{"ID":2854196,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.15775","arxiv_id":"2510.15775","title":"SANR: Scene-Aware Neural Representation for Light Field Image Compression with Rate-Distortion Optimization","abstract":"Light field images capture multi-view scene information and play a crucial role in 3D scene reconstruction. However, their high-dimensional nature results in enormous data volumes, posing a significant challenge for efficient compression in practical storage and transmission scenarios. Although neural representation-based methods have shown promise in light field image compression, most approaches rely on direct coordinate-to-pixel mapping through implicit neural representation (INR), often neglecting the explicit modeling of scene structure. Moreover, they typically lack end-to-end rate-distortion optimization, limiting their compression efficiency. To address these limitations, we propose SANR, a Scene-Aware Neural Representation framework for light field image compression with end-to-end rate-distortion optimization. For scene awareness, SANR introduces a hierarchical scene modeling block that leverages multi-scale latent codes to capture intrinsic scene structures, thereby reducing the information gap between INR input coordinates and the target light field image. From a compression perspective, SANR is the first to incorporate entropy-constrained quantization-aware training (QAT) into neural representation-based light field image compression, enabling end-to-end rate-distortion optimization. Extensive experiment results demonstrate that SANR significantly outperforms state-of-the-art techniques regarding rate-distortion performance with a 65.62\\% BD-rate saving against HEVC.","short_abstract":"Light field images capture multi-view scene information and play a crucial role in 3D scene reconstruction. However, their high-dimensional nature results in enormous data volumes, posing a significant challenge for efficient compression in practical storage and transmission scenarios. Although neural representation-ba...","url_abs":"https://arxiv.org/abs/2510.15775","url_pdf":"https://arxiv.org/pdf/2510.15775v1","authors":"[\"Gai Zhang\",\"Xinfeng Zhang\",\"Lv Tang\",\"Hongyu An\",\"Li Zhang\",\"Qingming Huang\"]","published":"2025-10-17T16:00:43Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.CV\",\"cs.MM\"]","methods":"[]","has_code":false}