Alex Yu
Alex Yu
  • Видео 4
  • Просмотров 41 938
184 Final Project
Team 8 - Real-time Reposable Rendering of Volumetric Digitalized Humans
Gaoyue Zhou, Alex Yu, Hang Gao, Chenyue Cai
CS 184/284 Spring 2021, UC Berkeley
We present an extension of the PlenOctrees viewer to support linear blend skinning (LBS)-based character animation.
Просмотров: 113

Видео

PlenOctrees - ICCV Oral Video
Просмотров 8410 месяцев назад
12mins ICCV Oral
PlenOctrees for Real-time Rendering of Neural Radiance Fields
Просмотров 16 тыс.3 года назад
Real-time rendering of NeRFs via distillation into PlenOctrees (view-dependent octrees). Please view in 1080p to see details. Website: alexyu.net/plenoctrees arxiv.org/abs/2103.14024
pixelNeRF: Neural Radiance Fields from One or Few Images
Просмотров 26 тыс.4 года назад
Website: alexyu.net/pixelnerf Github: github.com/sxyu/pixel-nerf

Комментарии

  • @onerimeuse
    @onerimeuse 9 месяцев назад

    Really impressive stuff mate. Nice work

  • @THEMATT222
    @THEMATT222 Год назад

    Noice 👍👍

  • @daulet344
    @daulet344 Год назад

    game changer!

  • @DasAntiNaziBroetchen
    @DasAntiNaziBroetchen Год назад

    God damn dude, normalize that volume. I can hardly hear you.

  • @jahn_star
    @jahn_star 3 года назад

    Waybe

  • @ChipWeinberger
    @ChipWeinberger 3 года назад

    hugely impressive

  • @dinoscheidt
    @dinoscheidt 3 года назад

    Tried it on the latest largest iPad Pro - stuck at 100% Loading.

    • @alexyu1325
      @alexyu1325 3 года назад

      Mobile browser is not supported right now due to WebGL compatibility problems.

    • @davecardwell3607
      @davecardwell3607 3 года назад

      @@alexyu1325 do we know what specifically blocks it? Great work btw.

  • @Q_20
    @Q_20 3 года назад

    Realtime novel view synthesis would be a major breakthrough in computer graphics

  • @Q_20
    @Q_20 3 года назад

    near-realtime rendering possible?

  • @chronokoks
    @chronokoks 3 года назад

    you guys rock! Keep it up. The first time I saw NERF I knew there's a lot to this technique and a lot that can be improved.

  • @kwea123
    @kwea123 3 года назад

    Why don't you train the plenoctree directly like in nsvf? Is it due to the .refine() method that changes model structure? Also, it would be great if it's possible to cast shadow on the object by the inserted mesh. Naively tracing rays from the light sources to the sample points and calculating if they intersect with the mesh is very costly (although it works quite nicely, I've tried).

    • @alexyu1325
      @alexyu1325 3 года назад

      Good question. So far it seems optimizing a MLP works better than optimizing a discrete grid. NSVF is using NeRF still. People have tried and are still trying alternate representations/architectures for NeRF.

  • @douglasteixeiradeabreu
    @douglasteixeiradeabreu 3 года назад

    Very good 💯

  • @taesiri
    @taesiri 3 года назад

    Impressive (real-time) results.

  • @santiagoespada7533
    @santiagoespada7533 4 года назад

    great work & explanation! Congrats