Carlos Esteves

Table of Contents



I'm a Ph.D. student in Computer and Information Science at the GRASP Laboratory, University of Pennsylvania, under the supervision of Kostas Daniilidis. I'm currently a research intern at Facebook AI Research with Georgia Gkioxari and Justin Johnson, and I was a Student Researcher at Google NYC in 2018 with Ameesh Makadia.

I received the B.S. in computer engineering (2007) and M.S. in electronic and computer engineering (2010) degrees from the Aeronautics Institute of Technology in Brazil (ITA).

Before starting my Ph.D. studies in 2015, I was a researcher at the Brazilian Aeronautics and Space Institute (IAE), and spent 3.5 years at Denel Dynamics, in South Africa, as a development engineer on a joint defense program.



  • Jun 07, 2019: I have been recognized as one of the "CVPR 2019 Outstanding Reviewers"! See the program here.
  • Apr 23, 2019: Our paper, Cross-domain 3D Equivariant Image Embeddings, has been accepted to ICML! Camera-ready available here.
  • Apr 02, 2019: Our paper, Equivariant Multi-View Networks, is now available here.
  • Mar 29, 2019: I'll be a research intern at Facebook AI Research this summer, with Georgia Gkioxari and Justin Johnson.
  • Jul 05, 2018: Our paper, Learning SO(3) Equivariant Representations with Spherical CNNs, has been accepted as an oral presentation to ECCV 2018! Acceptance rate was 2.4%. Camera-ready version here.
  • May 19, 2018: I'll be interning at Google NYC with Ameesh Makadia this summer.
  • Jan 31, 2018: Our Polar Transformer Networks paper has been accepted at ICLR 2018, with top 3% review scores!


My research is in computer vision and machine learning. Specifically, I'm interested in:

  • equivariant representations,
  • 3D vision,
  • wide baseline image matching,
  • pose estimation,
  • multi-image matching,
  • geolocalization.

Selected publications

Equivariant Multi-View Networks
C. Esteves, Y. Xu, C. Allen-Blanchette, K. Daniilidis.
arXiv preprint 1904.00993
[ pdf | code ]

Cross-domain 3D Equivariant Image Embeddings
C. Esteves, A. Sud, Z. Luo, K. Daniilidis, A. Makadia.
International Conference on Machine Learning, ICML 2019.
[ pdf ]

Learning SO(3) Equivariant Representations with Spherical CNNs
C. Esteves, C. Allen-Blanchette, A. Makadia, K. Daniilidis.
European Conference on Computer Vision, ECCV 2018 (oral; acceptance rate 2.4%).
[ pdf | poster | code ]

Labeling Panoramas with Spherical Hourglass Networks
C. Esteves, K. Daniilidis, A. Makadia.
360° Perception and Interaction Workshop at ECCV 2018.
[ pdf | poster ]

Polar Transformer Networks
C. Esteves, C. Allen-Blanchette, X. Zhou, K. Daniilidis.
International Conference on Learning Representations, ICLR 2018.
[ pdf | poster | code | OpenReview ]

Fast Multi-Image Matching via Density-Based Clustering
R. Tron, X. Zhou, C. Esteves, K. Daniilidis.
International Conference on Computer Vision, ICCV 2017.
[ pdf ]


  • CVPR reviewer (IEEE/CVF Conference on Computer Vision and Pattern Recognition)
    • CVPR 2019 Outstanding Reviewer
  • ICCV reviewer (IEEE International Conference on Computer Vision)
  • TPAMI reviewer (IEEE Transactions on Pattern Analysis and Machine Intelligence)


Machine Perception, CIS-580. Teaching assistant, Spring/2018, Spring/2019.
Advanced Robotics, MEAM-620. Teaching assistant, Spring/2017.
Robotics: Planning and Perception, CIS-390. Teaching assistant, Fall/2016.


Author: Carlos Esteves

Created: 2019-06-12 Wed 01:14