Shree Nayar

Probably the best CS class I've ever taken. The lectures are extremely well-organized and full of visuals (plus, all the lectures are on YouTube!). Shree is an excellent lecturer and extraordinarily knowledgeable about not just vision, but graphics and AI in general. All the TAs are PhD students too so they really know their stuff. The homeworks were clear and reasonable but definitely challenging. Shree's style probably doesn't suit everybody. He goes pretty quickly through the material and tends to gloss over the math proofs. Also, he can be a bit intimidating since he's so accomplished and has a very dry sense of humor. I happened to vibe with all that because I'm really into computer vision, but if you aren't, the class might feel unnecessarily intense.

Well-organized class, Shree is cool and the topics are also interesting! This class does require some mathematical background and MatLab is annoying, but I think it's nice that Shree focuses on the concepts instead of the derivations in lectures. Would recommend!

CV with Prof. Nayar was a very good course. Prof. Nayar is super clear when explaining confusing topics, and he does so in a very concise way. His lectures have good depth and very large breadth -- by the end of the course I was surprised by the sheer amount of material that we learned. It was intimidating to study hundreds of slides for the final but after finishing the final it was rather gratifying to look back on the amount of material learned. The homeworks in general were very doable if spaced out evenly throughout the week. The first few homeworks were harder IMO because I wasn't used to MATLAB. But if the concepts make sense in class, the implementation should not be too difficult. The exams were also not too difficult, no notes or calculators allowed so you can imagine that it can't be very math-intensive. It was purely conceptual with a few math questions or recalling formulas here and there. Overall studying for them was more painful than taking them.

This is a super interesting class for those interested in learning how everyday image processing algorithms work. It provides a comprehensive survey of vision algorithms from the ground up: from lenses and sensors (hi, photographers!) to basic 2d stuff to algorithms that reconstruct depth from multiple points of view to neural nets in the last lecture. With Deep Learning(TM) being billed as the one algorithm to rule them all, it was interesting to see how many simple, interpretable models have good performance without less complexity and faster run times. Prof. Nayar's lectures are fun and engaging -- he applies his sense of humor and PowerPoint animation skillz to make CV easier to learn. You don't need any books since the slides have all the formulas, derivations, and examples you need to do homework. (I wish we could get electronic copies of the slides, since it's in a computer **vision** class, sometimes you need to see the colors in a diagram/picture for things to make sense. And videos in the slides are completely lost in translation. But it doesn't sound like he plans on making the change any time soon.) I really dislike how the teaching staff handled office hours. It felt like every other week, they were held at a different time and place. As a TA for a similarly large class, I know that it's hard to teach and study at the same time. But there is a minimum quality of s…

Material was hard to understand. Easy material was covered until the registration deadline. Once the students are registered the material becomes hard. There is a group of shree's favourite students who will get good grades.

Vision was the most rewarding class by far. Prof. Nayar is funny, smart and makes lectures very interesting. He has an answer to all of your questions. He likes discipline, mind you, but is not that fanatic about it. You cannot miss any of his lectures as the slides will stare at you when you prepare for the midterm or final. You get printed slides so you just need to take down additional notes (if any). In Spring 2014, he tried a lot of new material and so the overall workload increased exponentially after midterm. He also took feedback post midterm and in the last class to update the class materials. There were review classes in the lecture before the tests which were quite helpful, if at all you started preparing! It helps to have a study group as making sense of each slide takes up a lot of time although everything seems like a breeze during the class. TA's were very helpful. Thomas was a little picky in giving points but used to explain important concepts easily. You won't understand where exactly you lost points but they do indicate the relevant challenge number. Though programming in MATLAB seems easy, debugging is a headache. Make sure you proceed step by step. Just a tip: avoid built in functions unless you are completely sure of what they return. Getting a working solution was not enough to secure full points. You need to provide a 'smart' solution. I was taking Comp…

Possibly the most difficult class in the CS department. Professor Nayar is also possibly the best professor in the department. Great lecturing style, clearly super intelligent, and genuinely does his best to make sure we understand the material. That said, we cover a lot of material in this class, and preparing for the exams is hellish. The exams generally cover some of the easier concepts in the class, but it's also easy to lose points on proofs and there are also quite a few questions where you just have to remember a specific detail or some model which you otherwise can't derive on the spot. No way around some of this stuff unless you put a lot of time into memorization of the material. Homeworks are great! They're done in MATLAB now (I think he said they were in C until a couple years ago), so they're constantly evolving - Nayar admits as much himself, especially that he put a lot more material in the class and on the HWs this semester. This is not a class you want to procrastinate on (nor can you afford to). If you start the night before, you may stay up all night, and just not be able to finish due to the difficulty of some of these homeworks. You should start at least a few days before so you have time to consult the TAs because you will inevitably run into MATLAB bugs, amongst other issues with understanding the Vision algorithms themselves. You should probably attend…

I can see why people like him, but the material is extremely difficult, beware! He makes lectures interesting and funny, but he glosses over important concepts and you never feel like you understand anything until the difficult midterm and final come around. You'll have to study your ass off just to pass. The programs are a lot fun. They take some thinking, but overall they're well-structured and very useful. The theory questions on homeworks are impossible. What's very unfair about this course though is that you can't recover from a single bad grade on anything (hw, midterm, or final). A single mess-up will glare at you on your final grade, not to mention that the curve is very small. The difference between letter grades is very slight, only a few points will be bump you up from a B+ to an A (notice there's no A-). But only a few points will drop you down from a B+ to a B-. Unfortunately he grades strictly by the numbers, and no amount of asking questions in class, going to office hours, or demonstrating grade improvement throughout the semester will factor into your final grade. He has no problem setting the average to a low grade.

Professor Shree Nayar is the best professor I met at Columbia. The course is very informative. He gives great lecture with a sense of humor. The TA are very helpful. The assignments are not that hard but yet gives you a sense of how things really work. I highly recommend this course to anybody who has interest in vision/graphics. It's a must for students in vision/graphics track. Highly recommended.

Professor Nayar is tied for my favorite professor. The main reason I believe he is so good is because he conveys material in an extremely concise, understandable and well-spoken manner and really knows the subject inside- out. He is also very approachable in person and makes an effort to know students on some basic level. The only thing that was a little weird about the vision class was the lack of math -- it was all in the slides but there is essentially no math in the entire class, which is in sharp contrast to the textbook. In addition, the first homework is pretty ridiculous in many ways and shouldn't be considered as a measure of the class' overall worth. Programming assignments are engaging, and exams are very fair. Prof. Nayar makes use of the entire spectrum of scores on exams, and I feel gives proper questions to let those who understand subjects thoroughly to stand out. The one complaint about them is that he does not even give a format for the exam, let alone sample questions -- this was very nerve-wracking for me personally but it ended up OK in the end.