Related papers: Microlens array grid estimation, light field decod…
Recent work has focused on generating synthetic imagery to increase the size and variability of training data for learning visual tasks in urban scenes. This includes increasing the occurrence of occlusions or varying environmental and…
Multiple optical scattering occurs when light propagates in a non-uniform medium. During the multiple scattering, images were distorted and the spatial information they carried became scrambled. However, the image information is not lost…
High dynamic range (HDR) imaging involves capturing a series of frames of the same scene, each with different exposure settings, to broaden the dynamic range of light. This can be achieved through burst capturing or using staggered HDR…
Photorealistic simulation plays a crucial role in applications such as autonomous driving, where advances in neural radiance fields (NeRFs) may allow better scalability through the automatic creation of digital 3D assets. However,…
We propose a neural inverse rendering approach that jointly reconstructs geometry, spatially varying reflectance, and lighting conditions from multi-view images captured under varying directional lighting. Unlike prior multi-view…
Mask-based lensless cameras can be flat, thin, and light-weight, which makes them suitable for novel designs of computational imaging systems with large surface areas and arbitrary shapes. Despite recent progress in lensless cameras, the…
Autonomous driving perception systems are particularly vulnerable in foggy conditions, where light scattering reduces contrast and obscures fine details critical for safe operation. While numerous defogging methods exist, from handcrafted…
Although recent deep learning-based calibration methods can predict extrinsic and intrinsic camera parameters from a single image, their generalization remains limited by the number and distribution of training data samples. The huge…
In low-light conditions, a conventional camera imaging pipeline produces sub-optimal images that are usually dark and noisy due to a low photon count and low signal-to-noise ratio (SNR). We present a data-driven approach that learns the…
We introduce a camera pipeline for rendering visually pleasing photographs in low light conditions, as part of the NTIRE2022 Night Photography Rendering challenge. Given the nature of the task, where the objective is verbally defined by an…
In this work we propose an alternative formulation to the problem of ground reflectivity grid based localization involving laser scanned data from multiple LIDARs mounted on autonomous vehicles. The driving idea of our localization…
In this paper, we run two methods of explanation, namely LIME and Grad-CAM, on a convolutional neural network trained to label images with the LEGO bricks that are visible in them. We evaluate them on two criteria, the improvement of the…
Compound eyes found in insects provide intriguing sources of biological inspiration for miniaturized imaging systems. Inspired by such insect eye structures, we demonstrate an ultrathin arrayed camera enabled by a flat multilevel…
The recently developed and publicly available synthetic image generation methods and services make it possible to create extremely realistic imagery on demand, raising great risks for the integrity and safety of online information.…
In this work, we revisit the problem of interference fringe patterns in CCD chips occurring in near-infrared bands due to multiple light reflections within the chip. We briefly discuss the traditional approaches that were developed to…
Three methods for handling beam-beam effects in luminosity measurement at ILC are tested and evaluated in this work. The first method represents an optimization of the LEP-type asymmetric selection cuts that reduce the counting biases. The…
We propose a novel grayness index for finding gray pixels and demonstrate its effectiveness and efficiency in illumination estimation. The grayness index, GI in short, is derived using the Dichromatic Reflection Model and is learning-free.…
Thermal infrared cameras are increasingly being used in various applications such as robot vision, industrial inspection and medical imaging, thanks to their improved resolution and portability. However, the performance of traditional…
In Light Field compression, graph-based coding is powerful to exploit signal redundancy along irregular shapes and obtains good energy compaction. However, apart from high time complexity to process high dimensional graphs, their graph…
Images acquired by computer vision systems under low light conditions have multiple characteristics like high noise, lousy illumination, reflectance, and bad contrast, which make object detection tasks difficult. Much work has been done to…