Related papers: Improved Adversarial Diffusion Compression for Rea…

Transformer-based Super-Resolution (SR) methods have demonstrated superior performance compared to convolutional neural network (CNN)-based SR approaches due to their capability to capture long-range dependencies. However, their high…

Existing video tokenizers typically use the traditional Variational Autoencoder (VAE) architecture for video compression and reconstruction. However, to achieve good performance, its training process often relies on complex multi-stage…

Autonomous vehicles are typical complex intelligent systems with artificial intelligence at their core. However, perception methods based on deep learning are extremely vulnerable to adversarial samples, resulting in security accidents. How…

Deep 3D point cloud models are sensitive to adversarial attacks, which poses threats to safety-critical applications such as autonomous driving. Robust training and defend-by-denoising are typical strategies for defending adversarial…

Real-SR endeavors to produce high-resolution images with rich details while mitigating the impact of multiple degradation factors. Although existing methods have achieved impressive achievements in detail recovery, they still fall short…

Video generation has recently emerged as a central task in the field of generative AI. However, the substantial computational cost inherent in video synthesis makes model distillation a critical technique for efficient deployment. Despite…

Diffusion Transformer (DiT), an emerging diffusion model for visual generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs primarily stem from the…

Autoregressive video generators are attractive for streaming, long-horizon, and interactive applications, but distilling strong black-box teachers into causal students remains difficult. The student must learn under its own rollout…

Diffusion-based Video Super-Resolution (VSR) is renowned for generating perceptually realistic videos, yet it grapples with maintaining detail consistency across frames due to stochastic fluctuations. The traditional approach of pixel-level…

Video diffusion transformers (DiTs) suffer from prohibitive inference latency due to quadratic attention complexity. Existing sparse attention methods either overlook semantic similarity or fail to adapt to heterogeneous token distributions…

Super-resolution remains a promising technique to enhance the quality of low-resolution images. This study introduces CATformer (Contrastive Adversarial Transformer), a novel neural network integrating diffusion-inspired feature refinement…

Modern text-to-video (T2V) diffusion models can synthesize visually compelling clips, yet they remain brittle at fine-scale structure: even state-of-the-art generators often produce distorted faces and hands, warped backgrounds, and…

Diffusion models have achieved impressive performance in video generation, but their iterative denoising process remains computationally expensive due to the large number of tokens processed at each timestep. Recently, progressive…

Real-world videos often extend over thousands of frames. Existing generative video super-resolution (VSR) approaches, however, face two persistent challenges when processing long sequences: (1) inefficiency due to the heavy cost of…

Diffusion Models (DMs) have achieved great success in image generation and other fields. By fine sampling through the trajectory defined by the SDE/ODE solver based on a well-trained score model, DMs can generate remarkable high-quality…

Diffusion models, known for their powerful generative capabilities, play a crucial role in addressing real-world super-resolution challenges. However, these models often focus on improving local textures while neglecting the impacts of…

Recently, a series of diffusion-aware distillation algorithms have emerged to alleviate the computational overhead associated with the multi-step inference process of Diffusion Models (DMs). Current distillation techniques often dichotomize…

Diffusion models with transformer architectures have demonstrated promising capabilities in generating high-fidelity images and scalability for high resolution. However, iterative sampling process required for synthesis is very…

Reconstructing 3D objects from extremely sparse views is a long-standing and challenging problem. While recent techniques employ image diffusion models for generating plausible images at novel viewpoints or for distilling pre-trained…

Recent progress in 3D reconstruction has enabled realistic 3D models from dense image captures, yet challenges persist with sparse views, often leading to artifacts in unseen areas. Recent works leverage Video Diffusion Models (VDMs) to…