dwofk/fast-depth

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1023 stars · 189 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

FastDepth is the official PyTorch implementation of the ICRA 2019 paper 'FastDepth: Fast Monocular Depth Estimation on Embedded Systems' from MIT. It provides trained MobileNet-based models, evaluation code on the NYU Depth V2 dataset, and guidance for deploying real-time monocular depth estimation on embedded devices like Jetson boards.

Use cases

• estimate depth from a single RGB image
• run real-time monocular depth estimation on embedded hardware like Jetson TX2
• evaluate depth estimation models on the NYU Depth V2 dataset
• use a lightweight pruned MobileNet depth network for robotics
• benchmark fast depth estimation networks on CUDA GPUs
• deploy a depth estimation model with TensorRT on an embedded system

When to choose

• you need fast monocular depth estimation on resource-constrained embedded hardware
• you want pretrained lightweight depth estimation models with evaluation code
• you are doing robotics research that requires real-time depth from a single camera

When to avoid

• you need state-of-the-art depth accuracy rather than speed
• you need stereo or multi-frame depth estimation
• you need actively maintained code on recent PyTorch versions

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing computer-vision machine-learning robotics embedded-systems python embedded depth-estimation monocular-depth mobilenet pytorch embedded-systems icra-2019 model-pruning nyu-depth-v2 linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="dwofk/fast-depth")