Get Started
Home
Topics
Search
Library
Research questionHow can learned image codecs provide progressively refinable reconstructions from a single bitstream?Many learned image codecs require separate compressed representations for different target bitrates. A progressive codec should let each received prefix decode a valid coarse image and refine it when more bits are appended.
AI
Computer Vision
Image & Video Processing
Machine Learning
Research Paper
Technology
Latest papersRecent research connected to this question, newest first.Tree-Structured Vector Quantization For Efficient And Progressive Image CompressionThe evidence concerns Tree-VQ, a tree-structured vector-quantization framework with prefix-compatible entropy coding and rate-aware refinement scheduling. Reported experiments address perceptual compression efficiency, parameter count, and latency.research paper · Sep 3, 2026
Related questions
How can ultra-low-bitrate video compression preserve perceptual quality and temporal consistency while decoding in real time?How can implicit-neural video codecs decouple bitrate scalability from decoding complexity in one embedded bitstream?How can neural video representation decoders reduce compute and memory use on resource-constrained devices without hurting reconstruction quality?How can hyperspectral image compression preserve spatial and spectral fidelity under tight storage budgets?