We propose a physics-based holographic network (PBHolo-Net) for three-dimensional imaging. due to the involvement of the wavefield propagation, the network is efficient, stable, and can perform more precise hologram r...
详细信息
This proceedings contains 170 papers. 3-dimageacquisition anddisplaytechnology have become critical for many applications, including virtual reality and augmented reality, medical and scientific visualization, def...
ISBN:
(纸本)9781943580156
This proceedings contains 170 papers. 3-dimageacquisition anddisplaytechnology have become critical for many applications, including virtual reality and augmented reality, medical and scientific visualization, defense, flight simulation and training, engineering design, and entertainment. This topical meeting aims to bring together researchers and engineers from a broad range of interdisciplinary fields to present their work in the science, technology, andapplications of non-holographic 3dimage collection anddisplay technologies. This meeting will cover research areas related to the acquisition, display, andapplications of (non-holographic) 3d information as well as the perception, human factors, and visual comfort of 3d information displays. Research related to scientific understanding of 3d information display andperception, technological innovation on 3dimageacquisition or display methods, and task-specific design andapplications of 3dacquisition or displaytechnology is of particular interest. Application areas of interest include but not limited to virtual reality, augmented reality, biomedicine, microscopy, endoscopy, healthcare, autonomous vehicle, wearable displays, and entertainment. The key terms of this proceedings include infrared gas spectroscopy, femtosecond laser pulses, intrapulse absorption spectroscopy, quartz-enhanced photoacoustic spectroscopy (QEPAS), agri-food industry, thermal radiation tomography, distributed integral imaging, autostereoscopic 3ddisplay, virtual reality, 3d integral microscopy.
We demonstrate a method to adaptively expand the dynamic range of phase imaging by separately measuring a sample's large and small phase distributions using the wavefront shaping in the dark-field configuration. &...
We propose broad taxonomy of pupil-steered systems and introduce an end-to-end optical model of a generalized pupil-steered system with a schematic eye. We explore the effects of various design parameters on retinal i...
详细信息
Generative models are gaining momentum in both academic and industrial applicationsdriven by the availability of large-scale datasets, especially in tasks involving image-to-image Translation. Meanwhile, poor human p...
详细信息
ISBN:
(数字)9798350377705
ISBN:
(纸本)9798350377712
Generative models are gaining momentum in both academic and industrial applicationsdriven by the availability of large-scale datasets, especially in tasks involving image-to-image Translation. Meanwhile, poor human perception of nighttime environment has led to a demand for translation from night-vision infrared to day-vision RGB images. However, collecting such cross-modal training data at the same time is impossible due to the thermal imaging properties of infrared cameras, the challenge lies in constructing image pairs during the day and at night respectively, where the requirement for data alignment poses significant difficulties. In this paper, we propose a Pixel-level alignedimage Pair generation framework PIP to explore efficient colorization of high-resolution infraredimages. Specifically, we first construct a 3d high-precision point cloud map for the purpose of establishing the correlation between day and night scenes. Corresponding point clouds of modal images are collected simultaneously during data acquisition to obtain image sensor poses by Global Matching with the map, which allows us to calculate the transformation relationship from infrared to RGB image coordinate systems based on the sensor parameters anddepth information of the map. Leveraging the relationship, the pixel values of RGB image is projected onto the infraredimage followed by optimization as the coloredimage. Accordingly, we present a dataset NUdT-PIP, the first of its kind containing large-scale pixel-level aligned cross-time infrared-RGB image pairs of complicated real road scenes. Experimental results demonstrate the reliability and strong applicability of our dataset in image-to-image Translation. Our code will be released at https://***/wjjjjyourFA/NUdT-PIP.
To obtain high spatial resolution and angular resolution in integral photography simultaneously, we investigated the use of single-pixel imaging for acquiring dense parallax images. We found that a parallax image in a...
详细信息
Learning-based method restores image information degraded by amplitude structure in the pupil plane. The fill-factor of aperture pattern determines the performance limit in the learning-based method. Experiments demon...
详细信息
We propose a digital holographic reconstruction algorithm based on deep learning with imperfect data. Experiments prove that this algorithm can reduce the impact of uncontrollable environmental factors on the dataset ...
详细信息
The inspection of tools in sheet-bulk metal forming poses special challenges for metrology. By using a fiber-optic fringe projection system, filigree, internal structures can be measured and the wear can be described ...
详细信息
暂无评论