S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908279244849152 |
|---|---|
| author | Chen, Yunuo Li, Qian He, Bing Feng, Donghui Wu, Ronghua Wang, Qi Song, Li Lu, Guo Zhang, Wenjun |
| author_facet | Chen, Yunuo Li, Qian He, Bing Feng, Donghui Wu, Ronghua Wang, Qi Song, Li Lu, Guo Zhang, Wenjun |
| contents | Transformer-based Learned Image Compression (LIC) suffers from a suboptimal trade-off between decoding latency and rate-distortion (R-D) performance. Moreover, the critical role of the FeedForward Network (FFN)-based channel aggregation module has been largely overlooked. Our research reveals that efficient channel aggregation-rather than complex and time-consuming spatial operations-is the key to achieving competitive LIC models. Based on this insight, we initiate the ``S2CFormer'' paradigm, a general architecture that simplifies spatial operations and enhances channel operations to overcome the previous trade-off. We present two instances of the S2CFormer: S2C-Conv, and S2C-Attention. Both models demonstrate state-of-the-art (SOTA) R-D performance and significantly faster decoding speed. Furthermore, we introduce S2C-Hybrid, an enhanced variant that maximizes the strengths of different S2CFormer instances to achieve a better performance-latency trade-off. This model outperforms all the existing methods on the Kodak, Tecnick, and CLIC Professional Validation datasets, setting a new benchmark for efficient and high-performance LIC. The code is at \href{https://github.com/YunuoChen/S2CFormer}{https://github.com/YunuoChen/S2CFormer}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_00700 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression Chen, Yunuo Li, Qian He, Bing Feng, Donghui Wu, Ronghua Wang, Qi Song, Li Lu, Guo Zhang, Wenjun Computer Vision and Pattern Recognition Image and Video Processing Transformer-based Learned Image Compression (LIC) suffers from a suboptimal trade-off between decoding latency and rate-distortion (R-D) performance. Moreover, the critical role of the FeedForward Network (FFN)-based channel aggregation module has been largely overlooked. Our research reveals that efficient channel aggregation-rather than complex and time-consuming spatial operations-is the key to achieving competitive LIC models. Based on this insight, we initiate the ``S2CFormer'' paradigm, a general architecture that simplifies spatial operations and enhances channel operations to overcome the previous trade-off. We present two instances of the S2CFormer: S2C-Conv, and S2C-Attention. Both models demonstrate state-of-the-art (SOTA) R-D performance and significantly faster decoding speed. Furthermore, we introduce S2C-Hybrid, an enhanced variant that maximizes the strengths of different S2CFormer instances to achieve a better performance-latency trade-off. This model outperforms all the existing methods on the Kodak, Tecnick, and CLIC Professional Validation datasets, setting a new benchmark for efficient and high-performance LIC. The code is at \href{https://github.com/YunuoChen/S2CFormer}{https://github.com/YunuoChen/S2CFormer}. |
| title | S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2502.00700 |