Related papers: Implicit Concept Removal of Diffusion Models
Geometric Deep Learning has recently made striking progress with the advent of continuous deep implicit fields. They allow for detailed modeling of watertight surfaces of arbitrary topology while not relying on a 3D Euclidean grid,…
Recent diffusion-based text-to-image customization methods have achieved significant success in understanding concrete concepts to control generation processes, such as styles and shapes. However, few efforts dive into the realistic yet…
Recent advances in text-to-image generative models have raised concerns about their potential to produce harmful content when provided with malicious input text prompts. To address this issue, two main approaches have emerged: (1)…
With the rise of large, publicly-available text-to-image diffusion models, text-guided real image editing has garnered much research attention recently. Existing methods tend to either rely on some form of per-instance or per-task…
Text-to-image diffusion models have demonstrated remarkable capabilities in generating high-quality images, yet their tendency to reproduce undesirable concepts, such as NSFW content, copyrighted styles, or specific objects, poses growing…
Diffusion models have achieved unprecedented success in image generation but pose increasing risks in terms of privacy, fairness, and security. A growing demand exists to \emph{erase} sensitive or harmful concepts (e.g., NSFW content,…
Motivated by ethical and legal concerns, the scientific community is actively developing methods to limit the misuse of Text-to-Image diffusion models for reproducing copyrighted, violent, explicit, or personal information in the generated…
Image inpainting aims to fill in the missing pixels with visually coherent and semantically plausible content. Despite the great progress brought from deep generative models, this task still suffers from i. the difficulties in large-scale…
Large-scale image generation models, with impressive quality made possible by the vast amount of data available on the Internet, raise social concerns that these models may generate harmful or copyrighted content. The biases and harmfulness…
With the rapid rise of generative AI and synthetic media, distinguishing AI-generated images from real ones has become crucial in safeguarding against misinformation and ensuring digital authenticity. Traditional watermarking techniques…
Concept erasure is the task of erasing information about a concept (e.g., gender or race) from a representation set while retaining the maximum possible utility -- information from original representations. Concept erasure is useful in…
Large-scale text-to-image diffusion models have been a ground-breaking development in generating convincing images following an input text prompt. The goal of image editing research is to give users control over the generated images by…
Lifelong few-shot customization for text-to-image diffusion aims to continually generalize existing models for new tasks with minimal data while preserving old knowledge. Current customization diffusion models excel in few-shot tasks but…
Recent success of text-to-image (T2I) generation and its increasing practical applications, enabled by diffusion models, require urgent consideration of erasing unwanted concepts, e.g., copyrighted, offensive, and unsafe ones, from the…
General object composition (GOC) aims to seamlessly integrate a target object into a background scene with desired geometric properties, while simultaneously preserving its fine-grained appearance details. Recent approaches derive semantic…
Diffusion models have transformed image generation, yet controlling their outputs to reliably erase undesired concepts remains challenging. Existing approaches usually require task-specific training and struggle to generalize across both…
Text-to-image (T2I) models today are capable of producing photorealistic, instruction-following images, yet they still frequently fail on prompts that require implicit world knowledge. Existing evaluation protocols either emphasize…
Image generation has recently seen tremendous advances, with diffusion models allowing to synthesize convincing images for a large variety of text prompts. In this article, we propose DiffEdit, a method to take advantage of text-conditioned…
Text-to-image diffusion models have demonstrated remarkable capabilities in generating artistic content by learning from billions of images, including popular artworks. However, the fundamental question of how these models internally…
Our understanding of the visual world is centered around various concept axes, characterizing different aspects of visual entities. While different concept axes can be easily specified by language, e.g. color, the exact visual nuances along…