AI Paper Atlas

Research map / Video / Video segmentation and tracking

Deep Kalman Filtering Network for Video Compression Artifact Reduction

Guo Lu, Wanli Ouyang, Dong Xu, Xiaoyun Zhang, Zhiyong Gao, Ming-Ting Sun

ECCV 2018 · Video › Video segmentation and tracking · approach: Learned video compression · 101 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 quantized prediction residual as input to the measurement network (ablation)Measurement network · Vimeo-90K JPEG2000 q=20PSNR (dB): 37.15 -> 37.49Improved
add recursive filtering using previous restored frame to the temporal mapping network (ablation)Temporal mapping network · Vimeo-90K JPEG2000 q=20PSNR (dB): 37.35 -> 37.76Improved
combine measurement and temporal networks through Kalman update (ablation)DKFN · Vimeo-90K JPEG2000 q=20PSNR (dB): 37.76 -> 37.93Improved
combine measurement and temporal networks through Kalman update vs measurement only (ablation)DKFN · Vimeo-90K JPEG2000 q=20PSNR (dB): 37.49 -> 37.93Improved
replace convolutional GRU recurrence with Kalman filter (ablation)DKFN · Vimeo-90K JPEG2000 q=20PSNR (dB): 37.10 -> 37.93Improved
add prediction residual to measurement network (ablation)Measurement network · Vimeo-90K JPEG2000 q=20SSIM: 0.967 -> 0.968Improved
add recursive filtering to temporal network (ablation)Temporal mapping network · Vimeo-90K JPEG2000 q=20SSIM: 0.967 -> 0.970Improved
use DKFN instead of TolowDKFN · Vimeo-90K JPEG2000 q=20PSNR (dB): 36.92 -> 37.93Improved
use DKFN instead of DnCNNDKFN · Vimeo-90K JPEG2000 q=20PSNR (dB): 37.26 -> 37.93Improved
use DKFN instead of DnCNNDKFN · Vimeo-90K HEVC qp=37PSNR (dB): 33.01 -> 33.23Improved
use DKFN instead of HEVC loop filterDKFN · Vimeo-90K HEVC qp=37PSNR (dB): 31.98 -> 33.23Improved
use DKFN instead of Tolow on unseen dataDKFN · MPI Sintel (cross-dataset)PSNR (dB): 34.78 -> 37.01Improved

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