SCIEN Talk

Light develops computational imaging technologies that utilize heterogenous constellations of small cameras to create sophisticated imaging effects. This enables the company to provide hardware solutions that are compact – they can easily fit into a cell phone, or a similar small form factor. In this talk, I will review the recent progress of computational imaging research done at the company.

Photonics has always been the technology of the future. Light is faster, can multiplex etc. have all been "good" arguments for several decades and the ushering in of optical computing has perpetually been just a few years away. However, over the last decade, with the advent of micro-and nanofabrication techniques and phenomenal advances in photonics, that era seems to have finally arrived. The ability to create integrated optical circuits on a chip is near. But (and yes, there's always a but) you need "functional" materials that can be used to control and manipulate this flow of information. In electronics, doping silicon results in one of the most versatile functional materials ever employed by humanity. And that can used to efficiently route electrical signals. How do you do that optically? I hope to convince you that whatever route photonics takes, a class of materials known as phase change materials, will play a key role in its commercialization. These materials can be addressed electrically, and whilst this can be used to control optical signals on photonic circuits this can also be used to create displays and smart windows. In this talk, I hope to give a whistle-stop tour of these applications of these materials with a view towards their near-term applications in displays, and their longer-term potential ranging from integrated photonic memories to machine-learning hardware components.

Active 3D imaging systems, such as LIDAR, are becoming increasingly prevalent for applications in autonomous vehicle navigation, remote sensing, human-computer interaction, and more. These imaging systems capture distance by directly measuring the time it takes for short pulses of light to travel to a point and return. With emerging sensor technology we can detect down to single arriving photons and identify their arrival at picosecond timescales, enabling new and exciting imaging modalities. In this talk, I discuss trillion-frame-per-second imaging, efficient depth imaging with sparse photon detections, and imaging objects hidden from direct line of sight.

3D Computer Vision (3D Vision) techniques have been the key solutions to various scene perception problems such as depth from image(s), camera/object pose estimation, localization and 3D reconstruction of a scene. These solutions are the major part of many AI applications including AR/VR, autonomous driving and robotics. In this talk, I will first review several categories of 3D Vision problems and their challenges. Given the category of static scene perception, I will introduce several learning-based depth estimation methods such as PlaneRCNN, Neural RGBD, and camera pose estimation methods including MapNet as well as few registration algorithms deployed in NVIDIA's products. I will then introduce more challenging real world scenarios where scenes contain non-stationary rigid changes, non-rigid motions, or varying appearance due to the reflectance and lighting changes, which can cause scene reconstruction to fail due to the view dependent properties. I will discuss several solutions to these problems and conclude by summarizing the future directions for 3D Vision research that are being conducted by NVIDIA's learning and perception research (LPR) team.

Cancer is a surgically treated disease; almost 80% of early stage solid tumors undergo surgery at some point in their treatment course. The biggest gap in quality remains the high rate of tumor-positive margins in surgical resections. The biggest barrier is that only a limited amount of the tissue can be sampled for frozen section analysis (< 5%). The biggest challenge is to develop equipment to direct frozen section analysis to the most area on the specimen most likely to contain a positive margin. To this end, we developed intraoperative devices to leverage molecular imaging during and immediately after cancer resections.

This talk will present the methods and procedures used to produce the first results from the Event Horizon Telescope. It is theorized that a black hole will leave a "shadow" on a background of hot gas. Taking a picture of this black hole shadow could help to address a number of important scientific questions, both on the nature of black holes and the validity of general relativity. Unfortunately, due to its small size, traditional imaging approaches require an Earth-sized radio telescope. In this talk, I discuss techniques we have developed to photograph a black hole using the Event Horizon Telescope, a network of telescopes scattered across the globe. Imaging a black hole's structure with this computational telescope requires us to reconstruct images from sparse measurements, heavily corrupted by atmospheric error.

Scientific researchers now utilize advanced microscopes to collect very large volumes of image data. These volumes often contain morphologically complex structures that can be difficulty to comprehend on a 2D monitor, even with 3D projection. syGlass is a software stack designed specifically for the visualization, exploration, and annotation of very large image volumes in virtual reality. This technology provides crucial advantages to exploring 3D volumetric data by correctly leveraging neurological processes and pipelines in the visual cortex, reducing cognitive load and search times, while increasing insight and annotation accuracy. The talk will provide a brief overview of new microscope technology, a description of the syGlass stack and product, some real use-cases from various labs around the world, and conclude with predictions and plans for the future of scientific communication.

For the vast majority of people in the world, the best camera they have ever owned is in their current cell phone. Sales of phone camera modules approached $30 billion in 2018, almost three times the sales of all lasers, and will soon exceed four times the sales of all lasers. This is one of the most ubiquitous and successful optical devices ever. Fundamental laws of physics limit the performance of smartphone cameras, and these laws act against the marketing-driven aspiration for thinner and thinner camera modules. I shall show that the single most important optical parameter is the lens diameter D.

Mobile photography has been transformed by software. While sensors and lens design have improved over time, the mobile phone industry relies increasingly on software to mitigate physical limits and the constraints imposed by industrial design. In this talk, I'll describe the HDR+ system for burst photography, comprising robust and efficient algorithms for capturing, fusing, and processing multiple images into a single higher-quality result. HDR+ is core imaging technology for Google's Pixel phones - it's used in all camera modes and powers millions of photos per day. I'll give a brief history of HDR+ starting from Google Glass (2013), present key algorithms from the HDR+ system, then describe the new features that enable the recently released Night Sight mode.

Neural networks have surpassed the performance of virtually any traditional computer vision algorithm thanks to their ability to learn priors directly from the data. The common encoder/decoder with skip connections architecture, for instance, has been successfully employed in a number of tasks, from optical flow estimation, to image deblurring, image denoising, and even higher level tasks, such as image-to-image translation.

To improve the results further, one must leverage the constraints of the specific problem at hand, in particular when the domain is fairly well understood, such as the case of computational imaging.

In this talk I will describe a few of my recent projects that build on this observation, ranging from reflection removal, to novel view synthesis, and deblurring.