, x4)PSNR (dB): 28.94 -> 29.10Improved
replace two spatial transformers with one spatio-temporal transformerVDSR · Video SR (own YouTube dataset, x4)PSNR (dB): 28.85 -> 28.94Improved
integrate STTN into FRVSRFRVSR · Video SR (own YouTube dataset, x4)PSNR (dB): 29.78 -> 30.09Improved
integrate STTN into FRVSRFRVSR · Video SR (own YouTube dataset, x4)parameters: ~2.6M -> ~2.4MImproved
add STTN in front of DVD, replacing four optical flow computationsDVD · Video deblurring (DVD dataset)PSNR (dB): 31.02 -> 31.45Improved
add STTN in front of DVDDVD · Video deblurring (DVD dataset)speed (FPS): 0.04 -> 1.99Improved

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