Research Internship (F/M/NB) - Real-time Neural Rendering

Nov 10, 2022
Bordeaux, France
... Not specified
... Internship
Full time
... Office work

Neural rendering research has gained lots of attention over the past two years [1]. In this context, a neural network can efficiently represent a 3D object by approximating absorbance and the emitted radiance at every point of a volume [2]. Rendering such objects is done via a volume rendering framework which requires hundreds of forward passes on the neural network. This makes the whole rendering process quite slow (between 1 and 0.1 fps). To address this issue, recent methods [3, 4] focus on reducing the size of the network by discretizing the volume and storing in each cell a high dimensional embedding. While these methods can achieve 200+ fps performance they require a large memory footprint (>2GB) and thus negating the low memory appeal of neural representations.

 

In this project, our goal is to develop real-time neural rendering techniques that have a small memory footprint. Recent work by Stizman et al [5] have shown that this can be achieved by letting the neural network approximate the object’s light field rather than its radiance.

 

References

[1] Xie, Yiheng, et al. "Neural fields in visual computing and beyond." Computer Graphics Forum. Vol. 41. No. 2. 2022

[2] Mildenhall, Ben, et al. "Nerf: Representing scenes as neural radiance fields for view synthesis." Communications of the ACM Vol 65. No 1. 2021

[3] Müller, Thomas, et al. "Instant neural graphics primitives with a multiresolution hash encoding." ACM SIGGRAPH 2022 Conference Proceedings.

[4] Karnewar, Animesh, et al. "Relu fields: The little non-linearity that could." ACM SIGGRAPH 2022 Conference Proceedings.

[5] Sitzmann Vincent, et al. “Light field networks: Neural scene representations with single-evaluation rendering.” Advances in Neural Information Processing Systems. 2021.

You are a last year student of an engineering school or a university research master;

You have solid knowledge in mathematics and computer science

You have skills in machine learning, computer graphics and geometry processing, and have mobilized them using C++ and Pytorch

Your level of English allows you to work in an international team and to communicate easily with non-French speakers.

 

Skills and competencies show up in different forms and can be based on different experiences, that's why we strongly encourage you to apply even though you may not have all the requirements listed above.

Process:

·         Phone Interview

·         Interview(s) with our internal teams

·         Final interview with the project manager

 

If your application is not retained, you will receive a negative answer.

 

At Ubisoft, you can come as you are. We embrace diversity in all its forms. We’re committed to fostering a work environment that is inclusive and respectful of all differences, we value diversity at our company and do not discriminate on the basis of race, ethnicity, religion, gender, sexual orientation, age or disability status. All personal informations will be treated as confidential according to the Employment Equity act

Top Jobs