Adam Harley

I am a Research Scientist at Meta, working on computer vision and machine learning. I am trying to get computers to understand motion and space.

Before Meta, I did a postdoc with Prof. Leonidas Guibas at Stanford University, and a Ph.D. in Robotics at Carnegie Mellon University with Prof. Katerina Fragkiadaki. Before that, I did a Master of Science in computer science, with Prof. Kosta Derpanis. Even earlier, I did a Bachelor of Arts in psychology.

Google Scholar Twitter Github CV

aharley@meta.com

Adam Harley

I am a Research Scientist at Meta, working on computer vision and machine learning. I am trying to get computers to understand motion and space.

Before Meta, I did a postdoc with Prof. Leonidas Guibas at Stanford University, and a Ph.D. in Robotics at Carnegie Mellon University with Prof. Katerina Fragkiadaki. Before that, I did a Master of Science in computer science, with Prof. Kosta Derpanis. Even earlier, I did a Bachelor of Arts in psychology.

Scholar Twitter Github CV

aharley@meta.com

News

I will give invited talks at two CVPR 2025 workshops: 4D Vision and Pixel-Level Vision Foundation Models.
I will serve as an Area Chair for 3DV 2025, WACV 2025, ICML 2025, NeurIPS 2025, and Action Editor for TMLR.
I gave a talk at the CV4Animals Workshop at CVPR 2024!
I served as an Area Chair for NeurIPS 2024.
I gave a talk at the Workshop on Large-scale Video Object Segmentation at ICCV 2023.
I gave a talk at the VOTS workshop at ICCV 2023.
I served as an Area Chair for WACV 2024.
I gave a talk at the Tracking and Its Many Guises workshop at CVPR 2023.
I gave a talk at the 3D Deep Learning for Automated Driving workshop at the Intelligent Vehicles Symposium 2023.
I gave a talk at the Self-Supervision on Wheels tutorial at ECCV 2022.
I co-organized Perception Through Structured Generative Models at ECCV 2020.
I co-organized Minds vs. Machines: How far are we from the common sense of a toddler? at CVPR 2020.

Publications

EgoPoints: Advancing Point Tracking for Egocentric Videos

WACV 2025

Ahmad Darkhalil, Rhodri Guerrier, Adam W. Harley, Dima Damen

project page paper code

Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular Videos

SIGGRAPH Asia 2024

Colton Stearns, Adam W. Harley, Mikaela Uy, Florian Dubost, Federico Tombari, Gordon Wetzstein, Leonidas Guibas

project page paper code

TAG: Tracking at Any Granularity

(draft)

Adam W. Harley, Yang You, Alex Sun, Yang Zheng, Nikhil Raghuraman, Sheldon Liang, Wen-Hsuan Chu, Suya You, Achal Dave, Pavel Tokmakov,  Rares Ambrus, Katerina Fragkiadaki, Leonidas Guibas

project page paper

View-Consistent Hierarchical 3D Segmentation Using Ultrametric Feature Fields

ECCV 2024

Haodi He, Adam W. Harley, Colton Stearns, Leonidas Guibas,

paper

MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds

arXiv 2024

Jiahui Lei, Yijia Weng, Adam W. Harley, Leonidas Guibas, Kostas Daniilidis

project page paper

Zero-Shot Image Feature Consensus with Deep Functional Maps

ECCV 2024

Xinle Cheng, Congyue Deng, Adam W. Harley, Yixin Zhu, Leonidas Guibas

paper

ODIN: A Single Model for 2D and 3D Perception

CVPR 2024

Ayush Jain, Pushkal Katara, Nikolaos Gkanatsios, Adam W. Harley, Gabriel Sarch, Kriti Aggarwal, Vishrav Chaudhary, Katerina Fragkiadaki

project page paper

Wing buzzing as a mechanism for generating vibrational signals in psyllids (Hemiptera: Psylloidea)

Insect Science 2024

Jernej Polajnar, Elizaveta Kvinikadze, Adam W. Harley, Igor Malenovsky

paper

Refining Pre-Trained Motion Models

ICRA 2024

Xinglong Sun, Adam W. Harley, Leonidas J. Guibas

project page paper code

PACE: Pose Annotations in Cluttered Environments

ECCV 2024

Yang You, Kai Xiong, Zhening Yang, Zhengxiang Huang, Junwei Zhou, Ruoxi Shi, Zhou Fang, Adam W. Harley, Cewu Lu

project page paper code/data

Zero-Shot Open-Vocabulary Tracking with Large Pre-Trained Models

ICRA 2024

Wen-Hsuan Chu, Adam W. Harley, Pavel Tokmakov, Achal Dave, Leonidas J. Guibas, Katerina Fragkiadaki

project page paper code

Cross-Image Context Matters for Bongard Problems

arXiv 2023

Nikhil Raghuraman, Adam W. Harley, Leonidas J. Guibas

project page paper code

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking

ICCV 2023 (Oral)

Yang Zheng, Adam W. Harley, Bokui Shen, Gordon Wetzstein, Leonidas J. Guibas

project page paper simulator code model code

Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?

ICRA 2023

Adam W. Harley, Zhaoyuan Fang, Jie Li, Rares Ambrus, Katerina Fragkiadaki

project page paper code

TIDEE: Tidying Up Novel Rooms using Visuo-Semantic Commonsense Priors

ECCV 2022 (Winner of "Embodied AI Rearrangement Challenge" @ CVPR 2023)

Gabriel Sarch, Zhaoyuan Fang, Adam W. Harley, Paul Schydlo, Michael J. Tarr, Saurabh Gupta, Katerina Fragkiadaki,

project page paper code blog

Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories

ECCV 2022 (Oral)

Adam W. Harley, Zhaoyuan Fang, Katerina Fragkiadaki

project page paper code blog

Track, Check, Repeat: An EM Approach to Unsupervised Tracking

CVPR 2021

Adam W. Harley, Yiming Zuo, Jing Wen, Ayush Mangal, Shubhankar Potdar, Ritwick Chaudhry, Katerina Fragkiadaki

project page paper code

CoCoNets: Continuous Contrastive 3D Scene Representations

CVPR 2021

Shamit Lal, Mihir Prabhudesai, Ishita Mediratta, Adam W. Harley, Katerina Fragkiadaki

project page paper code

Move to See Better: Self-Improving Embodied Object Detection

BMVC 2021

Zhaoyuan Fang, Ayush Jain, Gabriel Sarch, Adam W. Harley, Katerina Fragkiadaki

project page paper code

Disentangling 3D Prototypical Networks For Few-Shot Concept Learning

ICLR 2021

Mihir Prabhudesai, Shamit Lal, Darshan Patil, Hsiao-Yu Fish Tung, Adam W. Harley, Katerina Fragkiadaki

project page paper

Tracking Emerges by Looking Around Static Scenes, with Neural 3D Mapping

ECCV 2020

Adam W. Harley, Shrinidhi KL, Paul Schydlo, Katerina Fragkiadaki

paper ECCV Daily interview

3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations

CVPR workshops 2020

Mihir Prabhudesai, Shamit Lal, Hsiao-Yu Fish Tung, Adam W. Harley, Shubhankar Potdar, Katerina Fragkiadaki

project page paper workshop paper

Embodied Language Grounding With 3D Visual Feature Representations

CVPR 2020

Mihir Prabhudesai, Hsiao-Yu Fish Tung, Syed Ashar Javed, Maximilian Sieb, Adam W. Harley, Katerina Fragkiadaki

project page paper

Learning from Unlabelled Videos Using Contrastive Predictive Neural 3D Mapping

ICLR 2020

Adam W. Harley, Fangyu Li, Shrinidhi K. Lakshmikanth, Xian Zhou, Hsiao-Yu Fish Tung, Katerina Fragkiadaki

project page paper code

VR Facial Animation via Multiview Image Translation

SIGGRAPH 2019

Shih-En Wei, Jason Saragih, Tomas Simon, Adam W. Harley, Stephen Lombardi, Michal Perdoch, Alexander Hypes, Dawei Wang, Hernan Badino, Yaser Sheikh

project page paper

Image Disentanglement and Uncooperative Re-Entanglement for High-Fidelity Image-to-Image Translation

ICCV 2019 AIM workshop (Advances in Image Manipulation)

Adam W. Harley, Shih-En Wei, Jason Saragih, and Katerina Fragkiadaki

paper

Reward Learning from Narrated Demonstrations

CVPR 2018

Hsiao-Yu Fish Tung, Adam W. Harley, Liang-Kang Huang, and Katerina Fragkiadaki

paper

Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervision

ICCV 2017

Hsiao-Yu Fish Tung*, Adam W. Harley*, William Seto*, and Katerina Fragkiadaki

paper

Segmentation-Aware Convolutional Networks Using Local Attention Masks

ICCV 2017

Adam W. Harley, Konstantinos G. Derpanis, and Iasonas Kokkinos

project page paper code

Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothness

ECCV Workshops 2016

Jason J. Yu, Adam W. Harley, and Konstantinos G. Derpanis

project page paper

Segmentation-Aware Convolutional Nets

Master's Thesis (2016)

Adam W. Harley (Advised by Konstantinos G. Derpanis)

project page paper

Learning Dense Convolutional Embeddings for Semantic Segmentation

ICLR 2016 (Workshop)

Adam W. Harley, Konstantinos G. Derpanis, and Iasonas Kokkinos

project page paper

Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval

ICDAR 2015 (Best Student Paper Award)

Adam W. Harley, Alex Ufkes, and Konstantinos G. Derpanis

project page paper RVL-CDIP Dataset HuggingFace integration

An Interactive Node-Link Visualization of Convolutional Neural Networks

ISVC 2015

Adam W. Harley

project page paper PopSci article

The Effect of Cognitive Switching on Sustained Attention

Undergraduate Thesis (2012)

Adam W. Harley (Advised by Benjamin Dyson)

paper