Web: http://arxiv.org/abs/2201.08845

Jan. 24, 2022, 2:10 a.m. | Qiangeng Xu, Zexiang Xu, Julien Philip, Sai Bi, Zhixin Shu, Kalyan Sunkavalli, Ulrich Neumann

cs.CV updates on arXiv.org arxiv.org

Volumetric neural rendering methods like NeRF generate high-quality view
synthesis results but are optimized per-scene leading to prohibitive
reconstruction time. On the other hand, deep multi-view stereo methods can
quickly reconstruct scene geometry via direct network inference. Point-NeRF
combines the advantages of these two approaches by using neural 3D point
clouds, with associated neural features, to model a radiance field. Point-NeRF
can be rendered efficiently by aggregating neural point features near scene
surfaces, in a ray marching-based rendering pipeline. Moreover, …

arxiv cv neural

More from arxiv.org / cs.CV updates on arXiv.org

Data Analyst, Credit Risk

@ Stripe | US Remote

Senior Data Engineer

@ Snyk | Cluj, Romania, or Remote

Senior Software Engineer (C++), Autonomy Visualization

@ Nuro, Inc. | Mountain View, California (HQ)

Machine Learning Intern (January 2023)

@ Cohere | Toronto, Palo Alto, San Francisco, London

Senior Machine Learning Engineer, Reinforcement Learning, Personalization

@ Spotify | New York, NY

AWS Data Engineer

@ ProCogia | Seattle