Plenoxels: Radiance Fields without Neural Networks

Sara Fridovich-Keil; Alex Yu; Matthew Tancik; Qinhong Chen; Benjamin Recht; Angjoo Kanazawa

doi:10.1109/cvpr52688.2022.00542

Abstract

We introduce Plenoxels (plenoptic voxels), a systemfor photorealistic view synthesis. Plenoxels represent a scene as a sparse 3D grid with spherical harmonics. This representation can be optimized from calibrated images via gradient methods and regularization without any neural components. On standard, benchmark tasks, Plenoxels are optimized two orders of magnitude faster than Neural Radiance Fields with no loss in visual quality. For video and code, please see https://alexyu.net/plenoxels.

Keywords

RadianceComputer scienceVoxelArtificial neural networkSpherical harmonicsArtificial intelligenceGridBenchmark (surveying)Code (set theory)Representation (politics)Computer visionRegularization (linguistics)VisualizationMathematicsOpticsPhysics

Affiliated Institutions

Related Publications

pixelNeRF: Neural Radiance Fields from One or Few Images

Alex Yu , Vickie Ye , Matthew Tancik +1 more

We propose pixelNeRF, a learning framework that predicts a continuous neural scene representation conditioned on one or few input images. The existing approach for constructing ...

2021 1273 citations

VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection

Yin Zhou , Oncel Tuzel

Accurate detection of objects in 3D point clouds is a central problem in many applications, such as autonomous navigation, housekeeping robots, and augmented/virtual reality. To...

2018 4245 citations

NeRF

Ben Mildenhall , Pratul P. Srinivasan , Matthew Tancik +3 more

We present a method that achieves state-of-the-art results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using ...

2021 Communications of the ACM 4497 citations

3D Gaussian Splatting for Real-Time Radiance Field Rendering

Bernhard Kerbl , Georgios Kopanas , Thomas Leimkühler +1 more

Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires...

2023 ACM Transactions on Graphics 2903 citations

PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud

Shaoshuai Shi , Xiaogang Wang , Hongsheng Li

In this paper, we propose PointRCNN for 3D object detection from raw point cloud. The whole framework is composed of two stages: stage-1 for the bottom-up 3D proposal generation...

2019 2019 IEEE/CVF Conference on Computer ... 2773 citations

Publication Info

Year: 2022
Type: article
Pages: 5491-5500
Citations: 1105
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Plenoxels: Radiance Fields without Neural Networks

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

1105

OpenAlex

Cite This

APA Style

                            
                                    Sara Fridovich-Keil, 
                                
                                    Alex Yu, 
                                
                                    Matthew Tancik
                                
                                et al.
                            
                            (2022). 
                            Plenoxels: Radiance Fields without Neural Networks. 
                            2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
                            
                            , 5491-5500.
                            https://doi.org/10.1109/cvpr52688.2022.00542

Identifiers

DOI: 10.1109/cvpr52688.2022.00542