LiDAR Depth Map Guided Image Compression Model
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913405899636736 |
|---|---|
| author | Gnutti, Alessandro Della Fiore, Stefano Savardi, Mattia Chen, Yi-Hsin Leonardi, Riccardo Peng, Wen-Hsiao |
| author_facet | Gnutti, Alessandro Della Fiore, Stefano Savardi, Mattia Chen, Yi-Hsin Leonardi, Riccardo Peng, Wen-Hsiao |
| contents | The incorporation of LiDAR technology into some high-end smartphones has unlocked numerous possibilities across various applications, including photography, image restoration, augmented reality, and more. In this paper, we introduce a novel direction that harnesses LiDAR depth maps to enhance the compression of the corresponding RGB camera images. To the best of our knowledge, this represents the initial exploration in this particular research direction. Specifically, we propose a Transformer-based learned image compression system capable of achieving variable-rate compression using a single model while utilizing the LiDAR depth map as supplementary information for both the encoding and decoding processes. Experimental results demonstrate that integrating LiDAR yields an average PSNR gain of 0.83 dB and an average bitrate reduction of 16% as compared to its absence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_06517 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LiDAR Depth Map Guided Image Compression Model Gnutti, Alessandro Della Fiore, Stefano Savardi, Mattia Chen, Yi-Hsin Leonardi, Riccardo Peng, Wen-Hsiao Image and Video Processing The incorporation of LiDAR technology into some high-end smartphones has unlocked numerous possibilities across various applications, including photography, image restoration, augmented reality, and more. In this paper, we introduce a novel direction that harnesses LiDAR depth maps to enhance the compression of the corresponding RGB camera images. To the best of our knowledge, this represents the initial exploration in this particular research direction. Specifically, we propose a Transformer-based learned image compression system capable of achieving variable-rate compression using a single model while utilizing the LiDAR depth map as supplementary information for both the encoding and decoding processes. Experimental results demonstrate that integrating LiDAR yields an average PSNR gain of 0.83 dB and an average bitrate reduction of 16% as compared to its absence. |
| title | LiDAR Depth Map Guided Image Compression Model |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2401.06517 |