https://github.com/xiangjieSui/Omnidirectional-Images-as-Moving-Camera-Videos
Perceptual Quality Assessment of Omnidirectional Images as Moving Camera Videos
Papers with Code 아카이브
Video Quality Assessment
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 10
- 보존된 평가 기록
- 185
Video Quality Assessment is a computer vision task aiming to mimic video-based human subjective perception. The goal is to produce a mos score, where higher score indicates better perceptual quality. Some well-known benchmarks for this task are KoNViD-1k, LIVE-VQC, YouTube-UGC and LSVQ. SROCC/PLCC/RMSE are usually used to evaluate the performance of different models.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/zhengyuzhao/koniq-pytorch
KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment
https://github.com/zibojia/rslad
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/zjfheart/Friendly-Adversarial-Training
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/zwx8981/tcsvt-2022-bvqa
Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception
https://github.com/zzz2010/starganv2_paddle
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.