Related papers: Resolving the Identity Crisis in Text-to-Image Gen…
Personalized image synthesis has emerged as a pivotal application in text-to-image generation, enabling the creation of images featuring specific subjects in diverse contexts. While diffusion models have dominated this domain,…
We present Diffusion-KTO, a novel approach for aligning text-to-image diffusion models by formulating the alignment objective as the maximization of expected human utility. Since this objective applies to each generation independently,…
Recent advances have demonstrated compelling capabilities in synthesizing real individuals into generated videos, reflecting the growing demand for identity-aware content creation. Nevertheless, an openly accessible framework enabling…
We present a framework for high-fidelity product image recontextualization using text-to-image diffusion models and a novel data augmentation pipeline. This pipeline leverages image-to-video diffusion, in/outpainting & negatives to create…
Dichotomous Image Segmentation (DIS) tasks require highly precise annotations, and traditional dataset creation methods are labor intensive, costly, and require extensive domain expertise. Although using synthetic data for DIS is a…
Unsupervised person re-identification (re-ID) has become an important topic due to its potential to resolve the scalability problem of supervised re-ID models. However, existing methods simply utilize pseudo labels from clustering for…
Text-to-image customization, which aims to synthesize text-driven images for the given subjects, has recently revolutionized content creation. Existing works follow the pseudo-word paradigm, i.e., represent the given subjects as…
Face editing methods, essential for tasks like virtual avatars, digital human synthesis and identity preservation, have traditionally been built upon GAN-based techniques, while recent focus has shifted to diffusion-based models due to…
The increasing realism of AI-generated images has raised serious concerns about misinformation and privacy violations, highlighting the urgent need for accurate and interpretable detection methods. While existing approaches have made…
The field of text-conditioned image generation has made unparalleled progress with the recent advent of latent diffusion models. While remarkable, as the complexity of given text input increases, the state-of-the-art diffusion models may…
Recent advances in diffusion models have demonstrated impressive capability in generating high-quality images for simple prompts. However, when confronted with complex prompts involving multiple objects and hierarchical structures, existing…
Optimizing discrete diffusion model (DDM) with rewards remains a challenge: the non-autoregressive paradigm makes importance sampling intractable and rollout complex, puzzling reinforcement learning methods such as Group Relative Policy…
Diversity in image generation is essential to ensure fair representations and support creativity in ideation. Hence, many text-to-image models have implemented diversification mechanisms. Yet, after a few iterations of generation, a lack of…
Text-to-3D synthesis has recently emerged as a new approach to sampling 3D models by adopting pretrained text-to-image models as guiding visual priors. An intriguing but underexplored problem with existing text-to-3D methods is that 3D…
Identifying the same individual across different scenes is an important yet difficult task in intelligent video surveillance. Its main difficulty lies in how to preserve similarity of the same person against large appearance and structure…
Reinforcement learning has significantly enhanced the reasoning capabilities of Large Language Models (LLMs) in complex problem-solving tasks. Recently, the introduction of DeepSeek R1 has inspired a surge of interest in leveraging…
Despite recent advancements in text-to-image models, achieving semantically accurate images in text-to-image diffusion models is a persistent challenge. While existing initial latent optimization methods have demonstrated impressive…
Customized generation aims to incorporate a novel concept into a pre-trained text-to-image model, enabling new generations of the concept in novel contexts guided by textual prompts. However, customized generation suffers from an inherent…
Recent advances in text-to-image generation with diffusion models present transformative capabilities in image quality. However, user controllability of the generated image, and fast adaptation to new tasks still remains an open challenge,…
Text-to-image (T2I) diffusion models have demonstrated impressive performance in generating high-fidelity images, largely enabled by text-guided inference. However, this advantage often comes with a critical drawback: limited diversity, as…