Stars
SPAR: Single-Pass Any-Resolution ViT for Open-vocabulary Segmentation
Efficient Universal Perception Encoder: a single on-device vision encoder with versatile representations that match or exceed specialized experts across multiple task domains.
[ICLR '26 Oral] Official repository of the paper "AnyUp: Universal Feature Upsampling".
[CVPR 2026] Official Code for "UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders"
Fields of The World — interactive browser demo for field boundary delineation
Seg2Change: Adapting Open-Vocabulary Semantic Segmentation Model for Remote Sensing Change Detection
[CVPR'26] AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors
Exploring Generalizable Remote Sensing Change Detection via Low-Rank Exchange Adaptation of Vision Foundation Model (AAAI 2026)
Official repository for "AM-RADIO: Reduce All Domains Into One"
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
[ESSD 2025 & IEEE DFC 2025 & CVPRW 2026] Bright: A globally distributed multimodal VHR dataset for all-weather disaster response
Official implementation of EoCD: Encoder only Remote Sensing Change Detection (CVPR Findings 2026)
This repo includes codes for Working with Satellite Data: An Introduction to Google Earth Engine
Techniques for deep learning with satellite & aerial imagery
Muggled SAM: Segmentation without the magic
[CVPR 2026 - Highlight] Official Implementation of "Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation?"
Repository for Brewing Stronger Features: Dual-Teacher Distillation for Multispectral Earth Observation [CVPR 2026 Highlight].
[ICME2024 Oral, JSTARS2025, TGRS2026] Change detection of remote sensing images
A unsupervised change detection framework based on contrastive learning.
Convert planar diagram codes of knots, links and spatial graphs to planar diagrams using circle packing and circular arcs.
[JAG 2026] DreamCD: A change-label-free framework for change detection via a weakly conditional semantic diffusion model in optical VHR imagery