AI Paper Atlas

Research map / Video / Video segmentation and tracking

Non-Local ConvLSTM for Video Compression Artifact Reduction

Yi Xu, Longwen Gao, Kai Tian, Shuigeng Zhou, Huyang Sun

ICCV 2019 · Video › Video segmentation and tracking · approach: Learned video compression · 84 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 7 frames with ConvLSTM instead of a single frame (ablation)encoder-decoder · Yang et al. QP=37dPSNR: 0.395 -> 0.456Improved
replace plain ConvLSTM with non-local ConvLSTM (ablation)ConvLSTM with 7 frames · Yang et al. QP=37dPSNR: 0.456 -> 0.601Improved
use non-local module instead of motion estimation and compensation (ablation)ME-ConvLSTM · Yang et al. QP=37dPSNR: 0.503 -> 0.601Improved
use non-local module instead of motion estimation and compensation (ablation)ME-ConvLSTM · Yang et al. QP=37dSSIM: 0.827 -> 0.897Improved
fine-tune on longer 20-frame sequences (ablation)NL-ConvLSTM · Yang et al. QP=37dPSNR: 0.601 -> 0.604Improved
two-stage approximation of non-local similarity vs original non-local (ablation)NL-ConvLSTM · run-time at 180x180ms per frame: 4391.75 -> 102.13Improved
use multiple preceding and following frames with non-local ConvLSTM instead of two PQFs (MFQE)NL-ConvLSTM · Yang et al. QP=37dPSNR: 0.510 -> 0.601Improved
use NL-ConvLSTM instead of MFQENL-ConvLSTM · Yang et al. QP=42dPSNR: 0.461 -> 0.614Improved
NL-ConvLSTM instead of 3D CNNNL-ConvLSTM · Vimeo-90K QP=37PSNR: 33.25 -> 33.39Improved
NL-ConvLSTM instead of MFQE on quality fluctuationNL-ConvLSTM · Yang et al. sequencesPSNR STD: 1.055 -> 1.036Improved
NL-ConvLSTM instead of MFQE on peak-valley differenceNL-ConvLSTM · Yang et al. sequencesPSNR PVD: 1.109 -> 1.038Improved
use NL-ConvLSTM, which uses more frames, instead of single-frame or pair methodsNL-ConvLSTM · run-time 1920x1080ms per frame: 1009.00 -> 6738.00Hurt

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