TCNeRV improves video compression with temporal context modeling
tcnerv:dual-domain temporal context modeling for implicit neural video compression
Computer Vision and Pattern Recognition
Summary
Video compression is about shrinking video files while keeping good picture quality. The authors found that many methods treat video frames independently, missing how frames relate over time. They created a new approach called TCNeRV that uses information from previous frames to better predict the next ones, improving video quality especially at smaller file sizes. Their method works well even with fewer parameters compared to some existing systems.
What this means in practice
- •For video streaming services: Improve video quality at lower bit rates by integrating temporal context modeling in compression systems.$Commercial implications: Enables streaming platforms to deliver higher-quality video with less bandwidth, reducing costs and improving user experience.
- •For mobile app developers: Develop apps that encode and decode videos efficiently on resource-limited devices by using TCNeRV’s compact temporal context models.
Authors
Xuezhi Xiang, Yixin Zhao, Heqi Xiang, Jiayao Liu, Shanjun Zhang
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.