Using AI for Real-Time 3D Face Reconstruction
Events
Subscribe:  iCal  |  Google Calendar
Busan KR   15, Nov — 19, Nov
Minsk BY   15, Nov — 17, Nov
Minsk BY   16, Nov — 19, Nov
Utrecht NL   24, Nov — 26, Nov
Philadelphia US   30, Nov — 3, Dec
Latest comments
by Axx
11 hours ago

That helmet tho I think that one is spot on with kinda like a classic feel to it.

by Axx
11 hours ago

If I'm not mistaken, in the canon Samus can form the suit around her with her mind. In that case it's not necessary to make the suit industrial-looking (or the arm cannon that big) or have the paint stripes mentioned above, since Samus doesn't have to go buy parts to weld in place to upgrade anything. Also those glow plugs (bolts?) look bad, I get the blizzard look but I would change those and make them not come out of the suit like that. Something that wouldn't be necessary for someone that can form the suit around them.

by Artemis
12 hours ago

I like everything EXCEPT the caution stripes on her thighs. The caution stripes look terrible. Take them off.

Using AI for Real-Time 3D Face Reconstruction
27 April, 2018
News

What is your take on facial alignment and real-time 3D face reconstruction? There are so many possibilities here, but are such things even possible today? Take a look at a work that proposes using a convolutional neural network to deal with the tasks. The method is said to be capable of generating high-quality outputs, creating each image in less than 10 milliseconds. What’s the magic here?

First, let’s check out a quick introduction from Two Minute Papers:

Here is an abstract: 

Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network 

We propose a straightforward method that simultaneously reconstructs the 3D facial structure and provides dense alignment. To achieve this, we design a 2D representation called UV position map which records the 3D shape of a complete face in UV space, then train a simple Convolutional Neural Network to regress it from a single 2D image. We also integrate a weight mask into the loss function during training to improve the performance of the network. Our method does not rely on any prior face model and can reconstruct full facial geometry along with semantic meaning. Meanwhile, our network is very light-weighted and spends only 9.8ms to process an image, which is extremely faster than previous works. Experiments on multiple challenging datasets show that our method surpasses other state-of-the-art methods on both reconstruction and alignment tasks by a large margin.

Yao FengFan WuXiaohu ShaoYanfeng WangXi Zhou 

You can find the full paper here

Links: 

What are your thoughts on the proposed method? What do you think about its limitations? 

Source: arxiv.org

Leave a Reply

Be the First to Comment!

avatar
wpDiscuz