Related papers: NanoSD: Edge Efficient Foundation Model for Real T…
This paper presents a new exploration into a category of diffusion models built upon state space architecture. We endeavor to train diffusion models for image data, wherein the traditional U-Net backbone is supplanted by a state space…
Diffusion Transformers (DiTs) with billions of model parameters form the backbone of popular image and video generation models like DALL.E, Stable-Diffusion and SORA. Though these models are necessary in many low-latency applications like…
We establish rigorous benchmarks for visual perception robustness. Synthetic images such as ImageNet-C, ImageNet-9, and Stylized ImageNet provide specific type of evaluation over synthetic corruptions, backgrounds, and textures, yet those…
Image deblurring is a critical stage in mobile image signal processing pipelines, where the ability to restore fine structures and textures must be balanced with real-time constraints on edge devices. While recent deep networks such as…
We introduce native-resolution image synthesis, a novel generative modeling paradigm that enables the synthesis of images at arbitrary resolutions and aspect ratios. This approach overcomes the limitations of conventional fixed-resolution,…
We propose Latent-Shift -- an efficient text-to-video generation method based on a pretrained text-to-image generation model that consists of an autoencoder and a U-Net diffusion model. Learning a video diffusion model in the latent space…
Faithful image super-resolution (SR) not only needs to recover images that appear realistic, similar to image generation tasks, but also requires that the restored images maintain fidelity and structural consistency with the input. To this…
There is a growing interest in the use of latent diffusion models (LDMs) for image restoration (IR) tasks due to their ability to model effectively the distribution of natural images. While significant progress has been made, there are…
Recent methods for molecular generation face a trade-off: they either enforce strict equivariance with costly architectures or relax it to gain scalability and flexibility. We propose a frame-based diffusion paradigm that achieves…
Diffusion-based image generation models have advanced rapidly but pose a safety risk due to their potential to generate Not-Safe-For-Work (NSFW) content. Existing NSFW detection methods mainly operate either before or after image…
We present a cascaded diffusion model based on a part-level implicit 3D representation. Our model achieves state-of-the-art generation quality and also enables part-level shape editing and manipulation without any additional training in…
Diffusion models have emerged as the new state-of-the-art generative model with high quality samples, with intriguing properties such as mode coverage and high flexibility. They have also been shown to be effective inverse problem solvers,…
Diffusion models have demonstrated their powerful image generation capabilities, effectively fitting highly complex image distributions. These models can serve as strong priors for image restoration. Existing methods often utilize…
Recent literature has effectively leveraged diffusion models trained on continuous variables as priors for solving inverse problems. Notably, discrete diffusion models with discrete latent codes have shown strong performance, particularly…
Recent developments in stimulated emission depletion (STED) microscopy achieved nanometer scale resolution and showed great potential in live cell imaging. Yet, STED nanoscopy techniques are based on single point-scanning. This constitutes…
Video generation using diffusion-based models is constrained by high computational costs due to the frame-wise iterative diffusion process. This work presents a Diffusion Reuse MOtion (Dr. Mo) network to accelerate latent video generation.…
Diffusion models have recently gained unprecedented attention in the field of image synthesis due to their remarkable generative capabilities. Notwithstanding their prowess, these models often incur substantial computational costs,…
Neural Architecture Search (NAS) is quickly becoming the go-to approach to optimize the structure of Deep Learning (DL) models for complex tasks such as Image Classification or Object Detection. However, many other relevant applications of…
Neural networks have achieved remarkable performance across a wide range of tasks, yet they remain susceptible to adversarial perturbations, which pose significant risks in safety-critical applications. With the rise of multimodality,…
Deep generative models have emerged as promising tools for detecting arbitrary anomalies in data, dispensing with the necessity for manual labelling. Recently, autoregressive transformers have achieved state-of-the-art performance for…