Related papers: CAMILA: Context-Aware Masking for Image Editing wi…
Semantic image editing requires inpainting pixels following a semantic map. It is a challenging task since this inpainting requires both harmony with the context and strict compliance with the semantic maps. The majority of the previous…
The recent GAN inversion methods have been able to successfully invert the real image input to the corresponding editable latent code in StyleGAN. By combining with the language-vision model (CLIP), some text-driven image manipulation…
Instruction-based image editing focuses on equipping a generative model with the capacity to adhere to human-written instructions for editing images. Current approaches typically comprehend explicit and specific instructions. However, they…
Instruction-based image editing (IIE) aims to modify images according to textual instructions while preserving irrelevant content. Despite recent advances in diffusion transformers, existing methods often suffer from over-editing,…
Current text-driven image editing methods typically follow one of two directions: relying on large-scale, high-quality editing pair datasets to improve editing precision and diversity, or exploring alternative dataset-free techniques.…
Although image captioning models have made significant advancements in recent years, the majority of them heavily depend on high-quality datasets containing paired images and texts which are costly to acquire. Previous works leverage the…
News image captioning requires model to generate an informative caption rich in entities, with the news image and the associated news article. Current MLLMs still bear limitations in handling entity information in news image captioning…
Text-driven image editing has advanced rapidly, but reliably localizing these manipulations requires image manipulation localization (IML) models trained on large pixel-annotated datasets, and there is still no low-cost way to obtain such…
With the rapid advancement of image generation, visual text editing using natural language instructions has received increasing attention. The main challenge of this task is to fully understand the instruction and reference image, and thus…
Language has emerged as a natural interface for image editing. In this paper, we introduce a method for region-based image editing driven by textual prompts, without the need for user-provided masks or sketches. Specifically, our approach…
Contrastive Language-Image Pre-training (CLIP) plays an essential role in extracting valuable content information from images across diverse tasks. It aligns textual and visual modalities to comprehend the entire image, including all the…
Scene text recognition is a rapidly developing field that faces numerous challenges due to the complexity and diversity of scene text, including complex backgrounds, diverse fonts, flexible arrangements, and accidental occlusions. In this…
Editing complex visual content from ambiguous or partially specified instructions remains a core challenge in vision-language modeling. Existing models can contextualize content but often fail to infer the underlying intent within a…
We present a novel, training-free approach for textual editing of real images using diffusion models. Unlike prior methods that rely on computationally expensive finetuning, our approach leverages LAtent SPatial Alignment (LASPA) to…
In this paper, we propose the LoRA of Change (LoC) framework for image editing with visual instructions, i.e., before-after image pairs. Compared to the ambiguities, insufficient specificity, and diverse interpretations of natural language,…
Camouflage is primarily context-dependent yet current metrics for camouflaged scenarios overlook this critical factor. Instead, these metrics are originally designed for evaluating general or salient objects, with an inherent assumption of…
In this paper, we focus on the task of instruction-based image editing. Previous works like InstructPix2Pix, InstructDiffusion, and SmartEdit have explored end-to-end editing. However, two limitations still remain: First, existing datasets…
Recent diffusion-based image editing methods have significantly advanced text-guided tasks but often struggle to interpret complex, indirect instructions. Moreover, current models frequently suffer from poor identity preservation,…
Due to the lack of extensive precisely-annotated multi-label data in real word, semi-supervised multi-label learning (SSMLL) has gradually gained attention. Abundant knowledge embedded in vision-language models (VLMs) pre-trained on…
Existing multi-turn image editing paradigms are often confined to isolated single-step execution. Due to a lack of context-awareness and closed-loop feedback mechanisms, they are prone to error accumulation and semantic drift during…