Tag
JPEG XS (ISO/IEC 21122) is an image and video codec offering visually and mathematically lossless quality with low latency and low computational complexity, targeting professional video over IP, broadcast, VR, drones, and autonomous vehicles.
Nibnib is an open-source image compression format and Rust tool tuned for extreme decompression speed, originally designed for DVI output on the RP2350 microcontroller, achieving 4bpp compression by decoding two 16bpp pixels from a single palette-lookup byte.
John Loomis 的年度回顾，总结 Decker（受 HyperCard 启发的创作环境）过去一年在 1.61 到 1.71 之间的进展，包括 gamepad 支持、Lil 语言改进、新的 IMG3 图像压缩编码以及用户社区作品亮点。
H-DDCM 以隐式随机 Hadamard 字典取代稠密高斯码本，并采用无表字典序编码，实现可扩展、低内存的训练自由生成式图像与视频压缩，在单 GPU 上接近实时处理长视频。
AFP-GIC, a controllable generative image compression framework published in IEEE Access (2026), uses an asymmetric Adaptive Fused Prior Transfer pipeline to reduce hallucinations and local distortion at ultra-low bitrates, achieving 18.1% lower decoder latency and 20.5% fewer parameters than DC-VIC, with released code, benchmark data, and an interactive Hugging Face demo.
A Show HN post highlighting KCC (Kindle Comic Converter), an open-source tool that maximizes manga/comic image quality on e-ink ereaders using techniques like 2D DFT to fix rainbow moiré effects, black-level correction, dithering, and device-native downscaling for fullscreen display without margins.
AFP-GIC is an IEEE Access 2026 paper proposing Adaptive Fused Prior Transfer for controllable generative image compression, achieving up to 167:1 compression with a single pretrained model across five bitrate operating points and reducing decoder latency by 18.1% versus DC-VIC.
The paper introduces ZK-JPEG, a zero-knowledge cryptographic tool for image compression and editing that verifies transformations while maintaining privacy, useful for combating deep fakes and ensuring image provenance.
The article critiques JPEG XL as a web image codec, comparing its compression efficiency to alternatives like AVIF and discussing its browser adoption challenges.
This paper introduces a novel semi-tensor product for tensors and develops a multi-term randomized tensor singular value decomposition (MSTP-SVD) to improve low-rank approximation accuracy and computational efficiency for visual data processing tasks.
The author tests AI image detectors on compressed files and discusses how to interpret detection scores in real-world scenarios, highlighting conflicts between scores and visual inspection.
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.