Meta and World Resources Institute Release Canopy Height Maps v2 Using DINOv3 Self-Supervised Vision Model
Meta AI and the World Resources Institute have released Canopy Height Maps v2 (CHMv2), an open-source global forest mapping system powered by DINOv3, Meta's self-supervised vision model pre-trained on SAT-493M, a large satellite imagery dataset. The new model improves R² accuracy from 0.53 to 0.86 over the previous DINOv2-based version, with better performance on tall trees and greater geographic consistency. CHMv2 is already being adopted by the UK Forestry Commission, the European Commission's Joint Research Centre, and multiple US city planning initiatives. The model, maps, and dataset are publicly available.
Related guides (2)
Related events (8)
Forest Research Deploys DINOv2 for National-Scale Tree Canopy Monitoring in England
Forest Research, the UK Forestry Commission's research agency, is using Meta's DINOv2 computer vision model—trained on 18 million satellite images in collaboration with the World Resources Institute—to build enhanced tree canopy height maps at 1-meter resolution for England. The approach aims to replace expensive LiDAR and survey data with open-source AI-derived canopy height models applied to national aerial photography, enabling rolling three-year monitoring cycles. The deployment supports the UK government's Environmental Improvement Plan targets and the Natural Capital and Ecosystem Assessment program. Meta also announced DINOv3 as a successor to further improve visual intelligence for such applications.
Meta Introduces TRIBE v2: Predictive Foundation Model for Human Brain Activity
Meta AI has released TRIBE v2, a foundation model that predicts high-resolution fMRI brain activity in response to visual, auditory, and language stimuli. Trained on data from over 700 healthy volunteers, it achieves a 70x resolution increase over comparable models and supports zero-shot generalization to new subjects, languages, and tasks. The release includes model weights, codebase, a research paper, and an interactive demo under a CC BY-NC license. Meta positions the work as a bridge between neuroscience and AI development, enabling hypothesis testing without requiring human subjects in every experiment.
Meta releases Llama 3.2 90B Vision multimodal model on Hugging Face
Meta released Llama 3.2 90B Vision, a large multimodal model supporting image-text-to-text tasks, published on Hugging Face under the meta-llama organization. The model is part of the Llama 3.2 family and supports English, German, and French. This is a significant open-weights multimodal release from Meta, extending the Llama 3 series with vision capabilities at the 90B parameter scale.
Orakl Oncology uses Meta's DINOv2 to accelerate cancer organoid analysis and drug response prediction
Orakl Oncology, a spinoff from the Gustave Roussy Institute, has deployed Meta's open-source DINOv2 vision model to analyze cancer organoid images and predict patient drug responses in clinical trials. In collaboration with CentraleSupelec and the Jaulin Lab under the RHU ORGANOMIC initiative, the team found DINOv2 outperformed prior specialized models by 26.8% accuracy. The model enabled quantitative extraction of imaging data from organoid videos, replacing labor-intensive frame-by-frame analysis and significantly accelerating their biomedical platform development.
Meta SAM 3 (Segment Anything Model 3) Released on GitHub
Meta / Facebook Research has released SAM 3, the third generation of their Segment Anything Model, with code for inference and finetuning, pretrained model checkpoints, and example notebooks. The repository has accumulated over 10,000 stars with strong daily momentum (+93). SAM 3 continues Meta's open-weights tradition in computer vision foundation models. No accompanying paper or technical blog post is referenced in this item.
Meta releases Llama 3.2 90B Vision-Instruct multimodal model
Meta released Llama 3.2 90B Vision-Instruct on Hugging Face, a large multimodal model supporting image-text-to-text tasks. The model is part of the Llama 3.2 family and supports English and German. With 858 downloads and 358 likes, it represents Meta's open-weights push into vision-language capabilities at the 90B parameter scale.
FINO: Label-free adaptation of vision foundation models using metadata in scientific domains
Researchers propose FINO, a self-supervised method for adapting vision foundation models to specialized scientific domains without task labels, using metadata as a guidance signal instead. The approach combines a standard self-supervised objective with flexible handling of both discrete and continuous metadata to preserve informative factors while suppressing spurious ones. Evaluated across subcellular fluorescence microscopy, Earth observation, wildlife monitoring, and medical imaging, FINO outperforms both unsupervised domain adaptation and fully supervised fine-tuning, including domain-specific state-of-the-art models.
UPenn PRONTO Team Uses Meta's SAM 2 and DINO for Autonomous Military Medical Triage in DARPA Challenge
The University of Pennsylvania's PRONTO team is applying Meta's Segment Anything Model 2 (SAM 2) and DINO/Grounding DINO models to autonomous robotic triage in DARPA's three-year mass casualty incident challenge. The multi-robot system uses drones and ground robots to locate victims, then runs parallel injury classification pipelines combining SAM, DINO, and pose estimation to assess heart rate, respiration, wounds, and amputations without requiring labeled training data. Results are surfaced to first responders via a mobile interface for real-time prioritization. Phase 2 concluded in October 2025, with Phase 3 expected to push toward deployment-ready performance.