相关论文: Shape-Guided Diffusion with Inside-Outside Attenti…
Text-driven person image generation is an emerging and challenging task in cross-modality image generation. Controllable person image generation promotes a wide range of applications such as digital human interaction and virtual try-on.…
Despite many attempts to leverage pre-trained text-to-image models (T2I) like Stable Diffusion (SD) for controllable image editing, producing good predictable results remains a challenge. Previous approaches have focused on either…
Diffusion models (DMs) have gained prominence due to their ability to generate high-quality varied images with recent advancements in text-to-image generation. The research focus is now shifting towards the controllability of DMs. A…
The ability to manipulate objects in a desired configurations is a fundamental requirement for robots to complete various practical applications. While certain goals can be achieved by picking and placing the objects of interest directly,…
Personalizing text-to-image diffusion models is crucial for adapting the pre-trained models to specific target concepts, enabling diverse image generation. However, fine-tuning with few images introduces an inherent trade-off between…
Multiview diffusion models have rapidly emerged as a powerful tool for content creation with spatial consistency across viewpoints, offering rich visual realism without requiring explicit geometry and appearance representation. However,…
Recent advancements in diffusion and flow-matching models have demonstrated remarkable capabilities in high-fidelity image synthesis. A prominent line of research involves reward-guided guidance, which steers the generation process during…
Style transfer aims to render a content image with the visual characteristics of a reference style while preserving its underlying semantic layout and structural geometry. While recent diffusion-based models demonstrate strong stylization…
The diffusion-based generative models have achieved remarkable success in text-based image generation. However, since it contains enormous randomness in generation progress, it is still challenging to apply such models for real-world visual…
We present a novel image editing scenario termed Text-grounded Object Generation (TOG), defined as generating a new object in the real image spatially conditioned by textual descriptions. Existing diffusion models exhibit limitations of…
Producing quality segmentation masks for images is a fundamental problem in computer vision. Recent research has explored large-scale supervised training to enable zero-shot segmentation on virtually any image style and unsupervised…
Diffusion-based text-to-image personalization have achieved great success in generating subjects specified by users among various contexts. Even though, existing finetuning-based methods still suffer from model overfitting, which greatly…
Image editing approaches have become more powerful and flexible with the advent of powerful text-conditioned generative models. However, placing objects in an environment with a precise location and orientation still remains a challenge, as…
Current diffusion-based video editing primarily focuses on local editing (\textit{e.g.,} object/background editing) or global style editing by utilizing various dense correspondences. However, these methods often fail to accurately edit the…
Text-to-video editing aims to edit the visual appearance of a source video conditional on textual prompts. A major challenge in this task is to ensure that all frames in the edited video are visually consistent. Most recent works apply…
The rapid advancement of diffusion models has enhanced their image inpainting and editing capabilities but also introduced significant societal risks. Adversaries can exploit user images from social media to generate misleading or harmful…
Recent controllable generation approaches such as FreeControl and Diffusion Self-Guidance bring fine-grained spatial and appearance control to text-to-image (T2I) diffusion models without training auxiliary modules. However, these methods…
The modern text-to-image diffusion models boom has opened a new era in digital content production as it has proven the previously unseen ability to produce photorealistic and stylistically diverse imagery based on the semantics of…
Depth information provides valuable insights into the 3D structure especially the outline of objects, which can be utilized to improve the semantic segmentation tasks. However, a naive fusion of depth information can disrupt feature and…
We propose a method for editing images from human instructions: given an input image and a written instruction that tells the model what to do, our model follows these instructions to edit the image. To obtain training data for this…