Get Started
Home
Topics
Search
Library
Research questionHow can implicit-neural video codecs decouple bitrate scalability from decoding complexity in one embedded bitstream?Layered video codecs must adapt to varying network conditions and device capabilities. Existing scalable INR-based codecs often change the required decoding computation when bitrate changes, limiting independent control of quality and complexity.
AI
Computer Vision
Image & Video Processing
Research Paper
Technology
Latest papersRecent research connected to this question, newest first.Scalable Neural Video Representation CompressionThe source concerns scene-adaptive INR-based codecs that fit a compact neural network to each video. It reports UVG dataset comparisons with SHM 12.4 and multi-layer VTM-20.0, using one encoding process and a single embedded bitstream; implementation code is stated to be forthcoming.research paper · Sep 2, 2026
Related questions
How can neural video representation decoders reduce compute and memory use on resource-constrained devices without hurting reconstruction quality?How can ultra-low-bitrate video compression preserve perceptual quality and temporal consistency while decoding in real time?How can learned image codecs provide progressively refinable reconstructions from a single bitstream?How can implicit neural representations capture high-frequency detail without memorizing noise or requiring fragile tuning?