paper-with-me

홈 › Papers

Learned Scalable Video Coding For Humans and Machines

2023-07-18 · Hadi Hadizadeh, Ivan V. Bajić

Video coding has traditionally been developed to support services such as video streaming, videoconferencing, digital TV, and so on. The main intent was to enable human viewing of the encoded content. However, with the advances in deep neural networks (DNNs), encoded video is increasingly being used for automatic video analytics performed by machines. In applications such as automatic traffic monitoring, analytics such as vehicle detection, tracking and counting, would run continuously, while human viewing could be required occasionally to review potential incidents. To support such applications, a new paradigm for video coding is needed that will facilitate efficient representation and compression of video for both machine and human use in a scalable manner. In this manuscript, we introduce an end-to-end learnable video codec that supports a machine vision task in its base layer, while its enhancement layer, together with the base layer, supports input reconstruction for human viewing. The proposed system is constructed based on the concept of conditional coding to achieve better compression gains. Comprehensive experimental evaluations conducted on four standard video datasets demonstrate that our framework outperforms both state-of-the-art learned and conventional video codecs in its base layer, while maintaining comparable performance on the human vision task in its enhancement layer. Implementation of the proposed system is available at https://github.com/hadipardis/svc

📄 PDF Abstract BibTeX arXiv:2307.08978

Code (1)

hadipardis/svc 공식 구현 pytorch

Tasks

Object Detectionvehicle detectionVideo Compression

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Scalable Video Coding for Humans and Machines

2022-08-04 · Hyomin Choi, Ivan V. Bajić

Video content is watched not only by humans, but increasingly also by machines. For example, machine learning models analyze surveillance video for security and traffic monitoring, search through YouTube videos for inapp…

MS-SSIMObjectobject-detectionObject Detection+1

VVC+M: Plug and Play Scalable Image Coding for Humans and Machines

2023-05-17 · Alon Harell, Yalda Foroutan, Ivan V. Bajic

Compression for machines is an emerging field, where inputs are encoded while optimizing the performance of downstream automated analysis. In scalable coding for humans and machines, the compressed representation used fo…

Image Compression

Scalable Image Coding for Humans and Machines Using Feature Fusion Network

2024-05-15 · Takahiro Shindo, Taiju Watanabe, Yui Tatsumi, Hiroshi Watanabe

As image recognition models become more prevalent, scalable coding methods for machines and humans gain more importance. Applications of image recognition models include traffic monitoring and farm management. In these u…

Image Compression

Learned Disentangled Latent Representations for Scalable Image Coding for Humans and Machines

2023-01-10 · Ezgi Ozyilkan, Mateen Ulhaq, Hyomin Choi, Fabien Racape

As an increasing amount of image and video content will be analyzed by machines, there is demand for a new codec paradigm that is capable of compressing visual input primarily for the purpose of computer vision inference…

object-detectionObject Detection

Refining Coded Image in Human Vision Layer Using CNN-Based Post-Processing

2024-05-20 · Takahiro Shindo, Yui Tatsumi, Taiju Watanabe, Hiroshi Watanabe

Scalable image coding for both humans and machines is a technique that has gained a lot of attention recently. This technology enables the hierarchical decoding of images for human vision and image recognition models. It…

Image Compression