On Self-Adaptive Perception Loss Function for Sequential Lossy Compression
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915153849614336 |
|---|---|
| author | Salehkalaibar, Sadaf Phan, Buu Cai, Likun Dick, Joao Atz Yu, Wei Chen, Jun Khisti, Ashish |
| author_facet | Salehkalaibar, Sadaf Phan, Buu Cai, Likun Dick, Joao Atz Yu, Wei Chen, Jun Khisti, Ashish |
| contents | We consider causal, low-latency, sequential lossy compression, with mean squared-error (MSE) as the distortion loss, and a perception loss function (PLF) to enhance the realism of reconstructions. As the main contribution, we propose and analyze a new PLF that considers the joint distribution between the current source frame and the previous reconstructions. We establish the theoretical rate-distortion-perception function for first-order Markov sources and analyze the Gaussian model in detail. From a qualitative perspective, the proposed metric can simultaneously avoid the error-permanence phenomenon and also better exploit the temporal correlation between high-quality reconstructions. The proposed metric is referred to as self-adaptive perception loss function (PLF-SA), as its behavior adapts to the quality of reconstructed frames. We provide a detailed comparison of the proposed perception loss function with previous approaches through both information theoretic analysis as well as experiments involving moving MNIST and UVG datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_10628 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | On Self-Adaptive Perception Loss Function for Sequential Lossy Compression Salehkalaibar, Sadaf Phan, Buu Cai, Likun Dick, Joao Atz Yu, Wei Chen, Jun Khisti, Ashish Machine Learning Information Theory We consider causal, low-latency, sequential lossy compression, with mean squared-error (MSE) as the distortion loss, and a perception loss function (PLF) to enhance the realism of reconstructions. As the main contribution, we propose and analyze a new PLF that considers the joint distribution between the current source frame and the previous reconstructions. We establish the theoretical rate-distortion-perception function for first-order Markov sources and analyze the Gaussian model in detail. From a qualitative perspective, the proposed metric can simultaneously avoid the error-permanence phenomenon and also better exploit the temporal correlation between high-quality reconstructions. The proposed metric is referred to as self-adaptive perception loss function (PLF-SA), as its behavior adapts to the quality of reconstructed frames. We provide a detailed comparison of the proposed perception loss function with previous approaches through both information theoretic analysis as well as experiments involving moving MNIST and UVG datasets. |
| title | On Self-Adaptive Perception Loss Function for Sequential Lossy Compression |
| topic | Machine Learning Information Theory |
| url | https://arxiv.org/abs/2502.10628 |