ialhashim/DenseDepth

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1606 stars · 347 forks observed · 2026-08-28

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

Official Keras/TensorFlow implementation (with experimental PyTorch and TF2 code) of the DenseDepth paper for high-quality monocular depth estimation from a single RGB image via transfer learning. It includes pre-trained models for NYU Depth V2 and KITTI, training scripts, a Colab notebook, and a Qt demo rendering 3D point clouds from estimated depth.

Use cases

• estimate depth maps from single rgb images
• run monocular depth estimation with pretrained models
• generate 3d point clouds from a webcam or image
• train a depth estimation network on nyu depth v2 or kitti
• try depth estimation in a colab notebook

When to choose

• you need high-resolution depth maps from single images using a simple, well-cited encoder-decoder model
• you want pretrained NYU Depth V2 or KITTI depth models with Keras or PyTorch code
• you want a quick demo turning depth maps into 3D point clouds

When to avoid

• you need state-of-the-art depth estimation - the authors recommend AdaBins instead
• you need actively maintained code on modern TensorFlow/PyTorch versions
• you need stereo, video, or multi-frame depth rather than monocular estimation

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing computer-vision deep-learning machine-learning python cross-platform depth-estimation monocular-depth encoder-decoder transfer-learning keras pytorch pretrained-models nyu-depth-v2 kitti gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ialhashim/DenseDepth")