GIFnets: Differentiable GIF Encoding Framework
Innfarn Yoo, Xiyang Luo, Yilin Wang, Feng Yang, Peyman Milanfar
Abstract
Graphics Interchange Format (GIF) is a widely used image file format. Due to the limited number of palette colors, GIF encoding often introduces color banding artifacts. Traditionally, dithering is applied to reduce color banding, but introducing dotted-pattern artifacts. To reduce artifacts and provide a better and more efficient GIF encoding, we introduce a differentiable GIF encoding pipeline, which includes three novel neural networks: PaletteNet, DitherNet, and BandingNet. Each of these three networks provides an important functionality within the GIF encoding pipeline. PaletteNet predicts a near-optimal color palette given an input image. DitherNet manipulates the input image to reduce color banding artifacts and provides an alternative to traditional dithering. Finally, BandingNet is designed to detect color banding, and provides a new perceptual loss specifically for GIF images. As far as we know, this is the first fully differentiable GIF encoding pipeline based on deep neural networks and compatible with existing GIF decoders. User study shows that our algorithm is better than Floyd-Steinberg based GIF encoding.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Related papers
- Palette: Image-to-Image Diffusion ModelsChitwan Saharia, William Chan, Huiwen Chang, Chris A. Lee et al.SIGGRAPH 2022 · 1,638 citations
- NIF: A Fast Implicit Image Compression with Bottleneck Layers and Modulated Sinusoidal ActivationsLorenzo Catania, Dario AllegraACM MM 2023 · 10 citations
- Conditional Diffusion Process for Inverse HalftoningHao Jiang, Yadong MuNeurIPS 2022 · 11 citations
- End-to-End Differentiable Learning to HDR Image Synthesis for Multi-exposure ImagesJung Hee Kim, Siyeong Lee, Suk-Ju KangAAAI 2021 · 39 citations
- JPGNet: Joint Predictive Filtering and Generative Network for Image InpaintingQing Guo, Xiaoguang Li, Felix Juefei-Xu, Hongkai Yu et al.ACM MM 2021 · 34 citations
