paper-with-me

Papers

Utilizing Multi-step Loss for Single Image Reflection Removal

2024-12-11 · Abdelrahman Elnenaey, Marwan Torki

Image reflection removal is crucial for restoring image quality. Distorted images can negatively impact tasks like object detection and image segmentation. In this paper, we present a novel approach for image reflection removal using a single image. Instead of focusing on model architecture, we introduce a new training technique that can be generalized to image-to-image problems, with input and output being similar in nature. This technique is embodied in our multi-step loss mechanism, which has proven effective in the reflection removal task. Additionally, we address the scarcity of reflection removal training data by synthesizing a high-quality, non-linear synthetic dataset called RefGAN using Pix2Pix GAN. This dataset significantly enhances the model's ability to learn better patterns for reflection removal. We also utilize a ranged depth map, extracted from the depth estimation of the ambient image, as an auxiliary feature, leveraging its property of lacking depth estimations for reflections. Our approach demonstrates superior performance on the SIR^2 benchmark and other real-world datasets, proving its effectiveness by outperforming other state-of-the-art models.

📄 PDF Abstract BibTeX arXiv:2412.08582

Code (1)

AbdelrhmanElnenaey/SIRR_MSloss_RefGAN_RDM 공식 구현

Tasks

Depth EstimationImage Segmentationobject-detectionObject DetectionReflection RemovalSemantic Segmentation

Methods 이 논문이 사용한 방법론

Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
PatchGAN 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Batch Normalization 설명 없음
Sigmoid Activation 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Distilling Diffusion Models into Conditional GANs

2024-05-09 · Minguk Kang, Richard Zhang, Connelly Barnes, Sylvain Paris 외

We propose a method to distill a complex multistep diffusion model into a single-step conditional GAN student model, dramatically accelerating inference, while preserving image quality. Our approach interprets diffusion …

Image-to-Image Translation

HF-Diff: High-Frequency Perceptual Loss and Distribution Matching for One-Step Diffusion-Based Image Super-Resolution

2024-11-20 · Shoaib Meraj Sami, Md Mahedi Hasan, Jeremy Dawson, Nasser Nasrabadi

Although recent diffusion-based single-step super-resolution methods achieve better performance as compared to SinSR, they are computationally complex. To improve the performance of SinSR, we investigate preserving the h…

Image Super-ResolutionSuper-Resolution

Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses

2020-11-30 · NeurIPS 2020 12 · Gaurang Sriramanan, Sravanti Addepalli, Arya Baburaj, R. Venkatesh Babu

Advances in the development of adversarial attacks have been fundamental to the progress of adversarial defense research. Efficient and effective attacks are crucial for reliable evaluation of defenses, and also for deve…

Adversarial AttackAdversarial Defense

SEVA: Leveraging Single-Step Ensemble of Vicinal Augmentations for Test-Time Adaptation

2025-05-07 · Zixuan Hu, Yichun Hu, Ling-Yu Duan

Test-Time adaptation (TTA) aims to enhance model robustness against distribution shifts through rapid model adaptation during inference. While existing TTA methods often rely on entropy-based unsupervised training and ac…

Test-time Adaptation

FlashSR: One-step Versatile Audio Super-resolution via Diffusion Distillation

2025-01-18 · Jaekwon Im, Juhan Nam

Versatile audio super-resolution (SR) is the challenging task of restoring high-frequency components from low-resolution audio with sampling rates between 4kHz and 32kHz in various domains such as music, speech, and soun…

Audio Super-ResolutionSuper-Resolution