AI Paper Atlas

Research map / Video / Video segmentation and tracking

Motion-Aware Dynamic Architecture for Efficient Frame Interpolation

Myungsub Choi, Suyoung Lee, Heewon Kim, Kyoung Mu Lee

ICCV 2021 · Video › Video segmentation and tracking · approach: Video frame interpolation · 23 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 dynamic scale and depth framework (CAIN-SD) to CAINCAIN · Xiph-2KTFLOPs: 3.133 -> 1.598Improved
add the dynamic scale and depth framework (CAIN-SD) to CAINCAIN · Xiph-2KPSNR (dB): 35.21 -> 34.68Hurt
add the dynamic scale and depth framework (CAIN-SD) to CAINCAIN · Xiph-4KPSNR (dB): 32.56 -> 32.92Improved
add the dynamic scale and depth framework (CAIN-SD) to CAINCAIN · Xiph-2KGPU time (s): 0.225 -> 0.237Hurt
add the dynamic framework (CAIN-SD) to CAINCAIN · Xiph-2KCPU time (s): 10.64 -> 8.83Improved
add the depth finder to scale-only model (CAIN-S to CAIN-SD) (ablation)CAIN-S · REDS-120fps valTFLOPs: 1.507 -> 0.882Improved
use scale-only variant (CAIN-S) instead of CAIN (ablation)CAIN · REDS-120fps valTFLOPs: 1.305 -> 1.507Hurt
add scale selection to depth-only model (CAIN-D to CAIN-SD) (ablation)CAIN-D · REDS-120fps valTFLOPs: 1.008 -> 0.882Improved
lower depth weight lambda_d from 5e-9-ratio setting to 5e-10 with lambda_s fixed (ablation)CAIN-SD · Xiph-2KTFLOPs: 1.598 -> 3.804; PSNR 34.68 -> 35.33Hurt
increase lambda_s to 5e-8 (ablation)CAIN-SD · Xiph-2KPSNR (dB): 34.68 -> 31.10; TFLOPs 1.598 -> 1.827Hurt
decrease lambda_s to 5e-10 (ablation)CAIN-SD · Xiph-2KPSNR (dB): 34.68 -> 34.71; TFLOPs 1.598 -> 1.699Mixed
test with full-frame input instead of 256 patches (ablation)CAIN-SD · Xiph-2KPSNR (dB): 34.68 -> 33.24Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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