Related papers: Focal Guidance: Unlocking Controllability from Sem…
Diffusion models have revolutionized video generation, becoming essential tools in creative content generation and physical simulation. Transformer-based architectures (DiTs) and classifier-free guidance (CFG) are two cornerstones of this…
Extensive pre-training with large data is indispensable for downstream geometry and semantic visual perception tasks. Thanks to large-scale text-to-image (T2I) pretraining, recent works show promising results by simply fine-tuning T2I…
While Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in general visual understanding, they frequently falter in fine-grained perception tasks that require identifying tiny objects or discerning subtle…
Image-to-video (I2V) generation has the potential for societal harm because it enables the unauthorized animation of static images to create realistic deepfakes. While existing defenses effectively protect against static image manipulation,…
Image diffusion models, trained on massive image collections, have emerged as the most versatile image generator model in terms of quality and diversity. They support inverting real images and conditional (e.g., text) generation, making…
Despite significant progress in Text-to-Image (T2I) generative models, even lengthy and complex text descriptions still struggle to convey detailed controls. In contrast, Layout-to-Image (L2I) generation, aiming to generate realistic and…
In the rapidly advancing realm of visual generation, diffusion models have revolutionized the landscape, marking a significant shift in capabilities with their impressive text-guided generative functions. However, relying solely on text for…
Recent text-to-image (T2I) diffusion models show outstanding performance in generating high-quality images conditioned on textual prompts. However, they fail to semantically align the generated images with the prompts due to their limited…
Text-to-video generation has shown promising results. However, by taking only natural languages as input, users often face difficulties in providing detailed information to precisely control the model's output. In this work, we propose…
Despite recent advances, diffusion-based text-to-image models still struggle with accurate text rendering. Several studies have proposed fine-tuning or training-free refinement methods for accurate text rendering. However, the critical…
Text-and-Image-To-Image (TI2I), an extension of Text-To-Image (T2I), integrates image inputs with textual instructions to enhance image generation. Existing methods often partially utilize image inputs, focusing on specific elements like…
Text-to-video (T2V) diffusion models have rapidly advanced, yet generations still occasionally fail in practice, such as low text-video alignment or low perceptual quality. Since diffusion sampling is non-deterministic, it is difficult to…
Text-conditioned image generation models have recently shown immense qualitative success using denoising diffusion processes. However, unlike discriminative vision-and-language models, it is a non-trivial task to subject these…
Despite diffusion models having shown powerful abilities to generate photorealistic images, generating videos that are realistic and diverse still remains in its infancy. One of the key reasons is that current methods intertwine spatial…
Weakly-supervised semantic segmentation aims to assign category labels to each pixel using weak annotations, significantly reducing manual annotation costs. Although existing methods have achieved remarkable progress in well-lit scenarios,…
Controllable image-to-video (I2V) generation transforms a reference image into a coherent video guided by user-specified control signals. In content creation workflows, precise and simultaneous control over camera motion, object motion, and…
Text-to-image diffusion models excel at translating language prompts into photorealistic images by implicitly grounding textual concepts through their cross-modal attention mechanisms. Recent multi-modal diffusion transformers extend this…
Efficient fine-tuning of pre-trained Text-to-Image (T2I) models involves adjusting the model to suit a particular task or dataset while minimizing computational resources and limiting the number of trainable parameters. However, it often…
Visual understanding is inherently contextual -- what we focus on in an image depends on the task at hand. For instance, given an image of a person holding a bouquet of flowers, we may focus on either the person such as their clothing, or…
Negation is a fundamental linguistic operator, yet it remains inadequately modeled in diffusion-based generative systems. In this work, we present a formal treatment of linguistic negation in diffusion-based generative models by modeling it…