Related papers: Rethinking Diffusion Model-Based Video Super-Resol…
Diffusion models have become a leading paradigm for image super-resolution (SR), but existing methods struggle to guarantee both the high-frequency perceptual quality and the low-frequency structural fidelity of generated images. Although…
Augmentation for dense prediction typically relies on either sample mixing or generative synthesis. Mixing improves robustness but misaligned masks yield soft label ambiguity. Diffusion synthesis increases apparent diversity but, when…
Video Diffusion Models (VDMs) can generate high-quality videos, but often struggle with producing temporally coherent motion. Optical flow supervision is a promising approach to address this, with prior works commonly employing…
We present the RAW domain diffusion model (RDDM), an end-to-end diffusion model that restores photo-realistic images directly from the sensor RAW data. While recent sRGB-domain diffusion methods achieve impressive results, they are caught…
Advanced diffusion models (DMs) perform impressively in image super-resolution (SR), but the high memory and computational costs hinder their deployment. Binarization, an ultra-compression algorithm, offers the potential for effectively…
Omnidirectional image super-resolution (ODISR) aims to upscale low-resolution (LR) omnidirectional images (ODIs) to high-resolution (HR), catering to the growing demand for detailed visual content across a $ 180^{\circ}\times360^{\circ}$…
Image denoising is a fundamental and challenging task in the field of computer vision. Most supervised denoising methods learn to reconstruct clean images from noisy inputs, which have intrinsic spectral bias and tend to produce…
The task of Image-to-Video (I2V) generation aims to synthesize a video from a reference image and a text prompt. This requires diffusion models to reconcile high-frequency visual constraints and low-frequency textual guidance during the…
Reference-based image super-resolution (RefSR) is a promising SR branch and has shown great potential in overcoming the limitations of single image super-resolution. While previous state-of-the-art RefSR methods mainly focus on improving…
Latent diffusion models have emerged as a leading paradigm for efficient video generation. However, as user expectations shift toward higher-resolution outputs, relying solely on latent computation becomes inadequate. A promising approach…
Diffusion-based generative models have demonstrated exceptional promise in the video super-resolution (VSR) task, achieving a substantial advancement in detail generation relative to prior methods. However, these approaches face significant…
Recently, convolutional networks have achieved remarkable development in remote sensing image Super-Resoltuion (SR) by minimizing the regression objectives, e.g., MSE loss. However, despite achieving impressive performance, these methods…
Diffusion models have demonstrated remarkable performance in image and video synthesis. However, scaling them to high-resolution inputs is challenging and requires restructuring the diffusion pipeline into multiple independent components,…
Unsupervised learning of feature representations is a challenging yet important problem for analyzing a large collection of multimedia data that do not have semantic labels. Recently proposed neural network-based unsupervised learning…
Real-world image super-resolution is particularly challenging for diffusion models because real degradations are complex, heterogeneous, and rarely modeled explicitly. We propose a degradation-aware and structure-preserving diffusion…
Strong generative models can accurately learn channel distributions. This could save recurring costs for physical measurements of the channel. Moreover, the resulting differentiable channel model supports training neural encoders by…
Camera and LiDAR sensor modalities provide complementary appearance and geometric information useful for detecting 3D objects for autonomous vehicle applications. However, current end-to-end fusion methods are challenging to train and…
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…
To address the larger computation and storage requirements associated with large video datasets, video dataset distillation aims to capture spatial and temporal information in a significantly smaller dataset, such that training on the…
Global Navigation Satellite Systems (GNSS) are vital for reliable urban positioning. However, multipath and non-line-of-sight reception often introduce large measurement errors that degrade accuracy. Learning-based methods for predicting…