RGB-D Neural Radiance Fields: Local Sampling for Faster Training - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

RGB-D Neural Radiance Fields: Local Sampling for Faster Training

Résumé

Learning a 3D representation of a scene has been a challenging problem for decades in computer vision. Recent advances in implicit neural representation from images using neural radiance fields(NeRF) have shown promising results. Some of the limitations of previous NeRF based methods include longer training time, and inaccurate underlying geometry. The proposed method takes advantage of RGB-D data to reduce training time by leveraging depth sensing to improve local sampling. This paper proposes a depth-guided local sampling strategy and a smaller neural network architecture to achieve faster training time without compromising quality.

Dates et versions

hal-03653115 , version 1 (27-04-2022)

Identifiants

Citer

Arnab Dey, Andrew I. Comport. RGB-D Neural Radiance Fields: Local Sampling for Faster Training. 43rd Annual Conference of the European Association for Computer Graphics, Apr 2022, Reims, France. ⟨hal-03653115⟩
77 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More