Generative Multiplane Neural Radiance for 3D-Aware Image Generation

Amandeep Kumar, Ankan Kumar Bhunia, Sanath Narayan, Hisham Cholakkal, Rao Muhammad Anwer, Salman Khan, Ming-Hsuan Yang, Fahad Shahbaz Khan

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference article in proceedingsScientificvertaisarvioitu

Abstrakti

We present a method to efficiently generate 3D-aware high-resolution images that are view-consistent across multiple target views. The proposed multiplane neural radiance model, named GMNR, consists of a novel α-guided view-dependent representation (α-VdR) module for learning view-dependent information. The α-VdR module, faciliated by an α-guided pixel sampling technique, computes the view-dependent representation efficiently by learning viewing direction and position coefficients. Moreover, we propose a view-consistency loss to enforce photometric similarity across multiple views. The GMNR model can generate 3D-aware high-resolution images that are view-consistent across multiple camera poses, while maintaining the computational efficiency in terms of both training and inference time. Experiments on three datasets demonstrate the effectiveness of the proposed modules, leading to favorable results in terms of both generation quality and inference time, compared to existing approaches. Our GMNR model generates 3D-aware images of 1024×1024 pixels with 17.6 FPS on a single V100. Code: https://github.com/VIROBO-15/GMNR
AlkuperäiskieliEnglanti
Otsikko2023 IEEE/CVF International Conference on Computer Vision (ICCV)
KustantajaIEEE
ISBN (elektroninen)979-8-3503-0718-4
ISBN (painettu)979-8-3503-0719-1
DOI - pysyväislinkit
TilaJulkaistu - 2023
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaInternational Conference on Computer Vision - Paris, Ranska
Kesto: 1 lokak. 20236 lokak. 2023

Julkaisusarja

NimiIEEE International Conference on Computer Vision
KustantajaIEEE
ISSN (painettu)1550-5499
ISSN (elektroninen)2380-7504

Conference

ConferenceInternational Conference on Computer Vision
LyhennettäICCV
Maa/AlueRanska
KaupunkiParis
Ajanjakso01/10/202306/10/2023

Sormenjälki

Sukella tutkimusaiheisiin 'Generative Multiplane Neural Radiance for 3D-Aware Image Generation'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä