Projekteja vuodessa
Abstrakti
High-quality scene reconstruction and novel view synthesis based on Gaussian Splatting (3DGS) typically require steady, high-quality photographs, often impractical to capture with handheld cameras. We present a method that adapts to camera motion and allows high-quality scene reconstruction with handheld video data suffering from motion blur and rolling shutter distortion. Our approach is based on detailed modelling of the physical image formation process and utilizes velocities estimated using visual-inertial odometry (VIO). Camera poses are considered non-static during the exposure time of a single image frame and camera poses are further optimized in the reconstruction process. We formulate a differentiable rendering pipeline that leverages screen space approximation to efficiently incorporate rolling-shutter and motion blur effects into the 3DGS framework. Our results with both synthetic and real data demonstrate superior performance in mitigating camera motion over existing methods, thereby advancing 3DGS in naturalistic settings.
Alkuperäiskieli | Englanti |
---|---|
Otsikko | Computer Vision – ECCV 2024 |
Alaotsikko | 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part LXXI |
Toimittajat | Aleš Leonardis, Elisa Ricci, Stefan Roth, Olga Russakovsky, Torsten Sattler, Gül Varol |
Kustantaja | Springer |
Sivut | 160-177 |
ISBN (elektroninen) | 978-3-031-73209-6 |
ISBN (painettu) | 978-3-031-73208-9 |
DOI - pysyväislinkit | |
Tila | Julkaistu - 1 marrask. 2024 |
OKM-julkaisutyyppi | A4 Artikkeli konferenssijulkaisussa |
Tapahtuma | European Conference on Computer Vision - Milano, Italia Kesto: 29 syysk. 2024 → 4 lokak. 2024 Konferenssinumero: 18 |
Julkaisusarja
Nimi | Lecture Notes in Computer Science |
---|---|
Kustantaja | Springer |
Vuosikerta | 15129 |
ISSN (painettu) | 0302-9743 |
ISSN (elektroninen) | 1611-3349 |
Conference
Conference | European Conference on Computer Vision |
---|---|
Lyhennettä | ECCV |
Maa/Alue | Italia |
Kaupunki | Milano |
Ajanjakso | 29/09/2024 → 04/10/2024 |
Sormenjälki
Sukella tutkimusaiheisiin 'Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.-
Solin Arno /AoF Fellow Salary: Probabilistic principles for latent space exploration in deep learning
Solin, A. (Vastuullinen tutkija) & Mereu, R. (Projektin jäsen)
01/09/2021 → 31/08/2026
Projekti: Academy of Finland: Other research funding
-
-: Finnish Center for Artificial Intelligence
Kaski, S. (Vastuullinen tutkija)
01/01/2019 → 31/12/2022
Projekti: Academy of Finland: Other research funding