DensePose: Dense Human Pose Estimation In The Wild (CVPR 2018 Oral)

Ғылым және технология

Project page: densepose.org
Paper: arxiv.org/pdf/1802.00434.pdf

Пікірлер: 39

  • @LEDchip
    @LEDchip5 жыл бұрын

    This is truly wonderful work! Super kudos to the engineers making this happen, they are bringing us all into a new world, literally and figuratively. Being able to take video and capture the sets and actors in 3-d in a form that is truly useable, would allow virtually unlimited potential to redevelop story lines and re-render new movies with different actors, filming locations and may be even the way the films end, all at will. Computer farms on the cloud could give the power to anyone with a cell phone. I can’t wait to try this soon and see how it really works with my video.

  • @DamianReloaded
    @DamianReloaded6 жыл бұрын

    This is awesome. With this technology (and a few already existing others) they could potentially re-create any video/film recording in 3D. Imagine watching casablanca as one of the extras through VR! ^_^

  • @alistermunro7090

    @alistermunro7090

    6 жыл бұрын

    Casablanca is probably last on the mind with VR ;)

  • @punachaa
    @punachaa Жыл бұрын

    Great Research. If not we humans..some other brains are already seeing us ( people on earth) via radio/spectrum mapping in one or other form.. It is just that we dont know ..Thank you .

  • @JorgeGamaliel
    @JorgeGamaliel6 жыл бұрын

    Awesome! With generative adversarial networks many things become possible.

  • @alialtaf3412
    @alialtaf34126 жыл бұрын

    I am in love with this technology.. This can revolutionize Motion Capture while also saving cost.

  • @example.com.
    @example.com.6 жыл бұрын

    Awesome work

  • @hyunkim2172
    @hyunkim21726 жыл бұрын

    Just wonderful!!!

  • @hakopato
    @hakopato6 жыл бұрын

    Great work!

  • @Tactic3d
    @Tactic3d6 жыл бұрын

    great work !

  • @757beko
    @757beko6 жыл бұрын

    Wonderful!

  • @cangulec
    @cangulec6 жыл бұрын

    Amazing

  • @kamillatocha
    @kamillatocha5 жыл бұрын

    someone definitely needs to make a music video with this in it

  • @delikatus
    @delikatus5 жыл бұрын

    Am I correct that the output provided by the densepose code does not aim to be analogous to that of a full blown motion capture system, but instead only provides the positions of body parts in the 2D coordinates of the input images, i.e. it doesn't allow to track positions of body parts in a 3D space? Would love to be wrong about this and learn how to obtain 3D representations. Or is there other software that performs this step?

  • @Oakbeast
    @Oakbeast5 жыл бұрын

    how can the U / V coordinate data transfer to a bones or skeletal rig in say Maya, 3D max or Blender or any hub tool for that matter? killer tech; cant wait to see more

  • @khaerulumam42
    @khaerulumam426 жыл бұрын

    Awesomeeee!!

  • @souslicer
    @souslicer6 жыл бұрын

    please release the dataset

  • @erimi01
    @erimi015 жыл бұрын

    Hi! I'm trying to try out DensePose myself but are having issues following the install guide on the git, is there any way you could help?

  • @royaramezani7059
    @royaramezani70596 жыл бұрын

    Awesome work! Can you please share the GitHub link?

  • @SeaCreature_
    @SeaCreature_6 жыл бұрын

    I love it, what a great accomplishment. Give us the GitHub link for it :)

  • @BDCCN-TranPhuongNam
    @BDCCN-TranPhuongNam Жыл бұрын

    hi , how can i make a densepose RCNN part index image , its image will look like second image at 1 min 4 seconds of video ?

  • @KD_Kartik
    @KD_Kartik4 жыл бұрын

    hi its awesome technology and i need help me can you tell how to install this project in system

  • @thegreatskywalker
    @thegreatskywalker6 жыл бұрын

    Amazing work!!! Will the source code be available?

  • @jibinjohn8263

    @jibinjohn8263

    5 жыл бұрын

    You can use it for research not for development. Else you have to buy the licence once facebook release the 3d pose library.

  • @user-vg7zv5us5r
    @user-vg7zv5us5r Жыл бұрын

    And then? What was that software made for?

  • @jonhsonbuchanan1126
    @jonhsonbuchanan11266 жыл бұрын

    Can this be done in realtime?

  • @kazioo2

    @kazioo2

    6 жыл бұрын

    From the paper: "a discriminatively trained model can recover highly-accurate correspondence fields for complex scenes involving tens of persons with real-time speed: on a GTX 1080 GPU our system operates at 20-26 frames per second for a 240 × 320 image or 4-5 frames per second for a 800 × 1100 image."

  • @1HololensfansOfNaruto
    @1HololensfansOfNaruto6 жыл бұрын

    Is this processed in real time?

  • @souslicer

    @souslicer

    6 жыл бұрын

    yes

  • @CJCruiser

    @CJCruiser

    6 жыл бұрын

    it mentions "several frames per second with a single GPU" so it could be close to real time, or scaled up with a fatter GPU.

  • @aprendappdcomitalo953
    @aprendappdcomitalo953 Жыл бұрын

    1984 - it´s all U need to read now

  • @thumbsup1089
    @thumbsup10896 жыл бұрын

    Blocked from everyone (Black Mirror - White Christmas)

  • @HungPham-pg6oq
    @HungPham-pg6oq5 жыл бұрын

    Vrc-qwr mover

  • @nyuh
    @nyuh Жыл бұрын

    lmao

  • @radioactivebanana6774
    @radioactivebanana6774 Жыл бұрын

    Creepy. Wifi snd 5g track you everywhere even in your home. Time to go low tech.

Келесі