# Visual Scene Understanding

Distill-Any-Depth is a SOTA monocular depth estimation model trained based on knowledge distillation algorithms, capable of efficient and accurate depth estimation.

LLaVA-SpaceSGG is a visual question-answering model based on LLaVA-v1.5-13b, focusing on scene graph generation tasks. It can understand image content and generate structured scene descriptions.

DPT model using DINOv2 as the backbone network for monocular depth estimation tasks