Nikhila Ravi
RESEARCH ENGINEER | MENLO PARK, UNITED STATES
Nikhila is a Research Engineer at Facebook AI Research, with a focus on computer vision and 3D understanding. Previously at Facebook, she worked on tools and platforms for democratizing machine learning training and deployment for internal teams. Nikhila graduated with a Bachelor's and Master's in Engineering at Cambridge University and spent a year at Harvard University on a Kennedy Scholarship, where she focused on machine learning and AI.
Research Areas
Nikhila's Work
Nikhila's Publications
November 19, 2025
RESEARCH
COMPUTER VISION
SAM 3: Segment Anything with Concepts
Ronghang Hu, Peize Sun, Triantafyllos Afouras, Effrosyni Mavroudi, Katherine Xu, Tsung-Han Wu, Yu Zhou, Liliane Momeni, Shuangrui Ding, Sagar Vaze, Francois Porcher, Feng Li, Siyuan Li, Aishwarya Kamath, Ho Kei Cheng, Andrew Huang, Arpit Kalla, Baishan Guo, Chaitanya Ryali, Christoph Feichtenhofer, Didac Suris Coll-Vinent, Haitham Khedr, Jie Lei, Joseph Greer, Kalyan Vasudev Alwala, Kate Saenko, Laura Gustafson, Markus Marks, Meng Wang, Nicolas Carion, Nikhila Ravi, Pengchuan Zhang, Piotr Dollar, Rishi Hazra, Roman Rädle, Shoubhik Debnath, Tengyu Ma, Yuan-Ting Hu
November 19, 2025
April 17, 2025
COMPUTER VISION
Perception Encoder: The best visual embeddings are not at the output of the network
Hanoona Rasheed, Junke Wang, Marco Monteiro, Andrea Madotto, Po-Yao Huang, Chen Wei, Christoph Feichtenhofer, Daniel Bolya, Daniel Li (FAIR), Hu Xu, Jathushan Rajasegaran, Jiale Zhi, Nikhila Ravi, Peize Sun, Piotr Dollar, Shiyu Dong, Tengyu Ma, Jang Hyun Cho
April 17, 2025
April 17, 2025
COMPUTER VISION
PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding
Yale Song, Hanoona Rasheed, Miguel Martin, Huiyu Wang, Salman Khan, Philipp Krähenbühl, Lorenzo Torresani, Kristen Grauman, Andrea Madotto, Andrew Westbury, Babak Damavandi, Po-Yao Huang, Christoph Feichtenhofer, Daniel Bolya, Effrosyni Mavroudi, Muhammad Maaz, Nikhila Ravi, Peize Sun, Piotr Dollar, Shane Moon, Shashank Jain, Shuming Hu, Suyog Jain, Tammy Stark, Tengyu Ma, Triantafyllos Afouras, Tushar Nagarajan, Jang Hyun Cho, Vivian Lee
April 17, 2025
July 29, 2024
COMPUTER VISION
SAM 2: Segment Anything in Images and Videos
Eric Mintun, Junting Pan, Chao-Yuan Wu, Ross Girshick, Nikhila Ravi, Chay Ryali, Chloe Rolland, Christoph Feichtenhofer, Haitham Khedr, Kalyan Vasudev Alwala, Laura Gustafson, Nicolas Carion, Piotr Dollar, Roman Rädle, Ronghang Hu, Tengyu Ma, Valentin Gabeur, Yuan-Ting Hu
July 29, 2024
August 31, 2023
COMPUTER VISION
FACET: Fairness in Computer Vision Evaluation Benchmark
Laura Gustafson, Aaron Adcock, Candace Ross, Cheng-Yang Fu, Chloe Rolland, Melissa Hall, Nikhila Ravi, Quentin Duval
August 31, 2023
June 20, 2023
COMPUTER VISION
Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild
Garrick Brazil, Abhinav Kumar, Georgia Gkioxari, Julian Straub, Justin Johnson, Nikhila Ravi
June 20, 2023
April 05, 2023
COMPUTER VISION
Segment Anything
Alexander Kirillov, Alex Berg, Chloe Rolland, Eric Mintun, Hanzi Mao, Laura Gustafson, Nikhila Ravi, Piotr Dollar, Ross Girshick, Spencer Whitehead, Wan-Yen Lo, Tete Xiao
April 05, 2023
July 07, 2022
Omnivore: A Single Model for Many Visual Modalities
Ishan Misra, Armand Joulin, Laurens van der Maaten, Mannat Singh, Nikhila Ravi, Rohit Girdhar
July 07, 2022
September 22, 2021
Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis from a Single Image
Ronghang Hu, Alex Berg, Nikhila Ravi, Deepak Pathak
September 22, 2021
September 05, 2019
RESEARCH
C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motion
David Novotny, Andrea Vedaldi, Benjamin Graham, Natalia Neverova, Nikhila Ravi
September 05, 2019
Our approach
Latest news
Foundational models
Meta © 2026