AI4CE Lab @ NYU

CityWalker

[CVPR2025] CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos

DeepMapping

[CVPR2019 Oral] Self-supervised Point Cloud Map Estimation

DeepMapping2

[CVPR2023] DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization

DiscoNet

[NeurIPS2021] Learning Distilled Collaboration Graph for Multi-Agent Perception

GARF

[ICCV2025] GARF: Learning Generalizable 3D Reassembly for Real-World Fractures

insta360_ros_driver

A ROS driver for Insta360 cameras, enabling real-time image capture, processing, and publishing in ROS environments.

MSG

[NeurIPS2024] Multiview Scene Graph (topologically representing a scene from unposed images by interconnected place and object nodes)

Occ4cast

Occ4cast: LiDAR-based 4D Occupancy Completion and Forecasting

peac

[ICRA2014] Fast Plane Extraction Using Agglomerative Hierarchical Clustering (AHC)

SSCBench

[IROS2024] SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving

ai4ce/SSCBench

[IROS2024] SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving

ai4ce/Occ4cast

Occ4cast: LiDAR-based 4D Occupancy Completion and Forecasting

ai4ce/CityWalker

[CVPR2025] CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos

ai4ce/V2X-Sim

[RA-L2022] V2X-Sim Dataset and Benchmark

ai4ce/insta360_ros_driver

A ROS driver for Insta360 cameras, enabling real-time image capture, processing, and publishing in ROS environments.

ai4ce/MSG

[NeurIPS2024] Multiview Scene Graph (topologically representing a scene from unposed images by interconnected place and object nodes)

ai4ce/GARF

[ICCV2025] GARF: Learning Generalizable 3D Reassembly for Real-World Fractures

ai4ce/SeeDo

[IROS 2025] Human Demo Videos to Robot Action Plans

ai4ce/EUVS-Benchmark

[ICCV2025] Extrapolated Urban View Synthesis Benchmark

ai4ce/FusionSense

[ICRA2025] Integrates the vision, touch, and common-sense information of foundational models, customized to the agent's perceptual needs.

ai4ce/RAP

[ICCV2025] Adversarial Exploitation of Data Diversity Improves Visual Localization

ai4ce/NYU-VPR

[IROS2021] NYU-VPR: Long-Term Visual Place Recognition Benchmark with View Direction and Data Anonymization Influences

ai4ce/INT-ACT

Official repo for From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models

ai4ce/NYC-Event-VPR

ai4ce/TF-VPR

Self-supervised place recognition by exploring temporal and feature neighborhoods

ai4ce/NYC-Indoor-VPR

ai4ce/EgoPAT3Dv2

[ICRA 2024] Official Implementation of EgoPAT3Dv2: Predicting 3D Action Target from 2D Egocentric Vision for Human-Robot Interaction

ai4ce/vis_nav_player

[ROB-GY 6203] Example Visual Navigation Player Code for Course Project

ai4ce/LUWA

[CVPR 2024 Highlight] The first benchmark for lithic use-wear analysis leveraging SOTA vision and vision-language models (DINOv2, GPT-4V), demonstrating AI performance surpassing that of expert archaeologists.

ai4ce/LoQI-VPR

Implementation of the ICCV workshop paper LoQI-VPR. Project website available below

ai4ce/UNav-Server

ai4ce/SeeUnsafe

Integrate language and vision for traffic accident identification, reasoning, and visual grounding

ai4ce/ai4ce_sensor_ROS2_interfaces

This repo contains all the ROS2 packages developed at AI4CE lab for interfacing with various specialized sensors

ai4ce/ai4ce_project_website_template

A project website template

ai4ce/CoVISION

Co-VisiON: Co-Visibility ReasONing on Sparse Image Sets of Indoor Scenes

ai4ce/DPVO

DPVO accompanying the CityWalker repository

ai4ce/folder2hdf5

A sample codebase for converting folder dataset to a hdf5 dataset

ai4ce/gelsight_ROS2_interface

ai4ce/joy_hand_eye_ROS2

This minimal package can be used to perform hand-eye-calibration in a ROS2 environment with a joystick

ai4ce/vis_nav_game_public

Public version of vis_nav_game