LitePT: Lighter Yet Stronger Point Transformer

Code for "Human Pose Regression with Residual Log-likelihood Estimation", ICCV 2021 Oral

Sharp Monocular View Synthesis in Less Than a Second

(WIP) AerialExtreMatch: A Benchmark for Extreme-View Image Matching and Localization

OAM Imagery browser

SegEarth-OV3: Exploring SAM 3 for Open-Vocabulary Semantic Segmentation in Remote Sensing Images

RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization

ZoomEarth: Active Perception for Ultra-High-Resolution Geospatial Vision-Language Tasks

Finding Good Configurations of Planar Primitives, CVPR2022. Code from https://team.inria.fr/titane/software/

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

This repository contains the official implementation of the paper "LandSegmenter: Towards a Flexible Foundation Model for Land Use and Land Cover Mapping".

[ICCV2025 Highlight]: SGAD: Semantic and Geometric-aware Descriptor for Local Feature Matching

Official repository for "AM-RADIO: Reduce All Domains Into One"

[CVPR 2025 Oral] SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images

[NeurIPS 2026 - Oral] Official implementation of 'OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic Geodata‘.

Falcon: A Remote Sensing Vision-Language Foundation Model

Multimodal Image Matching Framework

MapGlue: Multimodal Remote Sensing Image Matching

CurriculumLoc for Visual Geo-localization

[NeurIPS 2025] Official repository for "ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation"

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

MapAnything: Universal Feed-Forward Metric 3D Reconstruction