1st Workshop on Neural Fields Beyond Conventional Cameras

in conjunction with ECCV 2024, Milan, Italy.

Date: 09/30 (AM)

Motivation 💡

Neural fields have been widely adopted for learning novel view synthesis and 3D reconstruction from RGB images by modelling transport of light in the visible spectrum. This workshop focuses on neural fields beyond conventional cameras, including (1) learning neural fields from data from different sensors across the electromagnetic spectrum and beyond, such as lidar, cryo-electron microscopy (cryoEM), thermal, event cameras, acoustic, and more, and (2) modelling associated physics-based differentiable forward models and/or the physics of more complex light transport (reflections, shadows, polarization, diffraction limits, optics, scattering in fog or water, etc.). Our goal is to bring together a diverse group of researchers using neural fields across sensor domains to foster learning and discussion in this growing area.

Schedule ⏰ (tentative)

13:15 - 13:20 Welcome & Introduction
13:20 - 13:45 Keynote 1
13:45 - 14:10 Keynote 2
14:10 - 14:35 Keynote 3
14:35 - 14:45 Paper Spotlight Presentation 1
14:45 - 14:55 Paper Spotlight Presentation 2
14:55 - 15:05 Paper Spotlight Presentation 3
15:05 - 15:50 Poster Session & Coffee Break
15:50 - 16:15 Keynote 4
16:15 - 16:40 Keynote 5
16:40 - 17:05 Keynote 6
17:05 - 17:40 Panel Discussion

Invited Speakers 🧑‍🏫 (tentative)

David Lindell

University of Toronto

David Lindell is an Assistant Professor in the Department of Computer Science at the University of Toronto and founding member of the Toronto Computational Imaging Group. His work is at the intersection of machine learning, computational imaging, and computer vision. Along these lines he has worked on next-generation computational imaging systems for imaging around corners and through scattering media, and new machine learning algorithms for representing and processing signals. His work is relevant to a broad range of applications in computer graphics, vision, and remote sensing.

Ellen Zhong

Princeton

Ellen Zhong is an Assistant Professor of Computer Science at Princeton University. She is interested in problems at the intersection of AI and biology. Her research develops machine learning methods for computational and structural biology problems with a focus on protein structure determination with cryo-electron microscopy (cryo-EM). She obtained her Ph.D. from MIT in 2022, advised by Bonnie Berger and Joey Davis, where she developed deep learning algorithms for 3D reconstruction of dynamic protein structures from cryo-EM images. She has interned at DeepMind (AlphaFold team) and previously worked on molecular dynamics algorithms at D. E. Shaw Research.

Daniel Cremers

TU Munich

Daniel Cremers is a Professor at Technical University of Munich where he holds the Chair of Computer Vision and Artificial Intelligence. His publications received several awards, including the 'Best Paper of the Year 2003' (Int. Pattern Recognition Society), the 'Olympus Award 2004' (now called 'German Pattern Recognition Award') and the '2005 UCLA Chancellor's Award for Postdoctoral Research'. For pioneering research he received a Starting Grant (2009), two Proof of Concept Grants (2014 \& 2018), a Consolidator Grant (2015) and an Advanced Grant (2020) by the European Research Council. In December 2010 he was listed among "Germany's top 40 researchers below 40" (Capital). On March 1st 2016, Prof. Cremers received the Gottfried Wilhelm Leibniz Award, the biggest award in German academia. In 2022 and 2023, he was listed among the top 10 most influential scholars in robotics of the last decade. He serves as co-founder, advisor and business angel to several startups.

Jon Barron

Google

Jon Barron is a senior staff research scientist at Google Research, where he works on computer vision and machine learning. He received a PhD in Computer Science from the University of California, Berkeley in 2013, where he was advised by Jitendra Malik, and he received a Honours BSc in Computer Science from the University of Toronto in 2007. He received a National Science Foundation Graduate Research Fellowship in 2009, the C.V. Ramamoorthy Distinguished Research Award in 2013, and the PAMI Young Researcher Award in 2020. His works have received awards at ECCV 2016, TPAMI 2016, ECCV 2020, ICCV 2021, CVPR 2022, the 2022 Communications of the ACM, and ICLR 2023.

Tali Treibitz

University of Haifa

Tali Treibitz is heading the Viseaon marine imaging lab in the School of Marine Sciences in the University of Haifa since 2014. She received her PhD degree in electrical engineering from the Technion-Israel Institute of Technology in 2010. Between 2010-2013 she was a post-doctoral researcher in the department of computer science and engineering, in the University of California, San Diego and in the Marine Physical Lab in Scripps Institution of Oceanography. Her lab focuses on cutting edge research in underwater computer vision, scene, color and 3D reconstruction, automatic analysis of scenes, and autonomous decision making based on visual input.

Carl Vondrick

Columbia University

Carl Vondrick is an Associate professor of computer science at Columbia University. His research focuses on computer vision and machine learning. By training machines to observe and interact with their surroundings, his group aims to create robust and versatile models for perception. They often develop visual models that capitalize on large amounts of unlabeled data and transfer across tasks and modalities. Other interests include sound and language, interpretable models and high-level reasoning. Recent work includes 3D reconstruction from shadows and thermal reflections.

Call for Papers 📢📢

This workshop aims to bring together a diverse group of researchers using neural fields across sensor domains to foster learning and discussion in this growing area. We welcome paper submissions on all topics related to neural fields beyond conventional cameras. Papers on gaussian splatting are welcomed within this. Accepted papers will be posted on the workshop website, but will not be part of the ECCV proceedings. Relevant topics for this workshop include but are not limited to:
  • Neural field-based reconstruction and view synthesis using non-RGB sensor measurements (LiDAR, Thermal, Event, CT, MRI, Ultrasound, Cryo-EM, Sonar, etc)
  • Neural fields for computational imaging
  • Neural fields for sensor modelling and calibration
  • Neural fields for modelling visual cues (shadows, reflections, polarization, etc)
  • Applications of the above to autonomous vehicles, AR/VR/XR, robotics, medicine, scientific dis- covery, and beyond

Style and Author Instructions

  • Paper Length: We ask authors to use the official ECCV 2024 or CVPR 2024 template and limit submissions to 4-8 pages, excluding references.
  • Dual Submissions: The workshop is non-archival. In addition, in light of the new single-track policy of ECCV 2024, we encourage papers accepted to ECCV 2024 to present at our workshop.
  • Presentation Forms: All accepted papers will get poster presentations during the workshop; selected papers will get oral presentations.

All submissions should anonymized. Papers with more than 8 pages (excluding references) will be rejected without review. Please carefully review the CVF dual submission policy when deciding the length of your submission. If you plan to submit the work for publication in the future, we strongly recommend submitting a four page version to this workshop. Supplementary material is optional with supported formats: pdf, mp4 and zip.

All submissions should adhere to the ECCV 2024 submission guidelines, wherever applicable.

Submission Portal: OpenReview

Paper Review Timeline:

Paper Submission and supplemental material deadline August 9, 2024 (AoE time)
Notification to authors August 30, 2024 (AoE time)
Camera ready deadline September 6, 2024 (AoE time)