paper-with-me

Papers

SDDNet: Style-guided Dual-layer Disentanglement Network for Shadow Detection

2023-08-17 · Runmin Cong, Yuchen Guan, Jinpeng Chen, Wei zhang, Yao Zhao, Sam Kwong

Despite significant progress in shadow detection, current methods still struggle with the adverse impact of background color, which may lead to errors when shadows are present on complex backgrounds. Drawing inspiration from the human visual system, we treat the input shadow image as a composition of a background layer and a shadow layer, and design a Style-guided Dual-layer Disentanglement Network (SDDNet) to model these layers independently. To achieve this, we devise a Feature Separation and Recombination (FSR) module that decomposes multi-level features into shadow-related and background-related components by offering specialized supervision for each component, while preserving information integrity and avoiding redundancy through the reconstruction constraint. Moreover, we propose a Shadow Style Filter (SSF) module to guide the feature disentanglement by focusing on style differentiation and uniformization. With these two modules and our overall pipeline, our model effectively minimizes the detrimental effects of background color, yielding superior performance on three public datasets with a real-time inference speed of 32 FPS.

📄 PDF Abstract BibTeX arXiv:2308.08935

Code (1)

rmcong/sddnet_acmmm23 공식 구현 pytorch

Tasks

DisentanglementShadow Detection

Methods 이 논문이 사용한 방법론

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

VQ-Style: Disentangling Style and Content in Motion with Residual Quantized Representations

2026-02-02 · Fatemeh Zargarbashi, Dhruv Agrawal, Jakob Buhmann, Martin Guay 외 arxiv

Human motion data is inherently rich and complex, containing both semantic content and subtle stylistic features that are challenging to model. We propose a novel method for effective disentanglement of the style and con…

Contrastive LearningStyle Transfer

Content-style disentangled representation for controllable artistic image stylization and generation

2024-12-19 · Ma Zhuoqi, Zhang Yixuan, You Zejun, Tian Long 외

Controllable artistic image stylization and generation aims to render the content provided by text or image with the learned artistic style, where content and style decoupling is the key to achieve satisfactory results. …

DisentanglementImage Stylization

UniCSG: Unified High-Fidelity Content-Constrained Style-Driven Generation via Staged Semantic and Frequency Disentanglement

2026-04-20 · Jingwei Yang, Ruoxi Wu, Wei Shen, Meng Li 외 arxiv

Style transfer must match a target style while preserving content semantics. DiT-based diffusion models often suffer from content-style entanglement, leading to reference-content leakage and unstable generation. We prese…

Style Transfer

Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translation

2021-03-30 · ICCV 2021 10 · Gihyun Kwon, Jong Chul Ye

One of the important research topics in image generative models is to disentangle the spatial contents and styles for their separate control. Although StyleGAN can generate content feature vectors from random noises, the…

DisentanglementImage GenerationTranslation

Fine-Grained Face Swapping via Regional GAN Inversion

2022-11-25 · CVPR 2023 1 · Zhian Liu, Maomao Li, Yong Zhang, Cairong Wang 외

We present a novel paradigm for high-fidelity face swapping that faithfully preserves the desired subtle geometry and texture details. We rethink face swapping from the perspective of fine-grained face editing, \textit{i…

DisentanglementFace Swapping