Problem
Research questions and friction points this paper is trying to address.
video compression
implicit neural representations
temporal context
reconstruction distortion
bit rate
tcnerv:dual-domain temporal context modeling for implicit neural video compression
🤖 AI Summary
本文提出TCNeRV，通过在特征和嵌入域中利用重建上下文来改善视频压缩，使用多尺度时序上下文融合模块和时序嵌入残差编码方法，以有限的模型容量实现更优的率失真性能。
📝 Abstract
Video compression aims to minimize reconstruction distor tion under a constrained bit rate. Existing video implicit neural representations (INRs) often decode frames independently, leaving intermediate features unconditioned on previous reconstructions and content embeddings without explicit temporal prediction. We propose TCNeRV, which exploits reconstructed context in both feature and embedding domains. Its multi-scale temporal-context fusion (MTCF) module injects gated historical features at multiple decoder scales, while temporal embedding-residual coding (TERC) predicts each content embedding and codes only its residual. With approximately 3M parameters, TCNeRV achieves an average PSNR of 36.08 dB on the UVG dataset, outperforming HNeRV-Boost by 2.20 dB. It reduces BD-rate by 22.06%, 66.73%, and 29.85% relative to HM, DCVC, and HiNeRV, respectively, demonstrating competitive rate-distortion performance with limited model capacity.
Innovation
Methods, ideas, or system contributions that make the work stand out.
multi-scale temporal-context fusion
temporal embedding-residual coding
implicit neural representations
🔎 Similar Papers
No similar papers found.
