Tag
A CLI and browser-based tool that converts PDFs into image-only PDFs with simulated scan effects like skew, grayscale, noise, and JPEG artifacts, using Go and WebAssembly.
The author describes accidentally creating wigglegrams (stereoscopic GIFs) by taking multiple similar photos, and wrote a script using perceptual hashing to automatically detect and stitch them together from their iCloud photo library.
Deconvolution is a Rust crate for image deconvolution and restoration, providing known-PSF and blind restoration methods, PSF/OTF conversion, preprocessing, and simulation utilities.
An in-depth guide explaining gamma correction, why it matters for image processing and rendering, and common pitfalls for coders.
Apple announces RAW 9 for Core Image, a significant update that uses a tiled CoreML model combining demosaic and denoise on the Apple Neural Engine for dramatically improved RAW image quality across Apple platforms.
A detailed technical guide explaining Exif metadata structure, how it is stored in JPEG and other image formats, and practical considerations for developers working with image pixel data.
The article compares two methods for normalizing RGB values (dividing by 255 vs 256) and explains the consequences for floating-point conversion and rounding, including uneven bin widths at the extremes.
FaceFusion is an open-source face fusion/Deepfake platform with 28.5k stars, supporting local high-precision face swapping, lip-syncing, as well as image, video, and batch processing, providing a complete job management system.
Bun.Image is a zero-dependency chainable image pipeline for decoding, resizing, rotating, and re-encoding JPEG, PNG, WebP, HEIC, and AVIF, running off-thread and inspired by Sharp.
A CLI and library that removes visible and invisible AI watermarks from images generated by various AI models, including metadata stripping and diffusion-based regeneration.
The author open-sourced a background removal tool built with open source tech, now also usable as a headless MCP service for AI agents.
Arthur Pastel optimized the fast_blur function in the Rust image-rs crate, achieving up to 5.9x speedup on u8 images by using box blur approximations for faster Gaussian-like blurs.
imgproxy v4 is a fast and secure self-hosted image processing server, now available with updates.
Maxime Rivest argues that compound AI systems for images are undervalued and suggests leveraging optimization frameworks like DSPy and GEPA to automate pipeline creation involving SAM and classifiers.
The article demonstrates how to apply dithering effects to images using CSS filters and SVG feTurbulence to maintain a consistent aesthetic.
A single-pass method combines online k-means palette refinement with ordered Bayer dithering, eliminating the separate pixel-mapping step and yielding slight speedups while producing visually interesting results.
A 1998 paper that introduces a simple bit-replication technique for boosting pixel bit-depth in digital images.
First per-image PCA decomposition of the 24-image Kodak PCD0992 suite reveals deliberate curation spanning two orders of magnitude in inter-channel redundancy.
OpenAI releases o3 and o4-mini models that can reason with images in their chain-of-thought process, enabling visual understanding through native image manipulation tools like cropping and zooming without separate specialized models. These models achieve state-of-the-art performance on multimodal benchmarks including STEM questions, chart reading, and visual search tasks.
851-labs/background-remover is an open-source AI model for removing backgrounds from images, available on Replicate with low cost and fast inference on Nvidia T4 GPUs.