Related papers: Content-Adaptive Image Retouching Guided by Attrib…
We present Causal-Adapter, a modular framework that adapts frozen text-to-image diffusion backbones for counterfactual image generation. Our method supports causal interventions on target attributes and consistently propagates their effects…
Recent image tone adjustment (or enhancement) approaches have predominantly adopted supervised learning for learning human-centric perceptual assessment. However, these approaches are constrained by intrinsic challenges of supervised…
Text-to-image generative models have achieved remarkable visual quality but still struggle with compositionality$-$accurately capturing object relationships, attribute bindings, and fine-grained details in prompts. A key limitation is that…
Contemporary image generation systems have achieved high fidelity and superior aesthetic quality beyond basic text-image alignment. However, existing evaluation frameworks have failed to evolve in parallel. This study reveals that human…
Recent advances in text-to-image (T2I) diffusion models have enabled remarkable control over various attributes, yet precise color specification remains a fundamental challenge. Existing approaches, such as ColorPeel, rely on model…
Supervised image captioning approaches have made great progress, but it is challenging to collect high-quality human-annotated image-text data. Recently, large-scale vision and language models (e.g., CLIP) and large-scale generative…
Most existing image tokenizers encode images into a fixed number of tokens or patches, overlooking the inherent variability in image complexity. To address this, we introduce Content-Adaptive Tokenizer (CAT), which dynamically adjusts…
Manipulating visual attributes of images through human-written text is a very challenging task. On the one hand, models have to learn the manipulation without the ground truth of the desired output. On the other hand, models have to deal…
Generating high-fidelity images of humans with fine-grained control over attributes such as hairstyle and clothing remains a core challenge in personalized text-to-image synthesis. While prior methods emphasize identity preservation from a…
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…
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…
Despite the high-quality results of text-to-image generation, stereotypical biases have been spotted in their generated contents, compromising the fairness of generative models. In this work, we propose to learn adaptive inclusive tokens to…
Cross-modal retrieval between videos and texts has gained increasing research interest due to the rapid emergence of videos on the web. Generally, a video contains rich instance and event information and the query text only describes a part…
Instruction driven image editing with standard CLIP text encoders often fails in complex scenes with many objects. We present QL-Adapter, a framework for multiple object editing that tackles two challenges: enforcing object counts and…
Pre-trained large text-to-image models synthesize impressive images with an appropriate use of text prompts. However, ambiguities inherent in natural language and out-of-distribution effects make it hard to synthesize image styles, that…
Current image transformation and recoloring algorithms try to introduce artistic effects in the photographed images, based on user input of target image(s) or selection of pre-designed filters. These manipulations, although intended to…
Real-world applications could benefit from the ability to automatically retarget an image to different aspect ratios and resolutions, while preserving its visually and semantically important content. However, not all images can be equally…
Image retargeting changes the aspect ratio of images while aiming to preserve content and minimise noticeable distortion. Fast and high-quality methods are particularly relevant at present, due to the large variety of image and display…
Curve & Lookup Table (LUT) based methods directly map a pixel to the target output, making them highly efficient tools for real-time photography processing. However, due to extreme memory complexity to learn full RGB space mapping, existing…
In recent years, learning-based color and tone enhancement methods for photos have become increasingly popular. However, most learning-based image enhancement methods just learn a mapping from one distribution to another based on one…