AI Paper Atlas

Research map / Video / Video segmentation and tracking

Data Overfitting for On-Device Super-Resolution with Dynamic Algorithm and Compiler Co-Design

Gen Li, zhihao shu, Jie Ji, Minghai Qin, Fatemeh Afghah, Wei Niu, Xiaolong Ma

ECCV 2024 · Video › Video segmentation and tracking · approach: Space-time video super-resolution · 1 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 dynamic multi-path network with uneven patch splitting (one model) instead of STDO multi-modelDy-DCA · UVG and VSD4K videosPSNR: 47.50 -> 47.64Improved
reduce transmitted models to one with uneven patchesDy-DCA vs STDO · mobile deploymentmodel switching and I/O overhead: 4x saving on model switching, 7x saving on I/OImproved
add compiler data-flow analysis with fusion and static execution planningDy-DCA on MNN · mobile CPU/GPU latency and memoryspeedup and memory: 1.7x speedup and 1.61x memory reductionImproved
increase number of paths from 2 to 4 (ablation)Dy-DCA (WDSR) · PSNR vs latencyPSNR and latency: PSNR 45.86 -> 46.51; max latency 32 -> 42 msMixed
Dy-DCA instead of single-model SRVCWDSR x2 · game-45sPSNR: 31.03 -> 45.86Improved
apply to longer videos (2-min game, combined 90s) (ablation)Dy-DCA (WDSR x4) · VSD4K long videoPSNR: game-2min 44.72; combine-90s 47.34No 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