Skip to content
JournalsWorldThe Global Research Discovery Platform
Login Sign Up
SCHOLARLY PUBLICATION ✓ Open Access

NeRF++: Analyzing and Improving Neural Radiance Fields

Kai Zhang, Gernot Riegler, Noah Snavely, Vladlen Koltun

📖 arXiv (Cornell University) 📅 2020-10-15 🔗 DOI: 10.48550/arxiv.2010.07492
⬇ Download PDF View Official Paper ↗

📄 Abstract

Neural Radiance Fields (NeRF) achieve impressive view synthesis results for a variety of capture settings, including 360 capture of bounded scenes and forward-facing capture of bounded and unbounded scenes. NeRF fits multi-layer perceptrons (MLPs) representing view-invariant opacity and view-dependent color volumes to a set of training images, and samples novel views based on volume rendering techniques. In this technical report, we first remark on radiance fields and their potential ambiguities, namely the shape-radiance ambiguity, and analyze NeRF’s success in avoiding such ambiguities. Second, we address a parametrization issue involved in applying NeRF to 360 captures of objects within large-scale, unbounded 3D scenes. Our method improves view synthesis fidelity in this challenging scenario. Code is available at https://github.com/Kai-46/nerfplusplus.

📤 Share this page

Found this useful? Share it with your network.

𝕏XfFacebookinLinkedIn✆WhatsApp✈Telegram✉EmailMMendeley
✓ Link copied! Paste it on ResearchGate / Academia.edu

🔬 Related Research Papers

arXiv (Cornell University)

The INT Photometric H-alpha Survey of the Northern Galactic Plane (IPHAS)

J. E. Drew, R. Greimel et al. 2005-01-01 · Read paper → arXiv (Cornell University)

Fingerprinting Soft Materials: A Framework for Characterizing Nonlinear Viscoelasticity

Randy H. Ewoldt, Gareth H. McKinley, Anette E. Hosoi 2007-10-29 · Read paper → arXiv (Cornell University)

Blockchain-Federated-Learning and Deep Learning Models for COVID-19 Detection Using CT Imaging

Rajesh Kumar, Abdullah Aman Khan et al. 2020-07-10 · Read paper → arXiv (Cornell University)

Deep Biaffine Attention for Neural Dependency Parsing

Timothy Dozat, Christopher D. Manning 2016-11-04 · Read paper → arXiv (Cornell University)

A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights

Weijie Su, Stephen Boyd, Emmanuel J. Candès 2015-03-04 · Read paper → arXiv (Cornell University)

A Stochastic Gradient Method with an Exponential Convergence Rate for Finite Training Sets

Nicolas Le Roux, Mark Schmidt, Francis Bach 2012-02-28 · Read paper → arXiv (Cornell University)

Church: a language for generative models

Noah D. Goodman, Vikash K. Mansinghka et al. 2012-06-13 · Read paper → arXiv (Cornell University)

Training Deep Nets with Sublinear Memory Cost

Tianqi Chen, Bing Xu et al. 2016-04-21 · Read paper → arXiv (Cornell University)

A New Approach to Generalized Fractional Derivatives

Udita N. Katugampola 2011-06-06 · Read paper → arXiv (Cornell University)

Similarity of Neural Network Representations Revisited

Simon Kornblith, Mohammad Norouzi et al. 2019-05-01 · Read paper → arXiv (Cornell University)

The PDF4LHC Working Group Interim Recommendations

M. Botje, Jonathan Mark Butterworth et al. 2011-01-03 · Read paper → arXiv (Cornell University)

Efficiently Modeling Long Sequences with Structured State Spaces

Albert Gu, Karan Goel, Christopher Ré 2021-10-31 · Read paper →