Tag
ELMZip is a novel satellite image compression framework using Extreme Learning Machines (ELM) and domain decomposition to enable efficient onboard neural representation, transmitting only compact output weights to reduce downlink payload while maintaining high reconstruction fidelity.
DeepSeek's OCR paper introduces 'optical compression,' showing that an image token can encode roughly 10 text tokens' worth of information with high accuracy, making images of text more token-efficient than raw text. Community tools and a new app, Imagizer, demonstrate this approach in practice.
A discussion on image compression techniques or tools, shared on lobste.rs.
Introduces SelfBootTok, a self-bootstrapped tokenization method that separates global and local information, reducing generator computation by ~40% and achieving a new state-of-the-art gFID of 1.56 with only 64 tokens.
FRAPPE is a novel autoencoding framework that uses a projection pursuit encoder to predict residuals from full input, enabling efficient variable-rate image compression with fast CPU-based encoding. At high compression ratios, FRAPPE-Image achieves higher perceptual quality than AVIF with 47x faster encoding, making real-time 1080p 30fps CPU-only encoding possible.
libwce is a minimal, patent-clean Rust library implementing a Bit-Plane Count (BPC) entropy layer for wavelet codecs, providing a stateless and dependency-free module for entropy coding.
MediaOptim is a tool that compresses images, video, and audio locally to save storage without uploading files.