paper-with-me

홈 › Papers

LaRE^2: Latent Reconstruction Error Based Method for Diffusion-Generated Image Detection

2024-03-26 · CVPR 2024 1 · Yunpeng Luo, Junlong Du, Ke Yan, Shouhong Ding

The evolution of Diffusion Models has dramatically improved image generation quality, making it increasingly difficult to differentiate between real and generated images. This development, while impressive, also raises significant privacy and security concerns. In response to this, we propose a novel Latent REconstruction error guided feature REfinement method (LaRE^2) for detecting the diffusion-generated images. We come up with the Latent Reconstruction Error (LaRE), the first reconstruction-error based feature in the latent space for generated image detection. LaRE surpasses existing methods in terms of feature extraction efficiency while preserving crucial cues required to differentiate between the real and the fake. To exploit LaRE, we propose an Error-Guided feature REfinement module (EGRE), which can refine the image feature guided by LaRE to enhance the discriminativeness of the feature. Our EGRE utilizes an align-then-refine mechanism, which effectively refines the image feature for generated-image detection from both spatial and channel perspectives. Extensive experiments on the large-scale GenImage benchmark demonstrate the superiority of our LaRE^2, which surpasses the best SoTA method by up to 11.9%/12.1% average ACC/AP across 8 different image generators. LaRE also surpasses existing methods in terms of feature extraction cost, delivering an impressive speed enhancement of 8 times. Code is available.

📄 PDF Abstract BibTeX arXiv:2403.17465

Code (1)

luo3300612/lare 공식 구현 pytorch

Tasks

Image Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Difflare: Removing Image Lens Flare with Latent Diffusion Model

2024-07-20 · Tianwen Zhou, Qihao Duan, Zitong Yu

The recovery of high-quality images from images corrupted by lens flare presents a significant challenge in low-level vision. Contemporary deep learning methods frequently entail training a lens flare removing model from…

Flare Removal

FLARE: Robot Learning with Implicit World Modeling

2025-05-21 · Ruijie Zheng, Jing Wang, Scott Reed, Johan Bjorck 외

We introduce $\textbf{F}$uture $\textbf{LA}$tent $\textbf{RE}$presentation Alignment ($\textbf{FLARE}$), a novel framework that integrates predictive latent world modeling into robot policy learning. By aligning features…

Imitation LearningVision-Language-Action

Latent Multi-Relation Reasoning for GAN-Prior based Image Super-Resolution

2022-08-04 · Jiahui Zhang, Fangneng Zhan, Yingchen Yu, Rongliang Wu 외

Recently, single image super-resolution (SR) under large scaling factors has witnessed impressive progress by introducing pre-trained generative adversarial networks (GANs) as priors. However, most GAN-Priors based SR me…

AttributeCode GenerationDisentanglementImage Super-Resolution+2

LATTE: Latent Trajectory Embedding for Diffusion-Generated Image Detection

2025-07-03 · Ana Vasilcoiu, Ivona Najdenkoska, Zeno Geradts, Marcel Worring arxiv

The rapid advancement of diffusion-based image generators has made it increasingly difficult to distinguish generated from real images. This erodes trust in digital media, making it critical to develop generated image de…

Trajectory Modeling

Canonical Latent Representations in Conditional Diffusion Models

2025-06-11 · Yitao Xu, Tong Zhang, Ehsan Pajouheshgar, Sabine Süsstrunk

Conditional diffusion models (CDMs) have shown impressive performance across a range of generative tasks. Their ability to model the full data distribution has opened new avenues for analysis-by-synthesis in downstream d…

Adversarial RobustnessRepresentation Learning