NeRF--: Neural Radiance Fields without known camera parameters
Considering the problem of novel view synthesis (NVS) from only a set of 2D images, we simplify the training process of Neural Radiance Field (NeRF) on forward-facing scenes by removing the requirement of known or pre-computed camera parameters, including both intrinsics and 6DoF poses. To this end,...
Main Authors: | Wang, Z, Wu, S, Xie, W, Chen, M, Prisacariu, VA |
---|---|
Format: | Internet publication |
Language: | English |
Published: |
2021
|
Similar Items
-
NoPe-NeRF: optimising neural radiance field with no pose prior
by: Bian, W, et al.
Published: (2023) -
NoPe-NeRF: optimising neural radiance field with no pose prior
by: Bian, W, et al.
Published: (2022) -
NeRF-Supervision: Learning Dense Object Descriptors from Neural Radiance Fields
by: Yen-Chen, Lin, et al.
Published: (2024) -
NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields
by: Rosinol, Antoni, et al.
Published: (2024) -
ABLE-NeRF: attention-based rendering with learnable embeddings for neural radiance field
by: Tang, Zhe Jun, et al.
Published: (2023)