(Models) Depth Anything V2 테스트

Mnocular Depth Estimation 모델인 Depth Anything V2의 환경구축 및 테스트

실행 환경

• CPU: Intel(R) Xeon(R) w5-3423 @ 12cores
• RAM: 256GB
• OS: Ubuntu-22.04 LTS
• GPU: NVIDIA RTX A6000 x 2ea
• CUDA Toolkit: CUDA 11.8, cuDNN 8.9.7
• 날짜: 2026.03.31.

---

Depth Anything V2 환경구축

git source download

• git: GitHub - DepthAnything/Depth-Anything-V2: [NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation · GitHub

git clone https://github.com/DepthAnything/Depth-Anything-V2

pip install

cd Depth-Anything-V2
pip install -r requirements.txt

pre-trained models download

Model	Params	Checkpoint
Depth-Anything-V2-Small	24.8M	Download
Depth-Anything-V2-Base	97.5M	Download
Depth-Anything-V2-Large	335.3M	Download
Depth-Anything-V2-Giant	1.3B	Coming soon

• 다운로드 받은 model은 /Depth-Anything-V2/checkpoints/ 에 위치하도록함

Depth Anything V2 테스트

Inference

• inference script

# Running script on images
python run.py \
  --encoder <vits | vitb | vitl | vitg> \
  --img-path <path> --outdir <outdir> \
  [--input-size <size>] [--pred-only] [--grayscale]
  
# Running script on videos
python run_video.py \
  --encoder <vits | vitb | vitl | vitg> \
  --video-path assets/examples_video --outdir video_depth_vis \
  [--input-size <size>] [--pred-only] [--grayscale]

• vitb 모델 테스트

python run.py --encoder vitb --img-path assets/examples --outdir depth_vis

Results