Cheng-Kang Ted Chao

Cheng-Kang Ted Chao, Yotam Gingold

Image and shape editing are ubiquitous among digital artworks. Graphics algorithms facilitate artists and designers to achieve desired editing intents without going through manually tedious retouching. In the recent advance of machine learning, artists' editing intents can even be driven by text, using a variety of well-trained neural networks. They have seen to be receiving an extensive success on such as generating photorealistic images, artworks and human poses, stylizing meshes from text, or auto-completion given image and shape priors. In this short survey, we provide an overview over 50 papers on state-of-the-art (text-guided) image-and-shape generation techniques. We start with an overview on recent editing algorithms in the introduction. Then, we provide a comprehensive review on text-guided editing techniques for 2D and 3D independently, where each of its sub-section begins with a brief background introduction. We also contextualize editing algorithms under recent implicit neural representations. Finally, we conclude the survey with the discussion over existing methods and potential research ideas.

Cheng-Kang Ted Chao, Yotam Gingold

Professional color editing requires precise control over both color (hue and saturation) and lightness, ideally through separate, independent controls. We present a real-time interactive color editing framework for 3D Gaussian Splatting (3DGS) that enables palette-based recoloring, per-palette tone curves for color-aware lightness adjustment, and accurate pixel-level constraints -- capabilities unavailable in prior palette-based 3DGS methods. Existing approaches decompose colors at the primitive level, optimizing per-Gaussian palette weights before splatting. However, sparse primitive-level weights do not guarantee sparse pixel-level decompositions after alpha-blending, causing palette edits to affect unintended regions and degrading editing quality. We address this through view-space palette decomposition, splatting weights instead of colors to optimize the observable appearance of the scene. We introduce a geometric loss using inverse barycentric coordinates to enforce consistent sparsity patterns, ensuring similar colors share similar decompositions. Our approach achieves superior editing quality compared to primitive-space methods, enabling professional color grading workflows for 3DGS scenes with real-time interaction.