中文
相关论文

相关论文: Physically Motivated Knowledge Distillation for Bl…

200 篇论文

By adopting popular pixel-wise loss, existing methods for defocus deblurring heavily rely on well aligned training image pairs. Although training pairs of ground-truth and blurry images are carefully collected, e.g., DPDD dataset,…

计算机视觉与模式识别 · 计算机科学 2022-11-30 Yu Li , Dongwei Ren , Xinya Shu , Wangmeng Zuo

In stereo-matching knowledge distillation methods of the self-supervised monocular depth estimation, the stereo-matching network's knowledge is distilled into a monocular depth network through pseudo-depth maps. In these methods, the…

计算机视觉与模式识别 · 计算机科学 2024-01-24 Woonghyun Ka , Jae Young Lee , Jaehyun Choi , Junmo Kim

Transformer-based encoder-decoder models have achieved remarkable success in image-to-image transfer tasks, particularly in image restoration. However, their high computational complexity-manifested in elevated FLOPs and parameter…

计算机视觉与模式识别 · 计算机科学 2025-01-17 Yongheng Zhang , Danfeng Yan

Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model. Previous KD methods typically train a student by minimizing a task-related loss and…

计算机视觉与模式识别 · 计算机科学 2019-09-10 Mengya Gao , Yujun Shen , Quanquan Li , Junjie Yan , Liang Wan , Dahua Lin , Chen Change Loy , Xiaoou Tang

This paper proposes the first self-supervised 6D object pose prediction from multimodal RGB+polarimetric images. The novel training paradigm comprises 1) a physical model to extract geometric information of polarized light, 2) a…

计算机视觉与模式识别 · 计算机科学 2023-12-05 Patrick Ruhkamp , Daoyi Gao , Nassir Navab , Benjamin Busam

Model compression through knowledge distillation has seen extensive application in classification and segmentation tasks. However, its potential in image-to-image translation, particularly in image restoration, remains underexplored. To…

计算机视觉与模式识别 · 计算机科学 2025-01-17 Yongheng Zhang , Danfeng Yan

Lossy compression algorithms aim to compactly encode images in a way which enables to restore them with minimal error. We show that a key limitation of existing algorithms is that they rely on error measures that are extremely sensitive to…

计算机视觉与模式识别 · 计算机科学 2018-04-13 Tamar Rott Shaham , Tomer Michaeli

The scarcity of large-scale 3D-text paired data poses a great challenge on open vocabulary 3D scene understanding, and hence it is popular to leverage internet-scale 2D data and transfer their open vocabulary capabilities to 3D models…

计算机视觉与模式识别 · 计算机科学 2024-07-19 Pengfei Wang , Yuxi Wang , Shuai Li , Zhaoxiang Zhang , Zhen Lei , Lei Zhang

Food recognition has a wide range of applications, such as health-aware recommendation and self-service restaurants. Most previous methods of food recognition firstly locate informative regions in some weakly-supervised manners and then…

计算机视觉与模式识别 · 计算机科学 2023-08-16 Yaohui Zhu , Linhu Liu , Jiang Tian

Monocular depth estimation, enabled by self-supervised learning, is a key technique for 3D perception in computer vision. However, it faces significant challenges in real-world scenarios, which encompass adverse weather variations, motion…

计算机视觉与模式识别 · 计算机科学 2024-10-10 Runze Chen , Haiyong Luo , Fang Zhao , Jingze Yu , Yupeng Jia , Juan Wang , Xuepeng Ma

Knowledge distillation has been applied to image classification successfully. However, object detection is much more sophisticated and most knowledge distillation methods have failed on it. In this paper, we point out that in object…

计算机视觉与模式识别 · 计算机科学 2022-03-10 Zhendong Yang , Zhe Li , Xiaohu Jiang , Yuan Gong , Zehuan Yuan , Danpei Zhao , Chun Yuan

In this paper we propose a blind deconvolution method which applies to data perturbed by Poisson noise. The objective function is a generalized Kullback-Leibler divergence, depending on both the unknown object and unknown point spread…

天体物理仪器与方法 · 物理学 2013-11-25 M. Prato , A. La Camera , S. Bonettini , M. Bertero

Underwater vision suffers from severe effects due to selective attenuation and scattering when light propagates through water. Such degradation not only affects the quality of underwater images but limits the ability of vision tasks.…

计算机视觉与模式识别 · 计算机科学 2018-01-16 Chongyi Li , Jichang Guo , Chunle Guo

Remote sensing images are essential for many applications of the earth's sciences, but their quality can usually be degraded due to limitations in sensor technology and complex imaging environments. To address this, various remote sensing…

计算机视觉与模式识别 · 计算机科学 2024-02-22 Yujie Feng , Yin Yang , Xiaohong Fan , Zhengpeng Zhang , Jianping Zhang

The optics of any camera degrades the sharpness of photographs, which is a key visual quality criterion. This degradation is characterized by the point-spread function (PSF), which depends on the wavelengths of light and is variable across…

图像与视频处理 · 电气工程与系统科学 2022-08-02 Thomas Eboli , Jean-Michel Morel , Gabriele Facciolo

Optical imaging systems are inherently imperfect due to diffraction limits, lens manufacturing tolerances, assembly misalignment, and other physical constraints. In addition, unavoidable camera shake and object motion further introduce…

计算机视觉与模式识别 · 计算机科学 2025-11-17 Yanlong Yang , Guanxiong Luo

Knowledge distillation is a popular technique for transferring the knowledge from a large teacher model to a smaller student model by mimicking. However, distillation by directly aligning the feature maps between teacher and student may…

计算机视觉与模式识别 · 计算机科学 2023-03-27 Ziwei Liu , Yongtao Wang , Xiaojie Chu

Many deep learning based methods are designed to remove non-uniform (spatially variant) motion blur caused by object motion and camera shake without knowing the blur kernel. Some methods directly output the latent sharp image in one stage,…

计算机视觉与模式识别 · 计算机科学 2022-04-25 Dong Huo , Abbas Masoumzadeh , Yee-Hong Yang

Background: Magnetic field inhomogeneities generate important geometric distortions in reconstructed echo-planar images. Various procedures were proposed for correcting these distortions on brain images; yet, few neuroimaging studies…

图像与视频处理 · 电气工程与系统科学 2021-08-10 Haykel Snoussi , Julien Cohen-Adad , Olivier Commowick , Benoit Combes , Elise Bannier , Soizic Leguy , Anne Kerbrat , Christian Barillot , Emmanuel Caruyer

Synthetic aperture sonar (SAS) image resolution is constrained by waveform bandwidth and array geometry. Specifically, the waveform bandwidth determines a point spread function (PSF) that blurs the locations of point scatterers in the…

计算机视觉与模式识别 · 计算机科学 2021-12-17 Albert Reed , Thomas Blanford , Daniel C. Brown , Suren Jayasuriya