BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:MaRF: Representing Mars as Neural Radiance Fields - Lorenzo Giusti
 \, Universita' La Sapienza
DTSTART:20230529T170000Z
DTEND:20230529T180000Z
UID:TALK201940@talks.cam.ac.uk
CONTACT:Pietro Lio
DESCRIPTION:MaRF is a novel framework able to synthesize the Martian envir
 onment using several collections of images from rover cameras. The idea is
  to generate a 3D scene of Mars' surface to address key challenges in plan
 etary surface exploration such as: planetary geology\, simulated navigatio
 n and shape analysis. Although there exist different methods to enable a 3
 D reconstruction of Mars' surface\, they rely on classical computer graphi
 cs techniques that incur high amounts of computational resources during th
 e reconstruction process\, and have limitations with generalizing reconstr
 uctions to unseen scenes and adapting to new images coming from rover came
 ras. The proposed framework solves the aforementioned limitations by explo
 iting Neural Radiance Fields (NeRFs)\, a method that synthesize complex sc
 enes by optimizing a continuous volumetric scene function using a sparse s
 et of images. To speed up the learning process\, we replaced the sparse se
 t of rover images with their neural graphics primitives (NGPs)\, a set of 
 vectors of fixed length that are learned to preserve the information of th
 e original images in a significantly smaller size. In the experimental sec
 tion\, we demonstrate the environments created from actual Mars datasets c
 aptured by Curiosity rover\, Perseverance rover and Ingenuity helicopter\,
  all of which are available on the Planetary Data System (PDS).   
LOCATION:Lecture Theatre 2\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR