AI Paper Atlas

Research map / Video / Video segmentation and tracking

MoTIF: Learning Motion Trajectories with Local Implicit Neural Functions for Continuous Space-Time Video Super-Resolution

Yi-Hsin Chen, Si-Cun Chen, Yi-Hsin Chen, Yen-Yu Lin, Wen-Hsiao Peng

ICCV 2023 · Video › Video segmentation and tracking · approach: Space-time video super-resolution · 33 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 forward motion instead of backward motion in the space-time implicit function (ablation)MoTIF · GoPro-CenterPSNR: 29.98 -> 31.04Improved
use explicit motion from pretrained optical flow instead of implicit motion (ablation)MoTIF · GoPro-CenterPSNR: 30.58 -> 31.04Improved
add forward-warped features F_t for decoding (ablation)MoTIF · Vid4PSNR: 22.38 -> 25.26Improved
encode flow reliability maps into motion latents (ablation)MoTIF · Vid4PSNR: 25.26 -> 25.61Improved
add warped reliability map Z_t to decoder (ablation)MoTIF · Vid4PSNR: 25.61 -> 25.79Improved
replace tri-linear motion interpolation with ST-INF (ablation)MoTIF · Vid4PSNR: 25.57 -> 25.79Improved
use 4 reference frames instead of 2 (ablation)MoTIF · GoPro-AveragePSNR: 30.08 -> 30.77Improved
replace VideoINR with MoTIF for temporal x6 spatial x6C-STVSR · GoProPSNR: 25.56 -> 29.36Improved
train MoTIF versus TMNet on Vid4MoTIF · Vid4PSNR: 25.96 -> 25.79Hurt
forward-warp latents once instead of backward warping twiceMoTIF · Vid4 complexity, temporal x16 spatial x4FPS: 29.06 -> 42.50Improved

Later papers that compared with this method

5 later accepted papers report MoTIF as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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