Related papers: D$^2$iT: Dynamic Diffusion Transformer for Accurat…
Diffusion models have become a leading approach for high-fidelity medical image synthesis. However, most existing methods for 3D medical image generation rely on convolutional U-Net backbones within latent diffusion frameworks. While…
Latent-space modeling has been the standard for Diffusion Transformers (DiTs). However, it relies on a two-stage pipeline where the pretrained autoencoder introduces lossy reconstruction, leading to error accumulation while hindering joint…
\textit{Nature is infinitely resolution-free}. In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing image resolutions outside of their trained domain. To address…
Diffusion models are widely used for generative tasks across domains. Given a pre-trained diffusion model, it is often desirable to fine-tune it further either to correct for errors in learning or to align with downstream applications.…
Recently, the strong latent Diffusion Probabilistic Model (DPM) has been applied to high-quality Text-to-Image (T2I) generation (e.g., Stable Diffusion), by injecting the encoded target text prompt into the gradually denoised diffusion…
Video compression aims to maximize reconstruction quality with minimal bitrates. Beyond standard distortion metrics, perceptual quality and temporal consistency are also critical. However, at ultra-low bitrates, traditional end-to-end…
Diffusion models have shown remarkable success in visual synthesis, but have also raised concerns about potential abuse for malicious purposes. In this paper, we seek to build a detector for telling apart real images from…
Recently, the tokens of images share the same static data flow in many dense networks. However, challenges arise from the variance among the objects in images, such as large variations in the spatial scale and difficulties of recognition…
Recent progress in diffusion models has significantly advanced the field of human image animation. While existing methods can generate temporally consistent results for short or regular motions, significant challenges remain, particularly…
Despite recent advances in UNet-based image editing, methods for shape-aware object editing in high-resolution images are still lacking. Compared to UNet, Diffusion Transformers (DiT) demonstrate superior capabilities to effectively capture…
Generative diffusion models have achieved remarkable success in producing high-quality images. However, these models typically operate in continuous intensity spaces, diffusing independently across pixels and color channels. As a result,…
Image compression under ultra-low bitrates remains challenging for both conventional learned image compression (LIC) and generative vector-quantized (VQ) modeling. Conventional LIC suffers from severe artifacts due to heavy quantization,…
Diffusion Transformers (DiT) are renowned for their impressive generative performance; however, they are significantly constrained by considerable computational costs due to the quadratic complexity in self-attention and the extensive…
Large-scale pre-trained diffusion models are becoming increasingly popular in solving the Real-World Image Super-Resolution (Real-ISR) problem because of their rich generative priors. The recent development of diffusion transformer (DiT)…
Pixel diffusion aims to generate images directly in pixel space in an end-to-end fashion. This approach avoids the limitations of VAE in the two-stage latent diffusion, offering higher model capacity. Existing pixel diffusion models suffer…
In this study, we explore Transformer-based diffusion models for image and video generation. Despite the dominance of Transformer architectures in various fields due to their flexibility and scalability, the visual generative domain…
Image fusion seeks to seamlessly integrate foreground objects with background scenes, producing realistic and harmonious fused images. Unlike existing methods that directly insert objects into the background, adaptive and interactive fusion…
3D shape generation has greatly flourished through the development of so-called "native" 3D diffusion, particularly through the Vecset Diffusion Model (VDM). While recent advancements have shown promising results in generating…
This paper introduces Diffuse-TreeVAE, a deep generative model that integrates hierarchical clustering into the framework of Denoising Diffusion Probabilistic Models (DDPMs). The proposed approach generates new images by sampling from a…
In this work, we propose a novel framework to enable diffusion models to adapt their generation quality based on real-time network bandwidth constraints. Traditional diffusion models produce high-fidelity images by performing a fixed number…