b-frame coding 1conditional transforms 1entropy coding 1learned image compression 1low-delay video 1mixture of experts 1model capacity scaling 1neural video compression 1state space models 1variable bit-rate 1
From the 2 of 2 linked papers with an AI index.
2 papers
cs.CV2026
MixCompress: Mixture of Experts for Variable Rate Learned Image Compression
Calvin-Khang Ta, Praneet Singh, Tong Shao +1
The paper introduces MixCompress, a learned image compression system that uses a sparsely gated mixture-of-experts and a mixture-of-depths mechanism to adaptively adjust model capa…
cs.CV2026
DCVC-MB: Neural B-Frame Video Compression using State Space Models
Arjun Arora, Calvin-Khang Ta, Carlos Restrepo-Galeano +7
The paper introduces DCVC-MB, a neural video codec for low-delay B‑frame compression that uses state‑space models for bidirectional prediction and an entropy‑aware skipping mechani…