相关论文: DMM: Building a Versatile Image Generation Model v…

With the advent of diffusion models, Text-to-Image (T2I) generation has seen substantial advancements. Current T2I models allow users to specify object colors using linguistic color names, and some methods aim to personalize color-object…

Text-to-image generation models have achieved remarkable capabilities in synthesizing images, but often struggle to provide fine-grained control over the output. Existing guidance approaches, such as segmentation maps and depth maps,…

Image anomaly detection plays a vital role in applications such as industrial quality inspection and medical imaging, where it directly contributes to improving product quality and system reliability. However, existing methods often…

Dataset Distillation (DD), a newly emerging field, aims at generating much smaller but efficient synthetic training datasets from large ones. Existing DD methods based on gradient matching achieve leading performance; however, they are…

Recent score-based diffusion models (SBDMs) show promising results in unpaired image-to-image translation (I2I). However, existing methods, either energy-based or statistically-based, provide no explicit form of the interfered intermediate…

Representation learning has been evolving from traditional supervised training to Contrastive Learning (CL) and Masked Image Modeling (MIM). Previous works have demonstrated their pros and cons in specific scenarios, i.e., CL and supervised…

The quadratic computational complexity of self-attention in diffusion transformers (DiT) introduces substantial computational costs in high-resolution image generation. While the linear-complexity Mamba model emerges as a potential…

Image data augmentation constitutes a critical methodology in modern computer vision tasks, since it can facilitate towards enhancing the diversity and quality of training datasets; thereby, improving the performance and robustness of…

Diffusion trajectory distillation accelerates sampling by training a student model to approximate the multi-step denoising trajectories of a pretrained teacher model using far fewer steps. Despite strong empirical results, the trade-off…

Reasoning distillation transfers complex reasoning abilities from large language models (LLMs) to smaller ones, yet its success depends on how well the training data align with the student model. This paper introduces the Data-Model…

Text-to-3D is an emerging task that allows users to create 3D content with infinite possibilities. Existing works tackle the problem by optimizing a 3D representation with guidance from pre-trained diffusion models. An apparent drawback is…

Modern Text-to-Image (T2I) Diffusion models have revolutionized image editing by enabling the generation of high-quality photorealistic images. While the de facto method for performing edits with T2I models is through text instructions,…

Visual generation grounded in Visual Foundation Model (VFM) representations offers a highly promising unified pathway for integrating visual understanding, perception, and generation. Despite this potential, training large-scale…

Image Auto-regressive (AR) models have emerged as a powerful paradigm of visual generative models. Despite their promising performance, they suffer from slow generation speed due to the large number of sampling steps required. Although…

Diffusion distillation models effectively accelerate reverse sampling by compressing the process into fewer steps. However, these models still exhibit a performance gap compared to their pre-trained diffusion model counterparts, exacerbated…

Diffusion and flow matching models have significantly advanced media generation, yet their design space is well-explored, somewhat limiting further improvements. Concurrently, autoregressive (AR) models, particularly those generating…

A diffusion probabilistic model (DPM), which constructs a forward diffusion process by gradually adding noise to data points and learns the reverse denoising process to generate new samples, has been shown to handle complex data…

In text-to-image models, consistent character generation is the task of achieving text alignment while maintaining the subject's appearance across different prompts. However, since style and appearance are often entangled, the existing…

Score Distillation Sampling (SDS) has emerged as a prominent method for text-to-3D generation by leveraging the strengths of 2D diffusion models. However, SDS is limited to generation tasks and lacks the capability to edit existing 3D…

Despite astonishing progress, generating realistic images of complex scenes remains a challenging problem. Recently, layout-to-image synthesis approaches have attracted much interest by conditioning the generator on a list of bounding boxes…