相关论文: ImageNet-D: Benchmarking Neural Network Robustness…

Diffusion-based models, widely used in text-to-image generation, have proven effective in 2D representation learning. Recently, this framework has been extended to 3D self-supervised learning by constructing a conditional point generator…

I explored adapting Stable Diffusion v1.5 for generating domain-specific satellite and aerial images in remote sensing. Recognizing the limitations of existing models like Midjourney and Stable Diffusion, trained primarily on natural RGB…

Images produced by diffusion models are increasingly popular in digital artwork and visual marketing. However, such generated images might replicate content from existing ones and pose the challenge of content originality. Existing Image…

In the realm of digital media, the advent of AI-generated synthetic images has introduced significant challenges in distinguishing between real and fabricated visual content. These images, often indistinguishable from authentic ones, pose a…

Stable Diffusion Models (SDMs) have shown remarkable proficiency in image synthesis. However, their broad application is impeded by their large model sizes and intensive computational requirements, which typically require expensive cloud…

Generative models have become a powerful tool for synthesizing training data in computer vision tasks. Current approaches solely focus on aligning generated images with the target dataset distribution. As a result, they capture only the…

Deep neural networks (DNNs) have found widespread applications in interpreting remote sensing (RS) imagery. However, it has been demonstrated in previous works that DNNs are vulnerable to different types of noises, particularly adversarial…

Recent advances in generative deep learning have enabled the creation of high-quality synthetic images in text-to-image generation. Prior work shows that fine-tuning a pretrained diffusion model on ImageNet and generating synthetic training…

In our contemporary academic inquiry, we present "Diffusion-C," a foundational methodology to analyze the generative restrictions of Diffusion Models, particularly those akin to GANs, DDPM, and DDIM. By employing input visual data that has…

Deep neural networks on 3D point cloud data have been widely used in the real world, especially in safety-critical applications. However, their robustness against corruptions is less studied. In this paper, we present ModelNet40-C, the…

Robust invisible watermarking aims to embed hidden information into images such that the watermark can survive various image manipulations. However, the rise of powerful diffusion-based image generation and editing techniques poses a new…

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…

CNNs perform remarkably well when the training and test distributions are i.i.d, but unseen image corruptions can cause a surprisingly large drop in performance. In various real scenarios, unexpected distortions, such as random noise,…

Enhancing the robustness of vision algorithms in real-world scenarios is challenging. One reason is that existing robustness benchmarks are limited, as they either rely on synthetic data or ignore the effects of individual nuisance factors.…

Modern deep neural networks tend to be evaluated on static test sets. One shortcoming of this is the fact that these deep neural networks cannot be easily evaluated for robustness issues with respect to specific scene variations. For…

Ground-truth RGBD data are fundamental for a wide range of computer vision applications; however, those labeled samples are difficult to collect and time-consuming to produce. A common solution to overcome this lack of data is to employ…

Generating 3D scenes is a challenging open problem, which requires synthesizing plausible content that is fully consistent in 3D space. While recent methods such as neural radiance fields excel at view synthesis and 3D reconstruction, they…

The class-conditional image generation based on diffusion models is renowned for generating high-quality and diverse images. However, most prior efforts focus on generating images for general categories, e.g., 1000 classes in ImageNet-1k. A…

Deep denoising models require extensive real-world training data, which is challenging to acquire. Current noise synthesis techniques struggle to accurately model complex noise distributions. We propose a novel Realistic Noise Synthesis…

Recent progress in computer vision has been dominated by deep neural networks trained over large amounts of labeled data. Collecting such datasets is however a tedious, often impossible task; hence a surge in approaches relying solely on…