Related papers: ReCo-Diff: Residual-Conditioned Deterministic Samp…
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…
Classifier-free guided diffusion models have recently been shown to be highly effective at high-resolution image generation, and they have been widely used in large-scale diffusion frameworks including DALLE-2, Stable Diffusion and Imagen.…
How can we learn generative models to sample data with arbitrary logical compositions of statistically independent attributes? The prevailing solution is to sample from distributions expressed as a composition of attributes' conditional…
We introduce Spectral Guidance, a framework for controlling diffusion models by leveraging the intrinsic geometry of the generative process. As data is progressively corrupted by noise, only a small number of features remain informative for…
This paper introduces innovative solutions to enhance spatial controllability in diffusion models reliant on text queries. We first introduce vision guidance as a foundational spatial cue within the perturbed distribution. This…
Diffusion models have recently attained significant interest within the community owing to their strong performance as generative models. Furthermore, its application to inverse problems have demonstrated state-of-the-art performance.…
RGB-to-hyperspectral image reconstruction is a highly ill-posed inverse problem, since multiple plausible spectral distributions may correspond to the same RGB observation. Existing regression-based methods usually learn a deterministic…
Diffusion models have shown remarkable progress in various generative tasks such as image and video generation. This paper studies the problem of leveraging pretrained diffusion models for performing discriminative tasks. Specifically, we…
Mesh reconstruction from multi-view images is a fundamental problem in computer vision, but its performance degrades significantly under sparse-view conditions, especially in unseen regions where no ground-truth observations are available.…
Diffusion models generate samples through an iterative denoising process, guided by a neural network. While training the denoiser on real-world data is computationally demanding, the sampling procedure itself is more flexible. This…
Diffusion-based sparse-view CT (SVCT) imaging has achieved remarkable advancements in recent years, thanks to its more stable generative capability. However, recovering reliable image content and visually consistent textures is still a…
The conditional diffusion model (CDM) enhances the standard diffusion model by providing more control, improving the quality and relevance of the outputs, and making the model adaptable to a wider range of complex tasks. However, inaccurate…
This paper presents PolyDiffuse, a novel structured reconstruction algorithm that transforms visual sensor data into polygonal shapes with Diffusion Models (DM), an emerging machinery amid exploding generative AI, while formulating…
Recent work showed that large diffusion models can be reused as highly precise monocular depth estimators by casting depth estimation as an image-conditional image generation task. While the proposed model achieved state-of-the-art results,…
Classifier-guided diffusion models have emerged as a powerful approach for conditional image generation, but they suffer from overconfident predictions during early denoising steps, causing the guidance gradient to vanish. This paper…
The generalization of deep learning-based low-dose computed tomography (CT) reconstruction models to doses unseen in the training data is important and remains challenging. Previous efforts heavily rely on paired data to improve the…
Seismic data frequently exhibits missing traces, substantially affecting subsequent seismic processing and interpretation. Deep learning-based approaches have demonstrated significant advancements in reconstructing irregularly missing…
We propose a novel and unified method, measurement-conditioned denoising diffusion probabilistic model (MC-DDPM), for under-sampled medical image reconstruction based on DDPM. Different from previous works, MC-DDPM is defined in measurement…
Local climate information is crucial for impact assessment and decision-making, yet coarse global climate simulations cannot capture small-scale phenomena. Current statistical downscaling methods infer these phenomena as temporally…
Image fusion aims to integrate complementary information from multiple input images acquired through various sources to synthesize a new fused image. Existing methods usually employ distinct constraint designs tailored to specific scenes,…