Accenture-NVS1: A Novel View Synthesis Dataset

Thomas Sugg; Kyle O'Brien; Lekh Poudel; Alex Dumouchelle; Michelle Jou; Marc Bosch; Deva Ramanan; Srinivasa Narasimhan; Shubham Tulsiani

Accenture-NVS1: A Novel View Synthesis Dataset

Computer Vision and Pattern Recognition 2025-08-01 v2 Machine Learning

Authors: Thomas Sugg , Kyle O'Brien , Lekh Poudel , Alex Dumouchelle , Michelle Jou , Marc Bosch , Deva Ramanan , Srinivasa Narasimhan , Shubham Tulsiani

View on arXiv ↗ PDF ↗

Abstract

This paper introduces ACC-NVS1, a specialized dataset designed for research on Novel View Synthesis specifically for airborne and ground imagery. Data for ACC-NVS1 was collected in Austin, TX and Pittsburgh, PA in 2023 and 2024. The collection encompasses six diverse real-world scenes captured from both airborne and ground cameras, resulting in a total of 148,000 images. ACC-NVS1 addresses challenges such as varying altitudes and transient objects. This dataset is intended to supplement existing datasets, providing additional resources for comprehensive research, rather than serving as a benchmark.

Keywords

novel view synthesis image classification

Cite

@article{arxiv.2503.18711,
  title  = {Accenture-NVS1: A Novel View Synthesis Dataset},
  author = {Thomas Sugg and Kyle O'Brien and Lekh Poudel and Alex Dumouchelle and Michelle Jou and Marc Bosch and Deva Ramanan and Srinivasa Narasimhan and Shubham Tulsiani},
  journal= {arXiv preprint arXiv:2503.18711},
  year   = {2025}
}

Comments

6 pages, 7 figures

Accenture-NVS1: A Novel View Synthesis Dataset

Abstract

Keywords

Cite

Comments

Related papers