Related papers: MASQ: Accelerating Masked Diffusion via Stage-Wise…
Diffusion Transformers (DiTs) have achieved state-of-the-art performance in image and video generation, but their success comes at the cost of heavy computation. This inefficiency is largely due to the fixed tokenization process, which uses…
Text-to-image generation has witnessed great progress, especially with the recent advancements in diffusion models. Since texts cannot provide detailed conditions like object appearance, reference images are usually leveraged for the…
Neural network accelerators have been widely applied to edge devices for complex tasks like object tracking, image recognition, etc. Previous works have explored the quantization technologies in related lightweight accelerator designs to…
Diffusion models dominate image editing, yet their global denoising mechanism entangles edited regions with surrounding context, causing modifications to propagate into areas that should remain intact. We propose a fundamentally different…
Motivated by discrete diffusion's success in language-vision modeling, we explore its potential for multi-view generation, a task dominated by continuous approaches. We introduce ViewMask-1-to-3, formulating multi-view synthesis as a…
Dataset distillation provides an effective approach to reduce memory and computational costs by optimizing a compact dataset that achieves performance comparable to the full original. However, for large-scale datasets and complex deep…
We offer a method for one-shot mask-guided image synthesis that allows controlling manipulations of a single image by inverting a quasi-robust classifier equipped with strong regularizers. Our proposed method, entitled MAGIC, leverages…
In this paper, an efficient skin detection system is proposed. The algorithm is based on a very fast efficient pre-processing step utilizing the concept of ternary conversion in order to identify candidate windows and subsequently, a novel…
Conventional multiply-accumulate (MAC) operations have long dominated computation time for deep neural networks (DNNs), espcially convolutional neural networks (CNNs). Recently, product quantization (PQ) has been applied to these workloads,…
Diffusion models are powerful, but they require a lot of time and data to train. We propose Patch Diffusion, a generic patch-wise training framework, to significantly reduce the training time costs while improving data efficiency, which…
Optical multilayer thin-films are fundamental components that enable the precise control of reflectance, transmittance, and phase shift in the design of photonic systems. Rapid and accessible simulation of these structures holds critical…
Diffusion models have achieved great success in synthesizing high-quality images. However, generating high-resolution images with diffusion models is still challenging due to the enormous computational costs, resulting in a prohibitive…
Recently, diffusion models have exhibited superior performance in the area of image inpainting. Inpainting methods based on diffusion models can usually generate realistic, high-quality image content for masked areas. However, due to the…
Text-to-image diffusion models (DMs) develop at an unprecedented pace, supported by thorough theoretical exploration and empirical analysis. Unfortunately, the discrepancy between DMs and autoregressive models (ARMs) complicates the path…
Diffusion Models (DMs) have demonstrated state-of-the-art performance in content generation without requiring adversarial training. These models are trained using a two-step process. First, a forward - diffusion - process gradually adds…
Point cloud streaming is increasingly getting popular, evolving into the norm for interactive service delivery and the future Metaverse. However, the substantial volume of data associated with point clouds presents numerous challenges,…
Diffusion-based image editing offers strong semantic controllability, but remains computationally expensive due to iterative high-resolution denoising over all spatial tokens. Dynamic-resolution sampling reduces this cost by performing…
Significant advancements in image generation have been made with diffusion models. Nevertheless, when contrasted with previous generative models, diffusion models face substantial computational overhead, leading to failure in real-time…
Understanding semantic information is an essential step in knowing what is being learned in both full-reference (FR) and no-reference (NR) image quality assessment (IQA) methods. However, especially for many severely distorted images, even…
The evolution of quantization and mixed-precision techniques has unlocked new possibilities for enhancing the speed and energy efficiency of NNs. Several recent studies indicate that adapting precision levels across different parameters can…