相关论文: RelationAdapter: Learning and Transferring Visual …

Comparing images captured by disparate sensors is a common challenge in remote sensing. This requires image translation -- converting imagery from one sensor domain to another while preserving the original content. Denoising Diffusion…

Image editing aims to edit the given synthetic or real image to meet the specific requirements from users. It is widely studied in recent years as a promising and challenging field of Artificial Intelligence Generative Content (AIGC).…

State-of-the-art text-to-image diffusion models can produce impressive visuals but may memorize and reproduce training images, creating copyright and privacy risks. Existing prompt perturbations applied at inference time, such as random…

Diffusion transformers (DiTs) achieve high generative quality but lock FLOPs to image resolution, limiting principled latency-quality trade-offs, and allocate computation uniformly across input spatial tokens, wasting resource allocation to…

Recent progress has shown great potential of visual prompt tuning (VPT) when adapting pre-trained vision transformers to various downstream tasks. However, most existing solutions independently optimize prompts at each layer, thereby…

This work focuses on generating high-quality images with specific style of reference images and content of provided textual descriptions. Current leading algorithms, i.e., DreamBooth and LoRA, require fine-tuning for each style, leading to…

The text-to-image synthesis by diffusion models has recently shown remarkable performance in generating high-quality images. Although performs well for simple texts, the models may get confused when faced with complex texts that contain…

Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image. One of the key challenges behind this task is leveraging the referring…

Recent advancements in text-to-image generation have been propelled by the development of diffusion models and multi-modality learning. However, since text is typically represented sequentially in these models, it often falls short in…

In image processing, one of the most challenging tasks is to render an image's semantic meaning using a variety of artistic approaches. Existing techniques for arbitrary style transfer (AST) frequently experience mode-collapse,…

Generating realistic human motion sequences from text descriptions is a challenging task that requires capturing the rich expressiveness of both natural language and human motion.Recent advances in diffusion models have enabled significant…

Textual-based prompt learning methods primarily employ multiple learnable soft prompts and hard class tokens in a cascading manner as text inputs, aiming to align image and text (category) spaces for downstream tasks. However, current…

Humans can accomplish complex contact-rich tasks using vision and touch, with highly reactive capabilities such as fast response to external changes and adaptive control of contact forces; however, this remains challenging for robots.…

In the last two years, text-to-image diffusion models have become extremely popular. As their quality and usage increase, a major concern has been the need for better output control. In addition to prompt engineering, one effective method…

As the field of image generation rapidly advances, traditional diffusion models and those integrated with multimodal large language models (LLMs) still encounter limitations in interpreting complex prompts and preserving image consistency…

Instruction-guided image editing enables users to specify modifications using natural language, offering more flexibility and control. Among existing frameworks, Diffusion Transformers (DiTs) outperform U-Net-based diffusion models in…

Despite the ability of existing large-scale text-to-image (T2I) models to generate high-quality images from detailed textual descriptions, they often lack the ability to precisely edit the generated or real images. In this paper, we propose…

Existing text-to-image editing methods tend to excel either in rigid or non-rigid editing but encounter challenges when combining both, resulting in misaligned outputs with the provided text prompts. In addition, integrating reference…

The extensive amounts of data required for training deep neural networks pose significant challenges on storage and transmission fronts. Dataset distillation has emerged as a promising technique to condense the information of massive…

Adapter-based parameter-efficient transfer learning has achieved exciting results in vision-language models. Traditional adapter methods often require training or fine-tuning, facing challenges such as insufficient samples or resource…