Daniel DeTone

Engineering · Physical Sciences

11h-index779citations24works1.02yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Robotics and Sensor-Based Localization(17), Advanced Vision and Imaging(13), Advanced Image and Video Retrieval Techniques(10), Advanced Neural Network Applications(5), Video Surveillance and Tracking Methods(3)

Publications24 total

ShapeR: Robust Conditional 3D Shape Generation from Casual Captures
arXiv (Cornell University)·2026Open Access
ShapeR: Robust Conditional 3D Shape Generation from Casual Captures
ArXiv.org·2026Open Access
Sonata: Self-Supervised Learning of Reliable Point Representations
2025· 5 cited
Sonata: Self-Supervised Learning of Reliable Point Representations
arXiv (Cornell University)·2025Open Access
EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation Models
arXiv (Cornell University)·2024Open Access
OrienterNet: Visual Localization in 2D Public Maps with Neural Matching
2023· 72 cited
OrienterNet: Visual Localization in 2D Public Maps with Neural Matching
arXiv (Cornell University)·2023Open Access
Implicit Map Augmentation for Relocalization
Lecture notes in computer science·2023· 1 cited
Theseus: A Library for Differentiable Nonlinear Optimization
arXiv (Cornell University)·2022· 46 citedOpen Access
Nerfels: Renderable Neural Codes for Improved Camera Pose Estimation
arXiv (Cornell University)·2022Open Access
NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learning
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)·2022· 25 cited
Feature Query Networks: Neural Surface Description for Camera Pose Refinement
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)·2022· 14 cited
Nerfels: Renderable Neural Codes for Improved Camera Pose Estimation
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)·2022· 8 cited
NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learning
arXiv (Cornell University)·2021Open Access
ODAM: Object Detection, Association, and Mapping using Posed RGB Video
2021 IEEE/CVF International Conference on Computer Vision (ICCV)·2021· 29 citedOpen Access
ODAM: Object Detection, Association, and Mapping using Posed RGB Video
arXiv (Cornell University)·2021Open Access
SuperGlue: Learning Feature Matching With Graph Neural Networks
2020· 123 citedOpen Access
Deep ChArUco: Dark ChArUco Marker Pose Estimation
2019· 79 cited
Self-Improving Visual Odometry
arXiv (Cornell University)·2018· 31 citedOpen Access
Deep ChArUco: Dark ChArUco Marker Pose Estimation
arXiv (Cornell University)·2018· 4 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Richard Newcombe(10), Tomasz Malisiewicz(9), Julian Straub(9), Tianwei Shen(8), Tsun-Yi Yang(7), Chris Sweeney(6), Andrew Rabinovich(5), Vasileios Balntas(5), Paul-Edouard Sarlin(3), David Novotný(3), Chris Sweeney(3), Danying Hu(2), Armen Avetisyan(2), Samuel Rota Bulò(2), Peter Kontschieder(2), Kejie Li(2), Steven Chen(2), Minh Vo(2), Ian Reid(2), Hamid Rezatofighi(2)