Kopte A, Kaup A (2026)
Publication Language: English
Publication Type: Conference contribution, Conference Contribution
Publication year: 2026
Conference Proceedings Title: Proceedings of the IEEE International Conference on Image Processing (ICIP)
Event location: Tampere
Open Access Link: https://arxiv.org/abs/2605.20977
Most neural video codecs rely on temporal conditioning, which makes them susceptible to error propagation over long sequences. While Transformer-based architectures like the Video Compression Transformer (VCT) offer a drift-free alternative, they suffer from high computational complexity and inferior Rate-Distortion (RD) performance. The recent Sliding Window Attention (SWA) addresses these shortcomings by reducing complexity and enhancing RD performance, yet it restricts decoding to a strictly sequential raster-scan order, creating a critical bottleneck in decoding latency. To resolve this, we propose Parallel Sliding Window Attention in Neural Video Coding (P-SWA), utilizing diagonal wavefronts to enable parallel decoding. By embedding a hyperprior and introducing an accumulator to fuse side information and local spatial context, our method increases decoding speed by 36 % over the parallel VCT. Simultaneously, it achieves Bjøntegaard Delta-rate savings of up to 10.0 % for I-frames and 7.1 % for P-frames over the SWA baseline.
APA:
Kopte, A., & Kaup, A. (2026). Parallel Context Modeling for Sliding Window Attention in Neural Video Coding. In IEEE (Eds.), Proceedings of the IEEE International Conference on Image Processing (ICIP). Tampere.
MLA:
Kopte, Alexander, and André Kaup. "Parallel Context Modeling for Sliding Window Attention in Neural Video Coding." Proceedings of the IEEE International Conference on Image Processing (ICIP), Tampere Ed. IEEE, 2026.
BibTeX: Download