- 4
- 40 892
Alex Yu
Приєднався 26 лип 2012
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.
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.
Переглядів: 110
Відео
PlenOctrees for Real-time Rendering of Neural Radiance Fields
Переглядів 16 тис.3 роки тому
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
Переглядів 25 тис.3 роки тому
Website: alexyu.net/pixelnerf Github: github.com/sxyu/pixel-nerf
Really impressive stuff mate. Nice work
Noice 👍👍
game changer!
God damn dude, normalize that volume. I can hardly hear you.
Waybe
hugely impressive
Tried it on the latest largest iPad Pro - stuck at 100% Loading.
Mobile browser is not supported right now due to WebGL compatibility problems.
@@alexyu1325 do we know what specifically blocks it? Great work btw.
Realtime novel view synthesis would be a major breakthrough in computer graphics
Instant NGP
@@trellas3689 Gaussian Splat
near-realtime rendering possible?
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.
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).
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.
Very good 💯
Impressive (real-time) results.
great work & explanation! Congrats