Related papers: Noise2Params: Unification and Parameter Determinat…
Recent deep learning-based image denoising methods have shown impressive performance; however, many lack the flexibility to adjust the denoising strength based on the noise levels, camera settings, and user preferences. In this paper, we…
Given 2D point correspondences between an image pair, inferring the camera motion is a fundamental issue in the computer vision community. The existing works generally set out from the epipolar constraint and estimate the essential matrix,…
Benchmarking models is a key factor for the rapid progress in machine learning (ML) research. Thus, further progress depends on improving benchmarking metrics. A standard metric to measure the behavioral alignment between ML models and…
Modeling imaging sensor noise is a fundamental problem for image processing and computer vision applications. While most previous works adopt statistical noise models, real-world noise is far more complicated and beyond what these models…
While deep learning offers powerful capabilities for scientific research, its application is often hindered by a lack of quantitative reliability. To address this, we introduce a probabilistic denoising framework that simultaneously…
Accurate calibration is crucial for using multiple cameras to triangulate the position of objects precisely. However, it is also a time-consuming process that needs to be repeated for every displacement of the cameras. The standard approach…
We propose a generic event camera calibration framework using image reconstruction. Instead of relying on blinking LED patterns or external screens, we show that neural-network-based image reconstruction is well suited for the task of…
Compared to conventional cameras, event cameras provide a high dynamic range and low latency, offering greater robustness to rapid motion and challenging lighting conditions. Although the potential of event cameras for visual place…
Event cameras offer high temporal resolution and power efficiency, making them well-suited for edge AI applications. However, their high event rates present challenges for data transmission and processing. Subsampling methods provide a…
Event cameras are novel bio-inspired sensors that measure per-pixel brightness differences asynchronously. Recovering brightness from events is appealing since the reconstructed images inherit the high dynamic range (HDR) and high-speed…
Event camera is a novel bio-inspired vision sensor that outputs event stream. In this paper, we propose a novel data fusion algorithm called EAS to fuse conventional intensity images with the event stream. The fusion result is applied to…
Like other experimental techniques, X-ray Photon Correlation Spectroscopy is subject to various kinds of noise. Random and correlated fluctuations and heterogeneities can be present in a two-time correlation function and obscure the…
Normalizing flows are a class of generative models that enable exact likelihood evaluation. While these models have already found various applications in particle physics, normalizing flows are not flexible enough to model many of the…
We present a technique for jointly denoising bursts of images taken from a handheld camera. In particular, we propose a convolutional neural network architecture for predicting spatially varying kernels that can both align and denoise…
In this work, we focus on using convolution neural networks (CNN) to perform object recognition on the event data. In object recognition, it is important for a neural network to be robust to the variations of the data during testing. For…
Event cameras triggered a paradigm shift in the computer vision community delineated by their asynchronous nature, low latency, and high dynamic range. Calibration of event cameras is always essential to account for the sensor intrinsic…
Image reconstruction methods based on deep neural networks have shown outstanding performance, equalling or exceeding the state-of-the-art results of conventional approaches, but often do not provide uncertainty information about the…
An event camera detects per-pixel intensity difference and produces asynchronous event stream with low latency, high dynamic range, and low power consumption. As a trade-off, the event camera has low spatial resolution. We propose an…
Recent studies indicate that deep neural networks degrade in generalization performance under noisy supervision. Existing methods focus on isolating clean subsets or correcting noisy labels, facing limitations such as high computational…
Automating the analysis of surveillance video footage is of great interest when urban environments or industrial sites are monitored by a large number of cameras. As anomalies are often context-specific, it is hard to predefine events of…