Related papers: Diffusion Model for Dense Matching

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…

Recent advancements in image motion deblurring, driven by CNNs and transformers, have made significant progress. Large-scale pre-trained diffusion models, which are rich in real-world modeling, have shown great promise for high-quality…

We introduce Transfusion, a recipe for training a multi-modal model over discrete and continuous data. Transfusion combines the language modeling loss function (next token prediction) with diffusion to train a single transformer over…

Although deep learning-based visual tracking methods have made significant progress, they exhibit vulnerabilities when facing carefully designed adversarial attacks, which can lead to a sharp decline in tracking performance. To address this…

We present the first text-based image editing approach for object parts based on pre-trained diffusion models. Diffusion-based image editing approaches capitalized on the deep understanding of diffusion models of image semantics to perform…

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…

Learning from a large corpus of data, pre-trained models have achieved impressive progress nowadays. As popular generative pre-training, diffusion models capture both low-level visual knowledge and high-level semantic relations. In this…

In this paper, we propose a diffusion-based face swapping framework for the first time, called DiffFace, composed of training ID conditional DDPM, sampling with facial guidance, and a target-preserving blending. In specific, in the training…

Federated learning aims at training models collaboratively across participants while protecting privacy. However, one major challenge for this paradigm is the data heterogeneity issue, where biased data preferences across multiple clients,…

Constructing high-definition (HD) maps is a crucial requirement for enabling autonomous driving. In recent years, several map segmentation algorithms have been developed to address this need, leveraging advancements in Bird's-Eye View (BEV)…

Diffusion models have shown promising generative capabilities across diverse domains, yet aligning their outputs with desired reward functions remains a challenge, particularly in cases where reward functions are non-differentiable. Some…

In recent advancements in high-fidelity image generation, Denoising Diffusion Probabilistic Models (DDPMs) have emerged as a key player. However, their application at high resolutions presents significant computational challenges. Current…

As one of the most successful generative models, diffusion models have demonstrated remarkable efficacy in synthesizing high-quality images. These models learn the underlying high-dimensional data distribution in an unsupervised manner.…

Diffusion, a fundamental internal mechanism emerging in many physical processes, describes the interaction among different objects. In many learning tasks with limited training samples, the diffusion connects the labeled and unlabeled data…

Real-world image denoising is an extremely important image processing problem, which aims to recover clean images from noisy images captured in natural environments. In recent years, diffusion models have achieved very promising results in…

The recovery of high-quality images from images corrupted by lens flare presents a significant challenge in low-level vision. Contemporary deep learning methods frequently entail training a lens flare removing model from scratch. However,…

Diffusion-based data augmentation (DiffDA) has emerged as a promising approach to improving classification performance under data scarcity. However, existing works vary significantly in task configurations, model choices, and experimental…

Recent years have witnessed the rapid development of acceleration techniques for diffusion models, especially caching-based acceleration methods. These studies seek to answer two fundamental questions: "When to cache" and "How to use…

Reinforcement learning (RL) algorithms have been used recently to align diffusion models with downstream objectives such as aesthetic quality and text-image consistency by fine-tuning them to maximize a single reward function under a fixed…

Recently, there has been an increased interest in the practical problem of learning multiple dense scene understanding tasks from partially annotated data, where each training sample is only labeled for a subset of the tasks. The missing of…