The Basics about Bundle Adjustment (Cyrill Stachniss)

แชร์
ฝัง
  • เผยแพร่เมื่อ 22 ธ.ค. 2024

ความคิดเห็น •

  • @LeviAckerman99999
    @LeviAckerman99999 ปีที่แล้ว +18

    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!

    • @CyrillStachniss
      @CyrillStachniss  ปีที่แล้ว +5

      Thanks, I am happy to hear that my material is useful!

    • @avnishpanwar9502
      @avnishpanwar9502 ปีที่แล้ว

      What phd are you pursuing?
      Myself doing a phd on 3d computer vision Slam

    • @vr4782
      @vr4782 10 หลายเดือนก่อน

      Totally agree

    • @ushakumari7915
      @ushakumari7915 หลายเดือนก่อน

      indeed this is very helpful for PhD .

  • @adriennewinter9949
    @adriennewinter9949 2 ปีที่แล้ว +4

    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

  • @borninmountains
    @borninmountains 10 หลายเดือนก่อน +1

    thank you so much Cyrill for this course, If and only I will pass my computer vision exams will be just because of you.

  • @BERNARDIN_1986
    @BERNARDIN_1986 ปีที่แล้ว +1

    The best video I have ever seen in this topic, Epic. Thanks for sharing.

  • @ruanjacobusvanbreda898
    @ruanjacobusvanbreda898 3 ปีที่แล้ว +3

    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.

  • @geethanarayanan2896
    @geethanarayanan2896 6 หลายเดือนก่อน +2

    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).

  • @vr4782
    @vr4782 10 หลายเดือนก่อน +1

    Thank you so much for your generosity. God bless you. All your videos are Really gold. Wow wow wow

  • @LukeSchoen
    @LukeSchoen 4 ปีที่แล้ว +10

    Great Stuff! these videos are golden!

  • @muhammadsarimmehdi
    @muhammadsarimmehdi 2 ปีที่แล้ว +1

    28:10 how did you set up that system? Seems like a huge leap from the previous slide to this one

  • @rachel2046
    @rachel2046 2 ปีที่แล้ว +1

    Great lecture. Really helped me understand bundle adjustment.

  • @Henqi
    @Henqi 3 ปีที่แล้ว +1

    Thank you for the lecture Cyrill!

  • @Shaharsarshalom1
    @Shaharsarshalom1 19 วันที่ผ่านมา +1

    thank you so much, love your videos

  • @yunmeihuang909
    @yunmeihuang909 ปีที่แล้ว +1

    Thank you! So great courses!

  • @xiaoda4923
    @xiaoda4923 2 ปีที่แล้ว +1

    Hi, thanks for the video! It is a very well explained lecture. Would it be possible for you to share the slides?

    • @CyrillStachniss
      @CyrillStachniss  2 ปีที่แล้ว +3

      Sure, see the teaching website of my lab www.ipb.uni-bonn.de

  • @tyoung96
    @tyoung96 2 ปีที่แล้ว

    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,

  • @poojakabra1479
    @poojakabra1479 2 ปีที่แล้ว +1

    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..

    • @mateuszwyszynski4331
      @mateuszwyszynski4331 2 ปีที่แล้ว

      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

  • @middleburyremotesensing3639
    @middleburyremotesensing3639 ปีที่แล้ว

    Thanks for this very clear and careful video. Super helpful!!

  • @muhammadsarimmehdi
    @muhammadsarimmehdi 2 ปีที่แล้ว

    how do you find the control points when you are doing visual inertial SLAM?

  • @thetomer9786
    @thetomer9786 3 ปีที่แล้ว

    Thanks for the great lectures Cyrill!

  • @sujandhali2483
    @sujandhali2483 2 ปีที่แล้ว

    How can we do autonomous navigation in orb slam

  • @juliocastanoamoros6497
    @juliocastanoamoros6497 3 ปีที่แล้ว

    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!

    • @mav45678
      @mav45678 3 ปีที่แล้ว +1

      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.

    • @juliocastanoamoros6497
      @juliocastanoamoros6497 3 ปีที่แล้ว

      @@mav45678 Ok, thank u so much!

  • @ahmadmaryanto5307
    @ahmadmaryanto5307 3 ปีที่แล้ว +1

    thaks very much Prof.

  • @JW-kl2wd
    @JW-kl2wd 3 ปีที่แล้ว

    Thanks for the great video

  • @yuchengluo3747
    @yuchengluo3747 3 ปีที่แล้ว

    thx a lot for your work !!!

  • @444haluk
    @444haluk 3 ปีที่แล้ว +3

    It's a crime that you are watched by thousands and not by hunred of thousands.

    • @CyrillStachniss
      @CyrillStachniss  3 ปีที่แล้ว +3

      Thanks

    • @aadi7448
      @aadi7448 3 ปีที่แล้ว

      Seriously. This is gold. Helps me revisit and consolidate things I learned in grad school.