Fast Learning Radiance Fields by Shooting Much Fewer Rays

08/14/2022
by   Wenyuan Zhang, et al.
7

Learning radiance fields has shown remarkable results for novel view synthesis. The learning procedure usually costs lots of time, which motivates the latest methods to speed up the learning procedure by learning without neural networks or using more efficient data structures. However, these specially designed approaches do not work for most of radiance fields based methods. To resolve this issue, we introduce a general strategy to speed up the learning procedure for almost all radiance fields based methods. Our key idea is to reduce the redundancy by shooting much fewer rays in the multi-view volume rendering procedure which is the base for almost all radiance fields based methods. We find that shooting rays at pixels with dramatic color change not only significantly reduces the training burden but also barely affects the accuracy of the learned radiance fields. In addition, we also adaptively subdivide each view into a quadtree according to the average rendering error in each node in the tree, which makes us dynamically shoot more rays in more complex regions with larger rendering error. We evaluate our method with different radiance fields based methods under the widely used benchmarks. Experimental results show that our method achieves comparable accuracy to the state-of-the-art with much faster training.

READ FULL TEXT

page 1

page 4

page 6

page 7

page 8

page 9

page 10

research
03/27/2023

NeUDF: Learning Unsigned Distance Fields from Multi-view Images for Reconstructing Non-watertight Models

Volume rendering-based 3D reconstruction from multi-view images has gain...
research
04/07/2022

ProbNVS: Fast Novel View Synthesis with Learned Probability-Guided Sampling

Existing state-of-the-art novel view synthesis methods rely on either fa...
research
03/27/2023

Generalizable Neural Voxels for Fast Human Radiance Fields

Rendering moving human bodies at free viewpoints only from a monocular v...
research
04/18/2023

SurfelNeRF: Neural Surfel Radiance Fields for Online Photorealistic Reconstruction of Indoor Scenes

Online reconstructing and rendering of large-scale indoor scenes is a lo...
research
11/30/2021

NeuSample: Neural Sample Field for Efficient View Synthesis

Neural radiance fields (NeRF) have shown great potentials in representin...
research
04/29/2022

A study of tree-based methods and their combination

Tree-based methods are popular machine learning techniques used in vario...
research
09/08/2023

Residency Octree: A Hybrid Approach for Scalable Web-Based Multi-Volume Rendering

We present a hybrid multi-volume rendering approach based on a novel Res...

Please sign up or login with your details

Forgot password? Click here to reset