Video Compression
102 papers with code • 0 benchmarks • 4 datasets
Video Compression is a process of reducing the size of an image or video file by exploiting spatial and temporal redundancies within an image or video frame and across multiple video frames. The ultimate goal of a successful Video Compression system is to reduce data volume while retaining the perceptual quality of the decompressed data.
Source: Adversarial Video Compression Guided by Soft Edge Detection
Benchmarks
These leaderboards are used to track progress in Video Compression
Libraries
Use these libraries to find Video Compression models and implementations
BVI-DVC
YT-UGC
Deep Fakes Dataset
Most implemented papers
MGANet: A Robust Model for Quality Enhancement of Compressed Video
mengab/MGANet
•
•
In video compression, most of the existing deep learning approaches concentrate on the visual quality of a single frame, while ignoring the useful priors as well as the temporal information of adjacent frames.
Enhancing Quality for VVC Compressed Videos by Jointly Exploiting Spatial Details and Temporal Structure
mengab/SDTS
•
•
In this paper, we propose a quality enhancement network of versatile video coding (VVC) compressed videos by jointly exploiting spatial details and temporal structure (SDTS).
Remote Heart Rate Measurement from Highly Compressed Facial Videos: an End-to-end Deep Learning Solution with Video Enhancement
ZitongYu/STVEN_rPPGNet
•
•
ICCV 2019
The method includes two parts: 1) a Spatio-Temporal Video Enhancement Network (STVEN) for video enhancement, and 2) an rPPG network (rPPGNet) for rPPG signal recovery.
Convolutional Tensor-Train LSTM for Spatio-temporal Learning
NVlabs/conv-tt-lstm
•
•
NeurIPS 2020
Learning from spatio-temporal data has numerous applications such as human-behavior analysis, object tracking, video compression, and physics simulation. However, existing methods still perform poorly on challenging video tasks such as long-term forecasting.
Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Model
The experiments show that our approach achieves the state-of-the-art learned video compression performance in terms of both PSNR and MS-SSIM.
End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video Compression
KUIS-AI-Tekalp-Research-Group/video-compression
•
•
Conventional video compression (VC) methods are based on motion compensated transform coding, and the steps of motion estimation, mode and quantization parameter selection, and entropy coding are optimized individually due to the combinatorial nature of the end-to-end optimization problem.
Flexible-Rate Learned Hierarchical Bi-Directional Video Compression With Motion Refinement and Frame-Level Bit Allocation
KUIS-AI-Tekalp-Research-Group/video-compression
•
•
This paper presents improvements and novel additions to our recent work on end-to-end optimized hierarchical bi-directional video compression to further advance the state-of-the-art in learned video compression.
Neural Video Compression with Diverse Contexts
Better yet, our codec has surpassed the under-developing next generation traditional codec/ECM in both RGB and YUV420 colorspaces, in terms of PSNR.
DeepCache: Principled Cache for Mobile Deep Vision
We present DeepCache, a principled cache design for deep learning inference in continuous mobile vision.
Compressed Video Action Recognition
chaoyuaw/pytorch-coviar
•
•
CVPR 2018
), we propose to train a deep network directly on the compressed video.
