no code implementations • 29 Jul 2024 • William C. Yau, Weijian Zhang, Hashan Kavinga Weerasooriya, Stanley H. Chan

Depth estimation using a single-photon LiDAR is often solved by a matched filter.

no code implementations • 2 Jul 2024 • Weijian Zhang, Hashan K. Weerasooriya, Prateek Chennuri, Stanley H. Chan

In single-photon light detection and ranging (SP-LiDAR) systems, the histogram distortion due to hardware dead time fundamentally limits the precision of depth estimation.

no code implementations • CVPR 2024 • Vishal Purohit, Junjie Luo, Yiheng Chi, Qi Guo, Stanley H. Chan, Qiang Qiu

In this paper, we explore the possibility of generating a color image from a single binary frame of a single-photon camera.

no code implementations • 26 Mar 2024 • Stanley H. Chan

The goal of this tutorial is to discuss the essential ideas underlying the diffusion models.

no code implementations • CVPR 2024 • Stanley H. Chan, Hashan K. Weerasooriya, Weijian Zhang, Pamela Abshire, Istvan Gyongy, Robert K. Henderson

This presents a fundamental trade-off between the spatial resolution of the sensor array and the SNR received at each pixel.

1 code implementation • CVPR 2024 • Xingguang Zhang, Nicholas Chimitt, Yiheng Chi, Zhiyuan Mao, Stanley H. Chan

Building upon the intuitions of classical TM algorithms, we present the Deep Atmospheric TUrbulence Mitigation network (DATUM).

no code implementations • 4 Dec 2023 • Yash Sanghvi, Yiheng Chi, Stanley H. Chan

Blind deconvolution problems are severely ill-posed because neither the underlying signal nor the forward operator are not known exactly.

no code implementations • 6 Sep 2023 • Abhiram Gnanasambandam, Yash Sanghvi, Stanley H. Chan

Non-blind image deconvolution has been studied for several decades but most of the existing work focuses on blur instead of noise.

no code implementations • 21 Jul 2023 • Stanley H. Chan

This article introduces the concept of computational image formation (CIF).

1 code implementation • ICCV 2023 • Ajay Jaiswal, Xingguang Zhang, Stanley H. Chan, Zhangyang Wang

Although fast and physics-grounded simulation tools have been introduced to help the deep-learning models adapt to real-world turbulence conditions recently, the training of such models only relies on the synthetic data and ground truth pairs.

no code implementations • 30 Jun 2023 • Xiangyu Qu, Yiheng Chi, Stanley H. Chan

The advancement of new digital image sensors has enabled the design of exposure multiplexing schemes where a single image capture can have multiple exposures and conversion gains in an interlaced format, similar to that of a Bayer color filter array.

no code implementations • CVPR 2023 • Yiheng Chi, Xingguang Zhang, Stanley H. Chan

For HDR imaging in photon-limited situations, the dynamic range can be enormous and the noise within one exposure is spatially varying.

no code implementations • 29 Mar 2023 • Guan Zhe Hong, Yin Cui, Ariel Fuxman, Stanley H. Chan, Enming Luo

Furthermore, we perform comprehensive experiments using the label hierarchies of iNaturalist 2021 and observe that the following conditions, in addition to proper choice of label granularity, enable the transfer to work well in practice: 1) the pretraining dataset needs to have a meaningful label hierarchy, and 2) the pretraining and target label functions need to align well.

no code implementations • 10 Mar 2023 • Nicholas Chimitt, Xingguang Zhang, Yiheng Chi, Stanley H. Chan

A spatially varying blur kernel $h(\mathbf{x},\mathbf{u})$ is specified by an input coordinate $\mathbf{u} \in \mathbb{R}^2$ and an output coordinate $\mathbf{x} \in \mathbb{R}^2$.

1 code implementation • CVPR 2023 • Yash Sanghvi, Zhiyuan Mao, Stanley H. Chan

By modeling the blur kernel using a low-dimensional representation with the key points on the motion trajectory, we significantly reduce the search space and improve the regularity of the kernel estimation problem.

no code implementations • 13 Oct 2022 • Nicholas Chimitt, Xingguang Zhang, Zhiyuan Mao, Stanley H. Chan

We show that the cross-correlation of the Zernike modes has an insignificant contribution to the statistics of the random samples.

no code implementations • 19 Aug 2022 • Stanley H. Chan

In particular, it is theoretically found that the sensor can offer three benefits: (1) Low-light: One-bit QIS performs better at low-light because it has a low read noise, and its one-bit quantization can produce an error-free measurement.

1 code implementation • 31 Jul 2022 • Yash Sanghvi, Abhiram Gnanasambandam, Zhiyuan Mao, Stanley H. Chan

When the noise is strong, these networks fail to simultaneously deblur and denoise; (3) While iterative schemes are known to be robust in the classical frameworks, they are seldom considered in deep neural networks because it requires a differentiable non-blind solver.

1 code implementation • 20 Jul 2022 • Zhiyuan Mao, Ajay Jaiswal, Zhangyang Wang, Stanley H. Chan

Image restoration algorithms for atmospheric turbulence are known to be much more challenging to design than traditional ones such as blur or noise because the distortion caused by the turbulence is an entanglement of spatially varying blur, geometric distortion, and sensor noise.

no code implementations • 13 Jul 2022 • Stanley H. Chan

Imaging at a long distance often requires advanced image restoration algorithms to compensate for the distortions caused by atmospheric turbulence.

no code implementations • 13 Jul 2022 • Xingguang Zhang, Zhiyuan Mao, Nicholas Chimitt, Stanley H. Chan

While existing deep-learning-based methods have demonstrated promising results in specific testing conditions, they suffer from three limitations: (1) lack of generalization capability from synthetic training data to real turbulence data; (2) failure to scale, hence causing memory and speed challenges when extending the idea to a large number of frames; (3) lack of a fast and accurate simulator to generate data for training neural networks.

no code implementations • 11 Mar 2022 • Stanley H. Chan

An intriguing phenomenon is observed when the quanta exposure is at the unity and the threshold is $q = 0. 5$.

no code implementations • 10 Dec 2021 • Abhiram Gnanasambandam, Stanley H. Chan

New theoretical results are derived for image sensors of any bit-depth and full-well capacity.

no code implementations • 9 Nov 2021 • Xue Zhang, Gene Cheung, Jiahao Pang, Yash Sanghvi, Abhiram Gnanasambandam, Stanley H. Chan

Specifically, we model depth formation as a combined process of signal-dependent noise addition and non-uniform log-based quantization.

1 code implementation • 28 Oct 2021 • Yash Sanghvi, Abhiram Gnanasambandam, Stanley H. Chan

Image deblurring in photon-limited conditions is ubiquitous in a variety of low-light applications such as photography, microscopy, and astronomy.

no code implementations • 20 Aug 2021 • Xiangyu Qu, Stanley H. Chan

Adversarial attacks pose a substantial threat to computer vision system security, but the social media industry constantly faces another form of "adversarial attack" in which the hackers attempt to upload inappropriate images and fool the automated screening systems by adding artificial graphics patterns.

no code implementations • 13 Aug 2021 • Abhiram Gnanasambandam, Alex M. Sherman, Stanley H. Chan

The system consists of a low-cost projector, a camera, and a computer.

1 code implementation • ICCV 2021 • Zhiyuan Mao, Nicholas Chimitt, Stanley H. Chan

Fast and accurate simulation of imaging through atmospheric turbulence is essential for developing turbulence mitigation algorithms.

no code implementations • 30 Jun 2021 • Masatoshi Nagahama, Koki Yamada, Yuichi Tanaka, Stanley H. Chan, Yonina C. Eldar

We overcome two main challenges in existing graph signal restoration methods: 1) limited performance of convex optimization algorithms due to fixed parameters which are often determined manually.

no code implementations • 24 Jun 2021 • Chengxi Li, Stanley H. Chan, Yi-Ting Chen

Identification of high-risk driving situations is generally approached through collision risk estimation or accident pattern recognition.

no code implementations • CVPR 2021 • Guanzhe Hong, Zhiyuan Mao, Xiaojun Lin, Stanley H. Chan

Feature-based student-teacher learning, a training method that encourages the student's hidden features to mimic those of the teacher network, is empirically successful in transferring the knowledge from a pre-trained teacher network to the student network.

no code implementations • 6 Nov 2020 • Abhiram Gnanasambandam, Stanley H. Chan

We provide a complete theoretical characterization of the sensor in the context of HDR imaging, by proving the fundamental limits in the dynamic range that QIS can offer and the trade-offs with noise and speed.

no code implementations • 16 Jul 2020 • Yiheng Chi, Abhiram Gnanasambandam, Vladlen Koltun, Stanley H. Chan

QIS are single-photon image sensors with photon counting capabilities.

no code implementations • ECCV 2020 • Abhiram Gnanasambandam, Stanley H. Chan

In this paper, we present a new low-light image classification solution using Quanta Image Sensors (QIS).

no code implementations • ICML 2020 • Abhiram Gnansambandam, Stanley H. Chan

The de facto training protocol to achieve this goal is to train the estimator with noisy samples whose noise levels are uniformly distributed across the range of interest.

no code implementations • 23 Apr 2020 • Nicholas Chimitt, Stanley H. Chan

Simulating atmospheric turbulence is an essential task for evaluating turbulence mitigation algorithms and training learning-based methods.

no code implementations • 5 Mar 2020 • Chengxi Li, Stanley H. Chan, Yi-Ting Chen

We formulate the task as the cause-effect problem and present a novel two-stage risk object identification framework based on causal inference with the proposed object-level manipulable driving model.

no code implementations • 20 Sep 2019 • Chengxi Li, Yue Meng, Stanley H. Chan, Yi-Ting Chen

First, we decompose egocentric interactions into ego-thing and ego-stuff interaction, modeled by two GCNs.

no code implementations • 17 May 2019 • Nicholas Chimitt, Zhiyuan Mao, Guanzhe Hong, Stanley H. Chan

We demonstrate how a simple prior can outperform state-of-the-art blind deconvolution methods.

no code implementations • 23 Mar 2019 • Omar A. Elgendy, Stanley H. Chan

In this paper, we discuss how to design color filter arrays for QIS and other small pixels.

no code implementations • 31 Aug 2018 • Stanley H. Chan

The Plug-and-Play (PnP) ADMM algorithm is a powerful image restoration framework that allows advanced image denoising priors to be integrated into physical forward models to generate high quality image restoration results.

no code implementations • 24 Aug 2018 • Xiran Wang, Jason Juang, Stanley H. Chan

The fusion framework allows us to integrate the individual strengths of alpha matting, background subtraction and image denoising to produce an overall better estimate.

no code implementations • 17 Nov 2017 • Joon Hee Choi, Omar Elgendy, Stanley H. Chan

Given a set of image denoisers, each having a different denoising capability, is there a provably optimal way of combining these denoisers to produce an overall better result?

no code implementations • 24 May 2017 • Gregery T. Buzzard, Stanley H. Chan, Suhas Sreehari, Charles A. Bouman

We give examples to illustrate consensus equilibrium and the convergence properties of these algorithms and demonstrate this method on some toy problems and on a denoising example in which we use an array of convolutional neural network denoisers, none of which is tuned to match the noise level in a noisy image but which in consensus can achieve a better result than any of them individually.

no code implementations • 12 Apr 2017 • Omar A. Elgendy, Stanley H. Chan

Second, we show that around the oracle threshold there exists a set of thresholds that give asymptotically unbiased reconstructions.

no code implementations • 5 May 2016 • Stanley H. Chan, Xiran Wang, Omar A. Elgendy

We compare Plug-and-Play ADMM with state-of-the-art algorithms in each problem type, and demonstrate promising experimental results of the algorithm.

no code implementations • 1 Feb 2016 • Stanley H. Chan

Different from classical image priors which are defined before running the reconstruction algorithm, algorithm-induced priors are defined by the denoising procedure used to replace one of the two modules in the ADMM algorithm.

no code implementations • 19 Jan 2016 • Enming Luo, Stanley H. Chan, Truong Q. Nguyen

We propose an adaptive learning procedure to learn patch-based image priors for image denoising.

no code implementations • 1 Jan 2016 • Stanley H. Chan, Todd Zickler, Yue M. Lu

We show that Sinkhorn-Knopp is equivalent to an Expectation-Maximization (EM) algorithm of learning a Gaussian mixture model of the image patches.

no code implementations • 14 Jul 2014 • Lee-Kang Liu, Stanley H. Chan, Truong Q. Nguyen

Experimental results show that the proposed method produces high quality dense depth estimates, and is robust to noisy measurements.

no code implementations • 30 Jun 2014 • Enming Luo, Stanley H. Chan, Truong Q. Nguyen

First, we determine the basis function of the denoising filter by solving a group sparsity minimization problem.

no code implementations • 27 Dec 2013 • Stanley H. Chan, Todd Zickler, Yue M. Lu

In particular, our error probability bounds show that, at any given sampling ratio, the probability for MCNLM to have a large deviation from the original NLM solution decays exponentially as the size of the image or database grows.

1 code implementation • NeurIPS 2013 • Edoardo M. Airoldi, Thiago B. Costa, Stanley H. Chan

Non-parametric approaches for analyzing network data based on exchangeable graph models (ExGM) have recently gained interest.

Cannot find the paper you are looking for? You can
Submit a new open access paper.

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.