tinghuiz/SfMLearner

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2017 stars · 554 forks observed · 2026-08-28

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

SfMLearner is a TensorFlow implementation of the CVPR 2017 paper 'Unsupervised Learning of Depth and Ego-Motion from Video'. It trains models to predict single-view depth and camera ego-motion from monocular video sequences without ground-truth labels.

Use cases

• estimate depth from monocular video with a neural network
• train a self-supervised depth prediction model on KITTI
• predict camera ego-motion from image sequences
• run single-view depth prediction demo on pretrained model
• learn visual odometry without ground truth poses
• reproduce unsupervised SfM learning research results

When to choose

• you need a research baseline for unsupervised depth and pose estimation
• you have monocular video from KITTI or Cityscapes and no labeled depth data
• you want to study or extend self-supervised structure-from-motion learning

When to avoid

• you need production-ready depth estimation with modern architectures
• you require recent TensorFlow or GPU stack support (built for TF 1.0 / CUDA 8)
• you need real-time visual odometry for deployment rather than research

Facets

library · maturity maintenance

deep-learning computer-vision machine-learning computer-vision deep-learning autonomous-vehicles robotics python depth-estimation ego-motion visual-odometry self-supervised-learning monocular-video tensorflow research-code kitti cityscapes linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="tinghuiz/SfMLearner")