相关论文: Dominating vs. Dominated: Generative Collapse in D…

Concept unlearning has emerged as a promising direction for reducing the risks of harmful content generation in text-to-image diffusion models by selectively erasing undesirable concepts from a model's parameters. Existing approaches…

Text-to-image diffusion models have achieved widespread popularity due to their unprecedented image generation capability. In particular, their ability to synthesize and modify human faces has spurred research into using generated face…

Text-to-image (T2I) diffusion models, with their impressive generative capabilities, have been adopted for image editing tasks, demonstrating remarkable efficacy. However, due to attention leakage and collision between the cross-attention…

Deepfake images are fast becoming a serious concern due to their realism. Diffusion models have recently demonstrated highly realistic visual content generation, which makes them an excellent potential tool for Deepfake generation. To curb…

Recently, the multimedia community has witnessed the rise of diffusion models trained on large-scale multi-modal data for visual content creation, particularly in the field of text-to-image generation. In this paper, we propose a new task…

Diffusion Transformer (DiT), a promising diffusion model for visual generation, demonstrates impressive performance but incurs significant computational overhead. Intriguingly, analysis of pre-trained DiT models reveals that global…

Neural networks struggle with image classification when biases are learned and misleads correlations, affecting their generalization and performance. Previous methods require attribute labels (e.g. background, color) or utilizes Generative…

Diffusion models have revolutionized generative modeling, enabling unprecedented realism in image and video synthesis. This success has sparked interest in leveraging their representations for visual understanding tasks. While recent works…

The rapid advancement in image generation models has predominantly been driven by diffusion models, which have demonstrated unparalleled success in generating high-fidelity, diverse images from textual prompts. Despite their success,…

Attention mechanism has been crucial for image diffusion models, however, their quadratic computational complexity limits the sizes of images we can process within reasonable time and memory constraints. This paper investigates the…

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We…

Accurately predicting 3D occupancy grids from visual inputs is critical for autonomous driving, but current discriminative methods struggle with noisy data, incomplete observations, and the complex structures inherent in 3D scenes. In this…

Latent diffusion models (LDMs) dominate high-quality image generation, yet integrating representation learning with generative modeling remains a challenge. We introduce a novel generative image modeling framework that seamlessly bridges…

In this work, we explore an untapped signal in diffusion model inference. While all previous methods generate images independently at inference, we instead ask if samples can be generated collaboratively. We propose Group Diffusion,…

Diffusion models have been widely deployed in various image generation tasks, demonstrating an extraordinary connection between image and text modalities. Although prior studies have explored the vulnerability of diffusion models from the…

The increasing prevalence of synthetic data in training loops has raised concerns about model collapse, where generative models degrade when trained on their own outputs. While prior work focuses on this self-consuming process, we study an…

Talking head generation is a significant research topic that still faces numerous challenges. Previous works often adopt generative adversarial networks or regression models, which are plagued by generation quality and average facial shape…

Training-free diffusion models have achieved remarkable progress in generating multi-subject consistent images within open-domain scenarios. The key idea of these methods is to incorporate reference subject information within the attention…

Diffusion Models (DMs) have emerged as powerful generative models with unprecedented image generation capability. These models are widely used for data augmentation and creative applications. However, DMs reflect the biases present in the…

While generative models have seen significant adoption across a wide range of data modalities, including 3D data, a consensus on which model is best suited for which task has yet to be reached. Further, conditional information such as text…