SSIM (square): 0.971LPIPS (square): 0.028PNSR (object): 35.61SSIM (object): 0.961
Papers with Code · CC BY-SA 4.0
Video Inpainting
The goal of Video Inpainting is to fill in missing regions of a given video sequence with contents that are both spatially and temporally coherent. Video Inpainting, also known as video completion, has many real-world applications such as undesired object removal and video restoration.
<span class="description-source">Source: Deep Flow-Guided Video Inpainting </span>
개요는 각 항목의 일부입니다. 위 탭에서 전체 기록을 페이지별로 탐색할 수 있습니다.
벤치마크
Papers with Code 아카이브의 데이터셋별 기록 예시입니다. 평가 조건과 지표 방향이 검증되지 않아 순위를 의미하지 않습니다.
Dataset기록된 모델 예시MetricPaperCode
데이터셋
7개논문
PSNR: 30.28SSIM: 0.9521VFID: 0.182Ewarp: 0.1533
PSNR: 28.81SSIM: 0.9404VFID: 0.187Ewarp: 0.1608
PSNR: 28.96SSIM: 0.9411VFID: 0.199Ewarp: 0.1785
PSNR: 33.82SSIM: 0.976VFID: 0.104Ewarp: -
PSNR: 30.80SSIM: 0.9497VFID: 0.165Ewarp: 0.1586
PSNR: 32.54SSIM: 0.9700VFID: 0.138Ewarp: 0.1362
PSNR: 28.57SSIM: 0.9409VFID: 0.170Ewarp: 0.1640
PSNR: 30.67SSIM: 0.9560VFID: 0.149Ewarp: 0.1449
PSNR: 34.43SSIM: 0.9735VFID: 0.042Ewarp: -
PSNR: 33.01SSIM: 0.9721VFID: 0.116Ewarp: 0.1315
라이브러리
Papers with Code 리더보드 row에 연결된 구현 저장소입니다.