Related papers: PLACID: Identity-Preserving Multi-Object Compositi…

Despite significant progress, controlled generation of complex images with interacting people remains difficult. Existing layout generation methods fall short of synthesizing realistic person instances; while pose-guided generation…

Synthesizing consistent and photorealistic 3D scenes is an open problem in computer vision. Video diffusion models generate impressive videos but cannot directly synthesize 3D representations, i.e., lack 3D consistency in the generated…

Despite recent advances in personalized image generation, existing models consistently fail to produce reliable multi-human scenes, often merging or losing facial identity. We present Ar2Can, a novel two-stage framework that disentangles…

Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space. Here, we apply the LDM paradigm to high-resolution…

Data augmentation is crucial for improving the robustness of face detection systems, especially under challenging conditions such as occlusion, illumination variation, and complex environments. Traditional copy paste augmentation often…

The ability to decompose complex multi-object scenes into meaningful abstractions like objects is fundamental to achieve higher-level cognition. Previous approaches for unsupervised object-oriented scene representation learning are either…

Multi-subject image generation aims to synthesize user-provided subjects in a single image while preserving subject fidelity, ensuring prompt consistency, and aligning with human aesthetic preferences. Existing In-Context-Learning based…

Gaussian Splatting (GS) has emerged as an effective representation for photorealistic rendering, but the underlying geometry, material, and lighting remain entangled, hindering scene editing. Existing GS-based methods struggle to…

3D hand-object interaction data is scarce due to the hardware constraints in scaling up the data collection process. In this paper, we propose HOIDiffusion for generating realistic and diverse 3D hand-object interaction data. Our model is a…

Although remarkable progress has been made in image style transfer, style is just one of the components of artistic paintings. Directly transferring extracted style features to natural images often results in outputs with obvious synthetic…

Large-scale text-to-image diffusion models have achieved great success in synthesizing high-quality and diverse images given target text prompts. Despite the revolutionary image generation ability, current state-of-the-art models still…

Despite the success of generating high-quality images given any text prompts by diffusion-based generative models, prior works directly generate the entire images, but cannot provide object-wise manipulation capability. To support wider…

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…

Limited real-world data severely impacts model performance in many computer vision domains, particularly for samples that are underrepresented in training. Synthetically generated images are a promising solution, but 1) it remains unclear…

We introduce a method for composing object-level visual prompts within a text-to-image diffusion model. Our approach addresses the task of generating semantically coherent compositions across diverse scenes and styles, similar to the…

Recent strides in Text-to-3D techniques have been propelled by distilling knowledge from powerful large text-to-image diffusion models (LDMs). Nonetheless, existing Text-to-3D approaches often grapple with challenges such as…

Face personalization aims to insert specific faces, taken from images, into pretrained text-to-image diffusion models. However, it is still challenging for previous methods to preserve both the identity similarity and editability due to…

Text-to-3D form plays a crucial role in creating editable 3D scenes for AR/VR. Recent advances have shown promise in merging neural radiance fields (NeRFs) with pre-trained diffusion models for text-to-3D object generation. However, one…

Although diffusion models have demonstrated remarkable generative capabilities, existing style transfer techniques often struggle to maintain identity while achieving high-quality stylization. This limitation becomes particularly critical…

Advanced image editing techniques, particularly inpainting, are essential for seamlessly removing unwanted elements while preserving visual integrity. Traditional GAN-based methods have achieved notable success, but recent advancements in…