Marc Levoy - Lectures on Digital Photography - Lecture 1 (21mar16).mp4
Marc Levoy5 HN recommenders · recommended in 5 months, 2019-2026
512K views · 10 years ago · lecture · evergreen
The first lecture in an 18-part series on digital photography from Marc Levoy's Stanford CS 178 course, recorded at Google in 2016. The series covers how digital cameras work and computational photography, with slides and assignments available on the course site.
HN recommends it as a free, serious introduction to digital and computational photography from a professor who helped build the early Pixel cameras.
57:57Lecture 1 | Introduction to Convolutional Neural Networks for Visual Recognition
Stanford University School of Engineering
2.9M views • 9 years ago
1:19:08CS231n Winter 2016: Lecture1: Introduction and Historical Context
Andrej Karpathy
462K views • 10 years ago
1:11:41Lecture 1 | Natural Language Processing with Deep Learning
Stanford University School of Engineering
820K views • 9 years ago
5:10Dual Photography
mm648230
24K views • 17 years ago
11:47!!Con 2017: HDR Photography in Microsoft Excel?! by Kevin Chen
Confreaks
119K views • 9 years ago
1:20:33Lecture 1 | Convex Optimization I (Stanford)
Stanford
753K views • 18 years ago
1:22:56Practical Deep Learning for Coders: Lesson 1
Jeremy Howard
610K views • 4 years ago
1:01:51Lecture 1: Introduction to Information Theory
Jakob Foerster
411K views • 12 years ago
1:08:40Lecture 1 | Machine Learning (Stanford)
Stanford
2.7M views • 18 years ago
11:02Imaging at a trillion frames per second | Ramesh Raskar
TED
3.2M views • 14 years ago
17:26Lecture 1 | Programming Paradigms (Stanford)
Stanford
1.2M views • 18 years ago
1:22:38CS480/680 Lecture 19: Attention and Transformer Networks
Pascal Poupart
374K views • 7 years ago
49:47Lecture 1 | Programming Methodology (Stanford)
Stanford
2.6M views • 18 years ago
1:12:56Lecture 1A: Overview and Introduction to Lisp
MIT OpenCourseWare
420K views • 7 years ago
25:52Halide Talk
Andrew Adams
53K views • 12 years ago
4:17AI Learns Noise Filtering For Photorealistic Videos | Two Minute Papers #215
Two Minute Papers
65K views • 8 years ago
3:21ProFORMA: Probabilistic Feature-based On-line Rapid Model Acquisition
QiPanComputerVision
571K views • 17 years ago
41:07KEYNOTE / Robert Erdmann
PyCon US
24K views • 5 years ago
2:47Visualizing video at the speed of light — one trillion frames per second
Massachusetts Institute of Technology (MIT)
12M views • 14 years ago
1:21:28Lecture 01 - The Learning Problem
caltech
1.5M views • 14 years ago
5 comments from Hacker News
To expand on the HDR example: There’s this interesting lecture series about computational photography by Marc Levoy, who worked on the earlier Pixel cameras: ▶ this video From what I remember, the core thesis is “take a lot of pictures and take the best parts”, which works for a surprising number of cases.
I did my PhD in Atomic, Molecular, and Optical (AMO) physics, and despite "optical" being part of that I realized midway that I didn't know enough about how regular cameras worked! It didn't take very long to learn, and it turned out to be extremely important in the work I did during the early days at Waymo and later at Motional. I wanted to pass along this fun video from several years ago that discusses HDR: link . It's short and fun, I recommend it to all HN readers. Separately, if you want a more serious introduction to digital photography, I recommend the lectures by Marc Levoy from his Stanford course: ▶ this video . I believe he runs his own group at Adobe now after leading a successful effort at Google making their pixel cameras the best in the industry for a couple of years. (And then everyone more-or-less caught up, just like with most tech improvements in the history of smartphones).
Marc Levoy's Lectures on Digital Photography: ▶ this video >This is one of 18 videos representing lectures on digital photography, from a version of my Stanford course CS 178 that was recorded at Google in Spring 2016.
> No google pixel / iOS quality level HDR & night sight modes Marc Levoy (the brains behind Google's amazing Computational Photography technology), said that he had gone to the Camera companies before and they rejected his proposals. Camera companies were too afraid that someone was going to take a photo, and it would end up looking bad, and result in people returning their camera. Source: Somewhere in this excellent course shared by Google: ▶ this video
The star tracking feature of the astrophotography mode definitely has me interested. I'm disappointed to see the continued lack of battery capacity on the smaller phone though. While I'd love a larger battery, I'm one of the unfortunate ones whose small hands can already barely reach across my Pixel 2's phone screen -- much less the top section. I'm also incredibly excited about the face unlocking feature -- I owned a Pixel Xs for about a week before returning it, and face unlock was my absolute favorite feature. It's very seamless especially compared to fingerprint unlock. As an aside, Marc Levoy, who spoke at the Google event today is a Professor Emeritus at Stanford, and has a great series titled "Lectures on Digital Photography" available for free on Youtube: ▶ this video