Related papers: ContextGen: Contextual Layout Anchoring for Identi…
Recent breakthroughs in text-to-image diffusion models have significantly advanced the generation of high-fidelity, photo-realistic images from textual descriptions. Yet, these models often struggle with interpreting spatial arrangements…
Recent advancements in personalizing text-to-image (T2I) diffusion models have shown the capability to generate images based on personalized visual concepts using a limited number of user-provided examples. However, these models often…
Recent advances in personalized generative models have demonstrated impressive capabilities in producing identity-consistent images of the same individual across diverse scenes. However, most existing methods lack explicit viewpoint control…
Image-to-Video generation (I2V) animates a static image into a temporally coherent video sequence following textual instructions, yet preserving fine-grained object identity under changing viewpoints remains a persistent challenge. Unlike…
In this paper, we present an efficient and effective single-stage framework (DiverGAN) to generate diverse, plausible and semantically consistent images according to a natural-language description. DiverGAN adopts two novel word-level…
Camouflage Images Generation (CIG) is an emerging research area that focuses on synthesizing images in which objects are harmoniously blended and exhibit high visual consistency with their surroundings. Existing methods perform CIG by…
Text-to-image (T2I) generation has made remarkable progress in producing high-quality images, but a fundamental challenge remains: creating backgrounds that naturally accommodate text placement without compromising image quality. This…
We seek to give users precise control over diffusion-based image generation by modeling complex scenes as sequences of layers, which define the desired spatial arrangement and visual attributes of objects in the scene. Collage Diffusion…
Unmanned aerial vehicle (UAV) based object detection is a critical but challenging task, when applied in dynamically changing scenarios with limited annotated training data. Layout-to-image generation approaches have proved effective in…
Accurate and controllable image editing is a challenging task that has attracted significant attention recently. Notably, DragGAN is an interactive point-based image editing framework that achieves impressive editing results with…
Despite remarkable achievements in video synthesis, achieving granular control over complex dynamics, such as nuanced movement among multiple interacting objects, still presents a significant hurdle for dynamic world modeling, compounded by…
Significant achievements in personalization of diffusion models have been witnessed. Conventional tuning-free methods mostly encode multiple reference images by averaging their image embeddings as the injection condition, but such an…
Recent advancements in large-scale text-to-image diffusion models have enabled many applications in image editing. However, none of these methods have been able to edit the layout of single existing images. To address this gap, we propose…
Context, as referred to situational factors related to the object of interest, can help infer the object's states or properties in visual recognition. As such contextual features are too diverse (across instances) to be annotated, existing…
Text-to-video generation has made remarkable advancements through diffusion models. However, Multi-Concept Video Customization (MCVC) remains a significant challenge. We identify two key challenges for this task: 1) the identity decoupling…
Human-centric generative models designed for AI-driven storytelling must bring together two core capabilities: identity consistency and precise control over human performance. While recent diffusion-based approaches have made significant…
Recent advances in generative modeling have enabled the generation of high-quality synthetic data that is applicable in a variety of domains, including face recognition. Here, state-of-the-art generative models typically rely on…
The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we…
We introduce Contextual Vision Transformers (ContextViT), a method designed to generate robust image representations for datasets experiencing shifts in latent factors across various groups. Derived from the concept of in-context learning,…
The dual-stream transformer architecture-based joint audio-video generation method has become the dominant paradigm in current research. By incorporating pre-trained video diffusion models and audio diffusion models, along with a…