262 citations · 888 across the 45 of their papers we have counts for
51 papers
Why Fine-grained Labels in Pretraining Benefit Generalization?
Guan Zhe Hong, Yin Cui, Ariel Fuxman +2
Recent studies show that pretraining a deep neural network with fine-grained labeled data, followed by fine-tuning on coarse-labeled data for downstream tasks, often yields better…
Physics-Driven Turbulence Image Restoration with Stochastic Refinement
Ajay Jaiswal, Xingguang Zhang, Stanley H. Chan +1
Image distortion by atmospheric turbulence is a stochastic degradation, which is a critical problem in long-range optical imaging systems. A number of research has been conducted d…
Computational Image Formation: Simulators in the Deep Learning Era
Stanley H. Chan
At the pinnacle of computational imaging is the co-optimization of camera and algorithm. This, however, is not the only form of computational imaging. In problems such as imaging t…
Spatially Varying Exposure with 2-by-2 Multiplexing: Optimality and Universality
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 i…
Anisoplanatic Optical Turbulence Simulation for Near-Continuous Profiles without Wave Propagation
Nicholas Chimitt, Stanley H. Chan
For the simulation of anisoplanatic optical turbulence, split-step propagation is the gold standard. Within the context of the degradations being limited to phase distortions, one…
HDR Imaging with Spatially Varying Signal-to-Noise Ratios
Yiheng Chi, Xingguang Zhang, Stanley H. Chan
While today's high dynamic range (HDR) image fusion algorithms are capable of blending multiple exposures, the acquisition is often controlled so that the dynamic range within one…
Structured Kernel Estimation for Photon-Limited Deconvolution
Yash Sanghvi, Zhiyuan Mao, Stanley H. Chan
Images taken in a low light condition with the presence of camera shake suffer from motion blur and photon shot noise. While state-of-the-art image restoration networks show promis…
Towards Understanding the Effect of Pretraining Label Granularity
Guan Zhe Hong, Yin Cui, Ariel Fuxman +2
In this paper, we study how the granularity of pretraining labels affects the generalization of deep neural networks in image classification tasks. We focus on the "fine-to-coarse"…
Scattering and Gathering for Spatially Varying Blurs
Nicholas Chimitt, Xingguang Zhang, Yiheng Chi +1
A spatially varying blur kernel is specified by an input coordinate and an output coordinate .…
Real-Time Dense Field Phase-to-Space Simulation of Imaging through Atmospheric Turbulence
Nicholas Chimitt, Xingguang Zhang, Zhiyuan Mao +1
Numerical simulation of atmospheric turbulence is one of the biggest bottlenecks in developing computational techniques for solving the inverse problem in long-range imaging. The c…
What Does a One-Bit Quanta Image Sensor Offer?
Stanley H. Chan
The one-bit quanta image sensor (QIS) is a photon-counting device that captures image intensities using binary bits. Assuming that the analog voltage generated at the floating diff…
Tilt-then-Blur or Blur-then-Tilt? Clarifying the Atmospheric Turbulence Model
Stanley H. Chan
Imaging at a long distance often requires advanced image restoration algorithms to compensate for the distortions caused by atmospheric turbulence. However, unlike many standard re…
Photon-Limited Blind Deconvolution using Unsupervised Iterative Kernel Estimation
Yash Sanghvi, Abhiram Gnanasambandam, Zhiyuan Mao +1
Blind deconvolution is a challenging problem, but in low-light it is even more difficult. Existing algorithms, both classical and deep-learning based, are not designed for this con…
Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A New Physics-Inspired Transformer Model
Zhiyuan Mao, Ajay Jaiswal, Zhangyang Wang +1
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…
Imaging through the Atmosphere using Turbulence Mitigation Transformer
Xingguang Zhang, Zhiyuan Mao, Nicholas Chimitt +1
Restoring images distorted by atmospheric turbulence is a ubiquitous problem in long-range imaging applications. While existing deep-learning-based methods have demonstrated promis…
On the Insensitivity of Bit Density to Read Noise in One-bit Quanta Image Sensors
Stanley H. Chan
The one-bit quanta image sensor is a photon-counting device that produces binary measurements where each bit represents the presence or absence of a photon. In the presence of read…
Exposure-Referred Signal-to-Noise Ratio for Digital Image Sensors
Abhiram Gnanasambandam, Stanley H. Chan
The signal-to-noise ratio (SNR) is a fundamental tool to measure the performance of an image sensor. However, confusions sometimes arise between the two types of SNRs. The first on…
Graph-Based Depth Denoising & Dequantization for Point Cloud Enhancement
Xue Zhang, Gene Cheung, Jiahao Pang +3
A 3D point cloud is typically constructed from depth measurements acquired by sensors at one or more viewpoints. The measurements suffer from both quantization and noise corruption…
Photon Limited Non-Blind Deblurring Using Algorithm Unrolling
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. However, the presence of photon s…
Detecting and Segmenting Adversarial Graphics Patterns from Images
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 h…
Accelerating Atmospheric Turbulence Simulation via Learned Phase-to-Space Transform
Zhiyuan Mao, Nicholas Chimitt, Stanley H. Chan
Fast and accurate simulation of imaging through atmospheric turbulence is essential for developing turbulence mitigation algorithms. Recognizing the limitations of previous approac…
Optical Adversarial Attack
Abhiram Gnanasambandam, Alex M. Sherman, Stanley H. Chan
We introduce OPtical ADversarial attack (OPAD). OPAD is an adversarial attack in the physical space aiming to fool image classifiers without physically touching the objects (e.g.,…
Graph Signal Restoration Using Nested Deep Algorithm Unrolling
Masatoshi Nagahama, Koki Yamada, Yuichi Tanaka +2
Graph signal processing is a ubiquitous task in many applications such as sensor, social, transportation and brain networks, point cloud processing, and graph neural networks. Ofte…
DROID: Driver-centric Risk Object Identification
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. In this work, we approach the problem from…