irolaina/FCRN-DepthPrediction

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1118 stars · 305 forks observed · 2026-08-28

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

Reference implementation and pretrained models for FCRN (Deeper Depth Prediction with Fully Convolutional Residual Networks), predicting depth maps from single RGB images. Provides TensorFlow and MatConvNet code for inference on arbitrary images and evaluation on NYU Depth v2 and Make3D benchmarks.

Use cases

• predict depth map from a single rgb image
• estimate monocular depth with a pretrained cnn
• evaluate depth prediction on nyu depth v2
• benchmark depth estimation on make3d
• run fcrn inference in tensorflow
• get depth maps for robotics or 3d reconstruction

When to choose

• you need the original FCRN paper models for research reproduction
• you want pretrained monocular depth estimation in TensorFlow or MatConvNet
• you need to benchmark against NYU Depth v2 or Make3D results

When to avoid

• you need actively maintained or modern depth estimation models
• you want production-ready deployment with recent framework versions
• you need training code rather than inference
• you prefer newer architectures like MiDaS or Depth Anything

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing computer-vision machine-learning deep-learning robotics python cpp cross-platform depth-estimation monocular-depth tensorflow matconvnet fcrn nyu-depth-v2 research-code inference

Member repositories

For agents

markdown · JSON · MCP: product_card(name="irolaina/FCRN-DepthPrediction")