Pierre Marza

PhD Student - Visual Navigation, Computer Vision, Deep Learning, Reinforcement Learning.

I am a PhD student at INSA Lyon, in the LIRIS research lab. I am advised by Laetita Matignon, Olivier Simonin and Christian Wolf. I study Visual Navigation, Embodied AI, Spatial Reasoning. I am interested in learning how to represent/map new photorealistic environments, ground reasoning with language, act efficiently in unknown scenes with few supervision. I interned at Meta AI (FAIR) with Devendra Chaplot in summer 2022.

Prior to this, I spent some time as an intern at Huawei Noah’s Ark Computer Vision Lab in London, working on Image Enhancement with Sean Moran, Steven McDonagh, Sarah Parisot, Greg Slabaugh, and others. I also interned at Orange Labs in Rennes, studying Visual Question Answering with Corentin Kervadec, Grigory Antipov, Moez Baccouche and Christian Wolf.

I got my Master’s degree from INSA Lyon, with a major in Computer Science. I spent a semester at KTH in Stockholm, studying Deep Learning, Machine Learning and Reinforcement Learning.

Reviewing experience: TPAMI, ICML 2022 (outstanding reviewer), ICLR 2023-2024, ICCV 2023, NeurIPS 2023, ECCV 2024 (outstanding reviewer)

My CV is available here

News

Sep 23, 2024 I have been selected as an outstanding reviewer for ECCV 2024.
Jun 30, 2024 One paper accepted at IROS 2024: AutoNeRF: Training Implicit Scene Representations with Autonomous Agents.
Feb 27, 2024 One paper accepted at CVPR 2024: Task-conditioned adaptation of visual features in multi-task policy learning.
Sep 18, 2023 I will be presenting 2 papers at the Nerf4ADR workshop at ICCV 2023: Multi-Object Navigation with dynamically learned neural implicit representations and AutoNeRF: Training Implicit Scene Representations with Autonomous Agents (oral presentation).
Jul 14, 2023 One paper accepted at ICCV 2023: Multi-Object Navigation with dynamically learned neural implicit representations.
Jul 9, 2023 I am attending the International Computer Vision Summer School (ICVSS 2023) in Sicily.
Apr 25, 2023 New paper on arXiv: AutoNeRF: Training Implicit Scene Representations with Autonomous Agents.
Oct 11, 2022 New paper on arXiv: Multi-Object Navigation with dynamically learned neural implicit representations.
Jul 17, 2022 I have been selected as an outstanding reviewer (Top 10%) for ICML 2022.
Jun 29, 2022 One paper accepted at IROS 2022: Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation.
Jun 27, 2022 Beginning of my internship at Meta AI (FAIR) in Menlo Park, working with Devendra Chaplot.
Feb 14, 2022 New paper on arXiv: An experimental study of the vision-bottleneck in VQA.
Jun 29, 2021 I presented some of our work on Learning Spatial Reasoning for Multi-Object Navigation during a Workshop on Learning and Robotics organized by the GDR ISIS, and entitled Apprentissage et Robotique. Slides are available here.
Jun 20, 2021 We won the MultiON Challenge for Embodied AI Workshop at CVPR 2021! [video] [arXiv]
Dec 1, 2020 I am starting my PhD at INSA Lyon/LIRIS, with C. Wolf, L. Matignon and O. Simonin.

Selected publications

  1. CVPR
    Task-conditioned adaptation of visual features in multi-task policy learning
    Pierre Marza, Laetitia Matignon, Olivier Simonin, Christian Wolf
    Computer Vision and Pattern Recognition (CVPR) 2024
  2. IROS
    AutoNeRF: Training Implicit Scene Representations with Autonomous Agents
    Pierre Marza, Laetitia Matignon, Olivier Simonin, Dhruv Batra, Christian Wolf, Devendra Singh Chaplot
    International Conference on Intelligent Robots and Systems (IROS) 2024
  3. ICCV
    Multi-Object Navigation with dynamically learned neural implicit representations
    Pierre Marza, Laetitia Matignon, Olivier Simonin, Christian Wolf
    International Conference on Computer Vision (ICCV) 2023
  4. IROS
    Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation (Winning entry of the MultiON Challenge at CVPR 2021)
    Pierre Marza, Laëtitia Matignon, Olivier Simonin, Christian Wolf
    International Conference on Intelligent Robots and Systems (IROS) 2022
  5. CVPR
    DeepLPF: Deep Local Parametric Filters for Image Enhancement
    Sean Moran, Pierre Marza, Steven McDonagh, Sarah Parisot, Gregory Slabaugh
    In Computer Vision and Pattern Recognition (CVPR) 2020

Patents

  1. Patent
    A device and method for image processing
    Sean Moran, Pierre Marza, Steven McDonagh, Sarah Parisot, Gregory Slabaugh
    2021