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

03/26/2022
by   Arnab Dey, et al.
4

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.

READ FULL TEXT

page 1

page 3

research
05/19/2022

Mip-NeRF RGB-D: Depth Assisted Fast Neural Radiance Fields

Neural scene representations, such as neural radiance fields (NeRF), are...
research
06/02/2022

EfficientNeRF: Efficient Neural Radiance Fields

Neural Radiance Fields (NeRF) has been wildly applied to various tasks f...
research
07/14/2020

Pose2RGBD. Generating Depth and RGB images from absolute positions

We propose a method at the intersection of Computer Vision and Computer ...
research
08/12/2021

Continual Neural Mapping: Learning An Implicit Scene Representation from Sequential Observations

Recent advances have enabled a single neural network to serve as an impl...
research
05/20/2022

How to Guide Adaptive Depth Sampling?

Recent advances in depth sensing technologies allow fast electronic mane...
research
03/26/2021

LightSAL: Lightweight Sign Agnostic Learning for Implicit Surface Representation

Recently, several works have addressed modeling of 3D shapes using deep ...
research
05/08/2023

NerfAcc: Efficient Sampling Accelerates NeRFs

Optimizing and rendering Neural Radiance Fields is computationally expen...

Please sign up or login with your details

Forgot password? Click here to reset