Related papers: Improved Adversarial Diffusion Compression for Rea…
A diffusion-based voice conversion (VC) model (e.g., VoiceGrad) can achieve high speech quality and speaker similarity; however, its conversion process is slow owing to iterative sampling. FastVoiceGrad overcomes this limitation by…
Standard Latent Diffusion Models rely on a complex, three-part architecture consisting of a separate encoder, decoder, and diffusion network, which are trained in multiple stages. This modular design is computationally inefficient, leads to…
In this work, we first propose DiffVC-OSD, a One-Step Diffusion-based Perceptual Neural Video Compression framework. Unlike conventional multi-step diffusion-based methods, DiffVC-OSD feeds the reconstructed latent representation directly…
Pre-trained text-to-image diffusion models are increasingly applied to real-world image super-resolution (Real-ISR) task. Given the iterative refinement nature of diffusion models, most existing approaches are computationally expensive.…
Diffusion Transformer (DiT), a promising diffusion model for visual generation, demonstrates impressive performance but incurs significant computational overhead. Intriguingly, analysis of pre-trained DiT models reveals that global…
The inference latency of diffusion models remains a critical barrier to their real-time application. While trajectory-based and distribution-based step distillation methods offer solutions, they present a fundamental trade-off.…
The emergence of diffusion models has significantly advanced generative AI, improving the quality, realism, and creativity of image and video generation. Among them, Stable Diffusion (StableDiff) stands out as a key model for text-to-image…
In recent years, end-to-end learnt video codecs have demonstrated their potential to compete with conventional coding algorithms in term of compression efficiency. However, most learning-based video compression models are associated with…
Dataset distillation is the technique of synthesizing smaller condensed datasets from large original datasets while retaining necessary information to persist the effect. In this paper, we approach the dataset distillation problem from a…
This study presents a new image super-resolution (SR) technique based on diffusion inversion, aiming at harnessing the rich image priors encapsulated in large pre-trained diffusion models to improve SR performance. We design a Partial noise…
Conventional class-guided diffusion models generally succeed in generating images with correct semantic content, but often struggle with texture details. This limitation stems from the usage of class priors, which only provide coarse and…
Diffusion Transformer (DiT), an emerging diffusion model for image generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs stem from the static inference…
Deep learning has shown great potential in accelerating diffusion tensor imaging (DTI). Nevertheless, existing methods tend to suffer from Rician noise and eddy current, leading to detail loss in reconstructing the DTI-derived parametric…
Current video deblurring methods have limitations in recovering high-frequency information since the regression losses are conservative with high-frequency details. Since Diffusion Models (DMs) have strong capabilities in generating…
The diffusion models are widely used for image and video generation, but their iterative generation process is slow and expansive. While existing distillation approaches have demonstrated the potential for one-step generation in the image…
Deep learning has shown great potential in accelerating diffusion tensor imaging (DTI). Nevertheless, existing methods tend to suffer from Rician noise and detail loss in reconstructing the DTI-derived parametric maps especially when…
Despite the recent advances in large-scale diffusion models, little progress has been made on the layout-to-image (L2I) synthesis task. Current L2I models either suffer from poor editability via text or weak alignment between the generated…
In recent years, the rapid expansion of dataset sizes and the increasing complexity of deep learning models have significantly escalated the demand for computational resources, both for data storage and model training. Dataset distillation…
In the context of continuously rising global air traffic, efficient and safe Conflict Detection and Resolution (CD&R) is paramount for air traffic management. Although Deep Reinforcement Learning (DRL) offers a promising pathway for CD&R…
Recent advances in video generation models has significantly accelerated video generation and related downstream tasks. Among these, video stylization holds important research value in areas such as immersive applications and artistic…