Apr 01, 2018
Outstanding Course! I could always count on Prof.Jianbo to crunch some of the most complex and confusing parts of the course into a much easier understandable language.
Jan 01, 2019
This is quite challenging course. So far, this is the course with the largest amount of material, I wish the class will be split into two courses.
By Mohammad H•
Jul 10, 2019
very useful course. However it needs some supplementary materials in math. also more solved examples.
Nov 06, 2016
very informative. the course is very demanding, due to very long lectures it is hard to stay in pace.
By Jesus F•
Oct 20, 2016
Good course, but assignmets are too long, difficult and with no much help. Workload is overpassed
By Xiaotao G•
Dec 16, 2018
It is hard compared to previous courses and need more time on it. But quite helpful!
By Rahul D•
Mar 30, 2020
I was expecting Some implementation of the SFM pipeline from OpenCV or OpenMVG.
By Mike Z•
Oct 10, 2018
Really good topic but the material can be improved a lot more.
And it's free !
By Shubham W•
Aug 13, 2017
Excellent course!! Especially Bundle Adjustment was covered in good details.
By Ricardo A R•
Feb 14, 2019
Need more videos for final weeks, hard to follow last week of the course
By Daniel C•
Dec 23, 2018
To put it simply: Shi's content is good and Danniilidis' content is bad.
By Aman B•
Jan 29, 2019
It was interesting, but damn the lectures are never ending.
Oct 27, 2017
a bit difficult to understand, anyway,finally passed!
By Ákos G•
Sep 13, 2020
Good course, but the video subtitles are garbage.
By xiao z•
May 03, 2020
need specific feed backs for those quizzes!!!
By li q•
Aug 10, 2016
The lecture notes should be better organized.
Sep 22, 2020
a little difficult for me,but learn a lot!
By Hussain M A•
Oct 01, 2019
Hard course but lots of good insight.
By Martin X•
Oct 23, 2016
The courses are good and helpful.
By Ali M H•
Oct 16, 2018
Thank you Professors !
Feb 18, 2017
By Fredo P C•
Feb 03, 2019
By Daniel S•
May 20, 2017
This course could use some help. It's a very interesting and important topic and is also difficult, but it could be explained better and the tie in between the lecture videos, quizzes and homework assignments could also be better. Some of the quiz questions are not answerable from reviewing the lecture notes and require outside knowledge of linear algebra and rotation mathematics. The assignments should also be better defined and set up so that there is incremental feedback available for the intermediate steps. For example, the last week's assignment has 5 steps, each of which requires a Matlab function to be written. In many online courses, there are "correct" intermediate results given so that each step can be verified before proceeding to the next step. In this assignment, there is not much feedback until you get to the third or fourth step and even then it's not the best. I had an error in one of the functions, but the problem feedback (photo comparisons) showed it as being OK until I submitted it for grading. It's important, since there's no instructor feedback , to provide some means of checking if you're doing things correctly.Some of the terminology used would be more clear if it was standardized; sometimes coordinates are x and y, sometimes u and v, there's also u1, u2, u3 and things like X = [x,y,z,w] and x = [u,v,w]. Its often quite difficult to know what's being referred to it's called x. I did learn a lot from this course, but it could have been a lot easier.
By Rishabh B•
Jun 10, 2016
The course is a very good overall description of the Perception field. The part I really liked is that there was no haste or a concept just superficially discussed - lectures are long and detailed. The presentation of lectures especially from Prof. Jianbo Shi are excellent - to represent Matrices in colours and give a intuitive sense of every formula(especially the Jacobians and treating the image blending process as painting) .
The bad part of this course is that pronunciations of faculties could be a little unclear and hence a very good transcript is required - which in this course is not upto the mark. There were few mistakes on the slides and should be rectified atleast in the pdf of the slides. What this means is that we have to go through some frustration while watching the video first time which gradually improves on second or third view. Also, there is absolutely no participation of teaching staff. A good content should be supplemented with assistance to further enhance learning experience. Few doubts because of this remains unclear and I wish I could have got this sorted in this class.
By carlos r l•
May 14, 2016
I dont like how this course was presented. The professors are good but the way how they present the course is extremely inefficient. I mean, because the instructor only speaks moving hands from one side to other, it was very difficult to visualize what and where the instructor was referencing to. Eg. a figure with 3 formulas and many variables there was no way to know in what alpha variable in formulas the instructor was talking about, once all formulas had the alpha variable. Also, when trying to describe a 3D environment only moving hands, its quite impossible to determine what and where the instructor is. One suggestion to try to minimize this problem would be try to use a lase pointer or a stick or a pen or something similar to help the student to now where the instructor exactly is. One example of good presentation is the course of ML from Andrew Ng where he writes all the things while speaking which facilitates the student to follow the sequence. Hope this can help.
By Timothy M•
Jul 09, 2017
some interesting material. The Slides for week 2 and 4 are terrible, too condensed with very little explanation on difficult topics. The Homeworks are pretty interesting, the assignments for week 3 and 4 complement eachother very well. the week 2 Kalman filter assignment didn't seem to work. I submitted something in frustration and was very surprised that it was accepted.
By Vladimir K•
Jun 15, 2016
I really loved the dense collection of relevant information, this course is a great introduction to computer vision-related algorithms.
Unfortunately the lecture videos are poorly edited and subtitles are inaccurate, however the slides are quite good and verbose enough to understand every topic.
Assignments are quite good, however formula derivation explanations could be better.