RealHDRTVNet: Enhancing SDRTV-to-HDRTV Conversion Using Real HDRTV Priors for Improved Accuracy and Generalization
Directly embedding real HDRTV priors into the SDRTV-to-HDRTV conversion process significantly improves accuracy and generalization compared to traditional feature mapping methods by constraining the solution space and enabling the network to learn from a diverse set of real-world HDRTV characteristics.
실제 SDRTV에서 HDRTV로의 변환을 위한 이중 역 저하 네트워크
실제 SDRTV 콘텐츠를 HDRTV로 변환할 때 발생하는 코딩 아티팩트 문제를 해결하기 위해 이중 역 저하 복원 네트워크(DIDNet)를 제안하며, 이는 아티팩트 증폭을 억제하면서 역 톤 매핑을 효과적으로 처리하여 결과적인 HDRTV의 시각적 품질을 향상시킵니다.
現実世界のSDRTVからHDRTVへの変換のためのデュアル逆劣化ネットワーク
現実世界のSDRTV映像をHDRTVに変換する際、符号化アーティファクトの増幅が課題となる。本稿では、デュアル逆劣化タスク（ビデオ修復と逆トーンマッピング）として捉えた新しい手法DIDNetを提案し、アーティファクト抑制と高品質なHDRTV生成を両立させる。
Dual Inverse Degradation Network for Real-World SDRTV-to-HDRTV Conversion: Addressing Artifact Amplification in Low-Quality SDRTV
This paper proposes a novel dual inverse degradation network (DIDNet) to address the challenge of converting real-world, often low-quality, SDRTV content to high-quality HDRTV while mitigating the amplification of coding artifacts inherent in compressed SDRTV.
Efficient SDRTV-to-HDRTV Conversion by Learning from Image Formation
This paper proposes an efficient and effective method, called HDRTVNet++, for converting SDRTV content to the HDRTV standard by modeling the image formation process and utilizing a divide-and-conquer approach.
© 2024 by Linnk AI