DTIC-PLCT-2025-09 - Medium support technician: Computer Graphics (Rendering) and Machine Learning Specialist

Project description: 

Physically-based rendering (PBR) requires an accurate reproduction of the physical behavior of light and its interaction with the surface materials, which is formalized by the rendering equation. The typical approach to solve the illumination integral is by resorting to Classical Monte Carlo (CMC), thanks to its simplicity and ease of implementation. However, CMC requires a large number of samples to obtain an accurate estimate, even when coupled with variance reduction techniques. To address this issue several methods have been proposed in the literature, among which Bayesian Monte Carlo (BMC) and other Gaussian Process-based approaches with promising results. Nevertheless, the use of BMC in CG is still in an incipient phase and its application to more evolved and widely used rendering algorithms remains cumbersome. This research project (named A-BMC) proposes to investigate and develop efficient solutions to generalize the application of this very promising technique to PBR. 

Main research field: Computer Graphics, (Physically-based Rendering), Machine Learning and Monte-Carlo Integration Methods

Tasks to be performed:

Support and active contribution to the following scientific activities, structured per research line of the project.

Research Line 1 (Progressive Bayesian Monte Carlo):

• Support the development of an Efficient Matlab/Python prototype for progressive BMC (this activity is related to tasks T1.3 and T1.4 of A-BMC).

• Support the fine-tuning of the Mitsuba (C ) implementation resulting from the Matlab/Python prototype (this activity is related to task T1.6 of A-BMC).

Research Line 2 (Active Sampling):

• Support the development of an Efficient Matlab/Python prototype for Active Sampling in the context of BMC integration (this activity is related to tasks T2.3 and T2.4 of A-BMC).

• Support the fine-tuning of the Mitsuba (C ) implementation resulting from the Matlab/Python prototype. This activity is related to task T1.6 of A-BMC).

Group and complement: Group 2 Level h

Dedication and working hours: Part time (30h/week).

Planned remuneration approx: 35.672,80 € gross per year

Financing fund: Proyecto PRESP MICIU/AEI/UE - CNS Marques, Ricardo, "Técnicas Avanzadas de Montecarlo Bayesiano para el Renderizado Foto Realista (A-BMC)" financiado por MICIU/AEI/ / y por la Unión Europea "NextGenerationEU"/PRTR, proyecto que finaliza el 31/08/2025.

This recruitment is financed by the Plan Estatal de Investigación Científica, Técnica y de Innovación

Requirements: 

• Bachelor degree.

The expected start date is March 1st 2025, the job is in Barcelona.

Selection criteria: The selection of the candidates will be made through evaluation of the curriculum and, where appropriate, with the carrying out a test and/or interview. Valuation will be as follows:

1- Academic Training (0-40 points).

• Master in Computer Graphics, Computer Vision or closely related field.

2- Other professional training and experience, adequacy to the proposed profile (0-40 points):

• Demonstration of very strong Computer Graphics background, in particular in Physically-Based Rendering.

• Experience with Machine Learning algorithms.

• Previous experience regarding scientific publications is highly regarded.

3- Other merits (0-20 points):

• It will be advantageous to have previous experience in industry and collaborating in innovation and European projects. UPF-GTI is looking for candidates that can join the project immediately and become part of it, contributing with productive results in the very short term. The working language will be English.

The minimum score to pass the selection process is 70 points. The candidate with the highest score in the selection process will be offered the job.