J
Jonathan T. Barron
Researcher at Google
Publications - 150
Citations - 16615
Jonathan T. Barron is an academic researcher from Google. The author has contributed to research in topics: Rendering (computer graphics) & Computer science. The author has an hindex of 40, co-authored 134 publications receiving 7979 citations. Previous affiliations of Jonathan T. Barron include University of Toronto & Courant Institute of Mathematical Sciences.
Papers
More filters
Posted Content
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
Ben Mildenhall,Pratul P. Srinivasan,Matthew Tancik,Jonathan T. Barron,Ravi Ramamoorthi,Ren Ng +5 more
TL;DR: This work describes how to effectively optimize neural radiance fields to render photorealistic novel views of scenes with complicated geometry and appearance, and demonstrates results that outperform prior work on neural rendering and view synthesis.
Book ChapterDOI
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
Ben Mildenhall,Pratul P. Srinivasan,Matthew Tancik,Jonathan T. Barron,Ravi Ramamoorthi,Ren Ng +5 more
TL;DR: In this article, a fully-connected (non-convolutional) deep network is used to synthesize novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views.
Posted Content
Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
Matthew Tancik,Pratul P. Srinivasan,Ben Mildenhall,Sara Fridovich-Keil,Nithin Raghavan,Utkarsh Singhal,Ravi Ramamoorthi,Jonathan T. Barron,Ren Ng +8 more
TL;DR: An approach for selecting problem-specific Fourier features that greatly improves the performance of MLPs for low-dimensional regression tasks relevant to the computer vision and graphics communities is suggested.
Journal ArticleDOI
Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation
TL;DR: This paper proposes a unified approach for bottom-up hierarchical image segmentation and object proposal generation for recognition, called Multiscale Combinatorial Grouping (MCG), and develops a fast normalized cuts algorithm and proposes a high-performance hierarchical segmenter that makes effective use of multiscale information.
Journal ArticleDOI
Shape, Illumination, and Reflectance from Shading
TL;DR: The technique can be viewed as a superset of several classic computer vision problems (shape-from-shading, intrinsic images, color constancy, illumination estimation, etc) and outperforms all previous solutions to those constituent problems.