A saviour video for my PhD study, cannot imagine there can be such a nice professor who is willing to devote so much effort and time to make everything so clear for free!
Thank you so much for your content! My whole postgraduate research lab are huge fans of yours. You're getting us all through our dissertation-only Masters. Thank you Prof. Stachniss
Thank you for the great content Mr Stachniss. It really helps to clarify and make this knowledge more accessible. You deserve a million subscribers at least.
Too good - I wish I had studied your videos 10 years ago when I was starting out. Somehow, the books don't give an intuitive picture making this a much more difficult area to approach than it should be. Prof. Stachniss, you should write a book with some good pen and paper and programming exercises. Forstner is probably the best right now. (I work in self driving cars, on BEV modelling, and LOVE this subject).
Thanks for your great leacture! I have some question. In 1:02:15, What kind of variables when you mentioned variance factor? Does it include all kinds of unknown parameters? Thanks,
Can someone explain how we get 10M scale parameters, I thought scale factor would be defined for a camera pair and not be different for every point in the pair of images..
I think it is because we are using homogeneous coordinates. For each 3D point you get only a homogeneous representation after applying projection. The scale in this homogeneous representation (the z coordinate) can be (and I guess usually will be) different for each point. Hence the scale parameter lambda varies across points
Hi, I wanted to ask you something about the scale factor. You avoid using this factor when you move from homogeneous world to euclidean world. Afterwards, you say the result of bundle adjustment does not contain any information about absolute scale. I wonder if this happens because of the change from homogeneous to euclidean world. Thank very much in advance for this amazing work!
The answer is no - these are two different (unrelated) scales. Even if you do BA in homogenous coords (i.e. do not get rid of lambdas), you will not be able to recover the absolute scale of the object in the world.
A saviour video for my PhD study, cannot imagine there can be such a nice professor who is willing to devote so much effort and time to make everything so clear for free!
Thanks, I am happy to hear that my material is useful!
What phd are you pursuing?
Myself doing a phd on 3d computer vision Slam
Totally agree
indeed this is very helpful for PhD .
Thank you so much for your content! My whole postgraduate research lab are huge fans of yours. You're getting us all through our dissertation-only Masters. Thank you Prof. Stachniss
Thanks 😁
thank you so much Cyrill for this course, If and only I will pass my computer vision exams will be just because of you.
Thanks!
The best video I have ever seen in this topic, Epic. Thanks for sharing.
Thank you for the great content Mr Stachniss. It really helps to clarify and make this knowledge more accessible. You deserve a million subscribers at least.
Thanks!
... at least squaresxD
Too good - I wish I had studied your videos 10 years ago when I was starting out. Somehow, the books don't give an intuitive picture making this a much more difficult area to approach than it should be. Prof. Stachniss, you should write a book with some good pen and paper and programming exercises. Forstner is probably the best right now. (I work in self driving cars, on BEV modelling, and LOVE this subject).
Thank you so much for your generosity. God bless you. All your videos are Really gold. Wow wow wow
Glad you like them!
Great Stuff! these videos are golden!
28:10 how did you set up that system? Seems like a huge leap from the previous slide to this one
Great lecture. Really helped me understand bundle adjustment.
Thank you for the lecture Cyrill!
thank you so much, love your videos
Thank you! So great courses!
Hi, thanks for the video! It is a very well explained lecture. Would it be possible for you to share the slides?
Sure, see the teaching website of my lab www.ipb.uni-bonn.de
Thanks for your great leacture! I have some question.
In 1:02:15, What kind of variables when you mentioned variance factor?
Does it include all kinds of unknown parameters?
Thanks,
Can someone explain how we get 10M scale parameters, I thought scale factor would be defined for a camera pair and not be different for every point in the pair of images..
I think it is because we are using homogeneous coordinates. For each 3D point you get only a homogeneous representation after applying projection. The scale in this homogeneous representation (the z coordinate) can be (and I guess usually will be) different for each point. Hence the scale parameter lambda varies across points
Thanks for this very clear and careful video. Super helpful!!
how do you find the control points when you are doing visual inertial SLAM?
Thanks for the great lectures Cyrill!
How can we do autonomous navigation in orb slam
Hi,
I wanted to ask you something about the scale factor. You avoid using this factor when you move from homogeneous world to euclidean world.
Afterwards, you say the result of bundle adjustment does not contain any information about absolute scale. I wonder if this happens because of the change from homogeneous to euclidean world.
Thank very much in advance for this amazing work!
The answer is no - these are two different (unrelated) scales. Even if you do BA in homogenous coords (i.e. do not get rid of lambdas), you will not be able to recover the absolute scale of the object in the world.
@@mav45678 Ok, thank u so much!
thaks very much Prof.
Thanks for the great video
thx a lot for your work !!!
It's a crime that you are watched by thousands and not by hunred of thousands.
Thanks
Seriously. This is gold. Helps me revisit and consolidate things I learned in grad school.