Related papers: One-Step Residual Shifting Diffusion for Image Sup…

Semantic correspondence, the task of determining relationships between different parts of images, underpins various applications including 3D reconstruction, image-to-image translation, object tracking, and visual place recognition. Recent…

Synthetic Aperture Radar (SAR) provides all-weather, high-resolution imaging capabilities, but its unique imaging mechanism often requires expert interpretation, limiting its widespread applicability. Translating SAR images into more easily…

Deep denoising models require extensive real-world training data, which is challenging to acquire. Current noise synthesis techniques struggle to accurately model complex noise distributions. We propose a novel Realistic Noise Synthesis…

Diffusion distillation, exemplified by Distribution Matching Distillation (DMD), has shown great promise in few-step generation but often sacrifices quality for sampling speed. While integrating Reinforcement Learning (RL) into distillation…

Diffusion models can synthesize realistic co-speech video from audio for various applications, such as video creation and virtual agents. However, existing diffusion-based methods are slow due to numerous denoising steps and costly…

Reasoning segmentation enables open-set object segmentation via implicit text queries, therefore serving as a foundation for embodied agents that should operate autonomously in real-world environments. However, existing methods for…

While deep learning techniques have proven successful in image-related tasks, the exponentially increased data storage and computation costs become a significant challenge. Dataset distillation addresses these challenges by synthesizing…

The generation and enhancement of satellite imagery are critical in remote sensing, requiring high-quality, detailed images for accurate analysis. This research introduces a two-stage diffusion model methodology for synthesizing…

Flow-based generative super-resolution (SR) models learn to produce a diverse set of feasible SR solutions, called the SR space. Diversity of SR solutions increases with the temperature ($\tau$) of latent variables, which introduces random…

Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to multiple tasks is challenging: joint…

Recent research on knowledge distillation has increasingly focused on logit distillation because of its simplicity, effectiveness, and versatility in model compression. In this paper, we introduce Refined Logit Distillation (RLD) to address…

Data-Free Knowledge Distillation (DFKD) is a novel task that aims to train high-performance student models using only the pre-trained teacher network without original training data. Most of the existing DFKD methods rely heavily on…

Methods for improving the efficiency of deep network training (i.e. the resources required to achieve a given level of model quality) are of immediate benefit to deep learning practitioners. Distillation is typically used to compress models…

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…

We present a new method for making diffusion models faster to sample. The method distills many-step diffusion models into few-step models by matching conditional expectations of the clean data given noisy data along the sampling trajectory.…

Generative models, particularly diffusion models, have made significant success in data synthesis across various modalities, including images, videos, and 3D assets. However, current diffusion models are computationally intensive, often…

Dataset distillation aims to minimize the time and memory needed for training deep networks on large datasets, by creating a small set of synthetic images that has a similar generalization performance to that of the full dataset. However,…

Recently, the deep convolutional neural network (CNN) has made remarkable progress in single image super resolution(SISR). However, blindly using the residual structure and dense structure to extract features from LR images, can cause the…

Existing Score Distillation Sampling (SDS)-based methods have driven significant progress in text-to-3D generation. However, 3D models produced by SDS-based methods tend to exhibit over-smoothing and low-quality outputs. These issues arise…

Diffusion-based generative models have demonstrated their powerful performance across various tasks, but this comes at a cost of the slow sampling speed. To achieve both efficient and high-quality synthesis, various distillation-based…