Related papers: DiffusionMat: Alpha Matting as Sequential Refineme…
Diffusion model has emerged as the \emph{de-facto} model for image generation, yet the heavy training overhead hinders its broader adoption in the research community. We observe that diffusion models are commonly trained to learn all…
Diffusion models achieve remarkable quality in image generation, but at a cost. Iterative denoising requires many time steps to produce high fidelity images. We argue that the denoising process is crucially limited by an accumulation of the…
Natural image matting estimates the alpha values of unknown regions in the trimap. Recently, deep learning based methods propagate the alpha values from the known regions to unknown regions according to the similarity between them. However,…
With the great success of diffusion models in image generation, diffusion-based image compression is attracting increasing interests. However, due to the random noise introduced in the diffusion learning, they usually produce…
The advance of generative models for images has inspired various training techniques for image recognition utilizing synthetic images. In semantic segmentation, one promising approach is extracting pseudo-masks from attention maps in…
Semantic segmentation and change detection are two fundamental challenges in remote sensing, requiring models to capture either spatial semantics or temporal differences from satellite imagery. Existing deep learning models often struggle…
The depth-of-field (DoF) effect, which introduces aesthetically pleasing blur, enhances photographic quality but is fixed and difficult to modify once the image has been created. This becomes problematic when the applied blur is…
While diffusion Multimodal Large Language Models (dMLLMs) have recently achieved remarkable strides in multimodal generation, the development of interpretability mechanisms has lagged behind their architectural evolution. Unlike traditional…
Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified…
Image denoising is an important problem in low-level vision and serves as a critical module for many image recovery tasks. Anisotropic diffusion is a wide family of image denoising approaches with promising performance. However, traditional…
Deep learning-based diagnostic systems have demonstrated potential in skin disease diagnosis. However, their performance can easily degrade on test domains due to distribution shifts caused by input-level corruptions, such as imaging…
Background: Photoacoustic Microscopy (PAM) integrates optical and acoustic imaging, offering enhanced penetration depth for detecting optical-absorbing components in tissues. Nonetheless, challenges arise in scanning large areas with high…
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)…
Facial attribute editing aims to modify target attributes while preserving attribute-irrelevant content and overall image fidelity. Existing GAN-based methods provide favorable controllability, but often suffer from weak alignment between…
The recently rising markup-to-image generation poses greater challenges as compared to natural image generation, due to its low tolerance for errors as well as the complex sequence and context correlations between markup and rendered image.…
Surgical triplet recognition is an essential building block to enable next-generation context-aware operating rooms. The goal is to identify the combinations of instruments, verbs, and targets presented in surgical video frames. In this…
Recently, diffusion models have gained significant attention as a novel set of deep learning-based generative methods. These models attempt to sample data from a Gaussian distribution that adheres to a target distribution, and have been…
We introduce a new general-purpose approach to deep learning on 3D surfaces, based on the insight that a simple diffusion layer is highly effective for spatial communication. The resulting networks are automatically robust to changes in…
Diffusion models have found valuable applications in anomaly detection by capturing the nominal data distribution and identifying anomalies via reconstruction. Despite their merits, they struggle to localize anomalies of varying scales,…
Recent advancements in large-scale text-to-image diffusion models have enabled many applications in image editing. However, none of these methods have been able to edit the layout of single existing images. To address this gap, we propose…