Related papers: PyramidalWan: On Making Pretrained Video Model Pyr…

This paper presents PipeFusion, an innovative parallel methodology to tackle the high latency issues associated with generating high-resolution images using diffusion transformers (DiTs) models. PipeFusion partitions images into patches and…

Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In this work, we propose a reinforcement learning based…

Video deblurring presents a considerable challenge owing to the complexity of blur, which frequently results from a combination of camera shakes, and object motions. In the field of video deblurring, many previous works have primarily…

Diffusion models have emerged as the de facto paradigm for video generation. However, their reliance on web-scale data of varied quality often yields results that are visually unappealing and misaligned with the textual prompts. To tackle…

Currently, methods for single-image deblurring based on CNNs and transformers have demonstrated promising performance. However, these methods often suffer from perceptual limitations, poor generalization ability, and struggle with heavy or…

In video surveillance, pedestrian retrieval (also called person re-identification) is a critical task. This task aims to retrieve the pedestrian of interest from non-overlapping cameras. Recently, transformer-based models have achieved…

One of the main drawback of diffusion models is the slow inference time for image generation. Among the most successful approaches to addressing this problem are distillation methods. However, these methods require considerable…

Recent advances in diffusion models enable many powerful instruments for image editing. One of these instruments is text-driven image manipulations: editing semantic attributes of an image according to the provided text description. %…

Diffusion models demonstrate remarkable capabilities in capturing complex data distributions and have achieved compelling results in many generative tasks. While they have recently been extended to dense prediction tasks such as depth…

We learn to compute optical flow by combining a classical spatial-pyramid formulation with deep learning. This estimates large motions in a coarse-to-fine approach by warping one image of a pair at each pyramid level by the current flow…

Visuomotor imitation learning policies enable robots to efficiently acquire manipulation skills from visual demonstrations. However, as scene complexity and visual distractions increase, policies that perform well in simple settings often…

As one of the most popular and sought-after generative models in the recent years, diffusion models have sparked the interests of many researchers and steadily shown excellent advantage in various generative tasks such as image synthesis,…

Diffusion models have been successfully adapted to text generation tasks by mapping the discrete text into the continuous space. However, there exist nonnegligible gaps between training and inference, owing to the absence of the forward…

This paper addresses the challenge of achieving high-quality and fast image generation that aligns with complex human preferences. While recent advancements in diffusion models and distillation have enabled rapid generation, the effective…

Large-scale generative models, such as text-to-image diffusion models, have garnered widespread attention across diverse domains due to their creative and high-fidelity image generation. Nonetheless, existing large-scale diffusion models…

Hiding data using neural networks (i.e., neural steganography) has achieved remarkable success across both discriminative classifiers and generative adversarial networks. However, the potential of data hiding in diffusion models remains…

This paper proposes ProEdit - a simple yet effective framework for high-quality 3D scene editing guided by diffusion distillation in a novel progressive manner. Inspired by the crucial observation that multi-view inconsistency in scene…

Diffusion models and flow-matching models have enabled generating diverse and realistic images by learning to transfer noise to data. However, sampling from these models involves iterative denoising over many neural network passes, making…

Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos based on text queries that describe only partial events. Existing methods suffer from incomplete global contextual perception, struggling with query ambiguity and…

Existing fusion methods are tailored for high-quality images but struggle with degraded images captured under harsh circumstances, thus limiting the practical potential of image fusion. This work presents a \textbf{D}egradation and…