Trending

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

Added to collectionTop 100 Deep Learning and AI Papers 2021

Computer Vision

Plenoxels: A System for Visual View Synthesis

Plenoxels: Radiance Fields without Neural Networks

We introduce a system for photorealistic viewsynthesis (plenoptic voxels, plenoptic voxels).

Plenoptic voxels represent a scene as a sparse 3d grid with sphericalharmonics.

This representation can be optimized from calibrated images via gradient methods and regularization without any neural components.

On standard, benchmark tasks, plenoptic voxels are optimized two orders of magnitude faster thanneural radiance fields with no loss in visual quality.

Authors

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

Related Topics

Gradient methods

Neural components

Plenoptic voxels

Read the Paper

Read Paper

Trending

Bookmarks

◐ Recommended Follows

Blockchain and security....

More

◐ Latest Activity

More

Plenoxels: A System for Visual View Synthesis - 42Papers

Read Related Papers

Multi-Scale Deep Learning for Estimating Horizontal Velocity Fields on the Solar Surface

In-field early disease recognition of potato late blight based on deep learning and proximal hyperspectral imaging

PU-Transformer: Point Cloud Upsampling Transformer

MonoPLFlowNet: Permutohedral Lattice FlowNet for Real-Scale 3D Scene FlowEstimation with Monocular Images

TriStereoNet: A Trinocular Framework for Multi-baseline Disparity Estimation

Full-body Neural Avatars of a Person Captured by an egocentric Fisheye Camera

Extracting Triangular 3D Models, Materials, and Lighting From Images

MorphMLP: A Self-Attention Free, MLP-Like Backbone for Image and Video

NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion

Conditional Object-Centric Learning from Video