Preprint
Sep 2026
tcnerv:dual-domain temporal context modeling for implicit neural video compression
TCNeRV is proposed, which exploits reconstructed context in both feature and embedding domains and 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.
Xue-Lian Xiang, Yi-Xin Zhao, He-Qi Xiang et al.
· 0 citations