Learning-Based JND-Directed HDR Video Preprocessing for Perceptually Lossless Compression With HEVC
The final consumer of videos is mostly human. Therefore, if videos can be compressed by fully utilizing the perception characteristics of human visual systems (HVS), the bitrates of the compressed videos can be significantly reduced with subjective visual quality degradation as little as possible. B...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9301307/ |
| _version_ | 1818349777014751232 |
|---|---|
| author | Sehwan Ki Jeonghyeok Do Munchurl Kim |
| author_facet | Sehwan Ki Jeonghyeok Do Munchurl Kim |
| author_sort | Sehwan Ki |
| collection | DOAJ |
| description | The final consumer of videos is mostly human. Therefore, if videos can be compressed by fully utilizing the perception characteristics of human visual systems (HVS), the bitrates of the compressed videos can be significantly reduced with subjective visual quality degradation as little as possible. Based on this, we newly propose a learning-based Just Noticeable Distortion (JND)-directed preprocessing scheme for perceptual video compression, especially for 10-bit High Dynamic Range (HDR) videos, which is called the HDR-JNDNet. Our HDR-JNDNet effectively suppresses the perceptual redundancy of 10-bit HDR video signals so that the compression efficiency can be significantly enhanced for the HEVC main10 profile encoder. To our best knowledge, our work is the first approach to training a CNN-based model to directly generate the JND-directed suppressed frames of 10-bit HDR video with the negligible perceptual quality difference between the decoded frames for the original HDR video input with and without the preprocessing by our HDR-JNDNet. Via intensive experiments, when the HDR-JNDNet is applied as preprocessing for the HDR video input before compression, it allows to remarkably save the required bitrates up to the maximum (average) 40.66% (18.37%) for 4K-UHD/HDR test videos, with little subjective video quality degradation without increasing the computational complexity. |
| first_indexed | 2024-12-13T18:11:20Z |
| format | Article |
| id | doaj.art-147ba642c8814654ad405a1b81c1e3d1 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-13T18:11:20Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-147ba642c8814654ad405a1b81c1e3d12022-12-21T23:35:57ZengIEEEIEEE Access2169-35362020-01-01822860522861810.1109/ACCESS.2020.30461949301307Learning-Based JND-Directed HDR Video Preprocessing for Perceptually Lossless Compression With HEVCSehwan Ki0https://orcid.org/0000-0002-3809-7886Jeonghyeok Do1https://orcid.org/0000-0003-0030-0129Munchurl Kim2https://orcid.org/0000-0003-0146-5419Korea Advanced Institute of Science and Technology, Daejeon, South KoreaKorea Advanced Institute of Science and Technology, Daejeon, South KoreaKorea Advanced Institute of Science and Technology, Daejeon, South KoreaThe final consumer of videos is mostly human. Therefore, if videos can be compressed by fully utilizing the perception characteristics of human visual systems (HVS), the bitrates of the compressed videos can be significantly reduced with subjective visual quality degradation as little as possible. Based on this, we newly propose a learning-based Just Noticeable Distortion (JND)-directed preprocessing scheme for perceptual video compression, especially for 10-bit High Dynamic Range (HDR) videos, which is called the HDR-JNDNet. Our HDR-JNDNet effectively suppresses the perceptual redundancy of 10-bit HDR video signals so that the compression efficiency can be significantly enhanced for the HEVC main10 profile encoder. To our best knowledge, our work is the first approach to training a CNN-based model to directly generate the JND-directed suppressed frames of 10-bit HDR video with the negligible perceptual quality difference between the decoded frames for the original HDR video input with and without the preprocessing by our HDR-JNDNet. Via intensive experiments, when the HDR-JNDNet is applied as preprocessing for the HDR video input before compression, it allows to remarkably save the required bitrates up to the maximum (average) 40.66% (18.37%) for 4K-UHD/HDR test videos, with little subjective video quality degradation without increasing the computational complexity.https://ieeexplore.ieee.org/document/9301307/High dynamic range (HDR) videovideo compressionjust noticeable distortion (JND)perceptual video coding (PVC) |
| spellingShingle | Sehwan Ki Jeonghyeok Do Munchurl Kim Learning-Based JND-Directed HDR Video Preprocessing for Perceptually Lossless Compression With HEVC IEEE Access High dynamic range (HDR) video video compression just noticeable distortion (JND) perceptual video coding (PVC) |
| title | Learning-Based JND-Directed HDR Video Preprocessing for Perceptually Lossless Compression With HEVC |
| title_full | Learning-Based JND-Directed HDR Video Preprocessing for Perceptually Lossless Compression With HEVC |
| title_fullStr | Learning-Based JND-Directed HDR Video Preprocessing for Perceptually Lossless Compression With HEVC |
| title_full_unstemmed | Learning-Based JND-Directed HDR Video Preprocessing for Perceptually Lossless Compression With HEVC |
| title_short | Learning-Based JND-Directed HDR Video Preprocessing for Perceptually Lossless Compression With HEVC |
| title_sort | learning based jnd directed hdr video preprocessing for perceptually lossless compression with hevc |
| topic | High dynamic range (HDR) video video compression just noticeable distortion (JND) perceptual video coding (PVC) |
| url | https://ieeexplore.ieee.org/document/9301307/ |
| work_keys_str_mv | AT sehwanki learningbasedjnddirectedhdrvideopreprocessingforperceptuallylosslesscompressionwithhevc AT jeonghyeokdo learningbasedjnddirectedhdrvideopreprocessingforperceptuallylosslesscompressionwithhevc AT munchurlkim learningbasedjnddirectedhdrvideopreprocessingforperceptuallylosslesscompressionwithhevc |