Intellindust-AI-Lab/GTR

[TMLR 26] EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation

Reference PyTorch implementation and models for DINOv3

This is an official implementation for "AutoFocusFormer: Image Segmentation off the Grid".

Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation

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 show how to use the model.

Self-supervised learning for spatial perception

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

Ultralytics YOLO26 quickstart for detection, instance and semantic segmentation, depth estimation, classification, pose, OBB, and tracking.