FAJSCC is a new deepJSCC architecture for images that achieves better transmission performance with lower complexity than prior models and enables independent encoder-decoder compute adjustment.
Bjøntegaard delta (BD): A tutorial overview of the metric, evolution, challenges, and recommenda- tions
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Blackwell NVENC UHQ achieves up to 22.79% BD-Rate improvement over prior modes but raises end-to-end latency over 400% and board power by 40%, limiting it to VoD transcoding rather than interactive use.
4-way split-frame encoding on Blackwell GPUs achieves 122 fps for 8K 10-bit 4:2:2 HEVC, enabling real-time high-density V-PCC with up to 5% BD-Rate penalty.
citing papers explorer
-
Feature Importance-Aware Deep Joint Source-Channel Coding for Computationally Efficient and Adjustable Image Transmission
FAJSCC is a new deepJSCC architecture for images that achieves better transmission performance with lower complexity than prior models and enables independent encoder-decoder compute adjustment.