# ialhashim/DenseDepth

High Quality Monocular Depth Estimation via Transfer Learning

Repository: https://github.com/ialhashim/DenseDepth
Canonical: https://ross.abutalabs.com/products/densedepth
Homepage: https://arxiv.org/abs/1812.11941
Language: Jupyter Notebook
License: GPL-3.0
License Family: copyleft
Topics: deep-learning, deep-neural-networks, python, keras-tensorflow, depth-estimation, encoder-decoder-model, transfer-learning, pytorch
Last push: 2022-12-07T05:16:56+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2805, "days_push": 1365, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1606, forks 347 (observed 2026-08-28T04:05:10.488873+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python, cross-platform
- tags: depth-estimation, monocular-depth, encoder-decoder, transfer-learning, keras, pytorch, pretrained-models, nyu-depth-v2, kitti, gpu

## Member repositories
- ialhashim/DenseDepth (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:10.488873+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:52:13.987250+00:00, confidence not recorded.
  - readme: https://github.com/ialhashim/DenseDepth (fetched 2026-08-28T04:05:10.488873+00:00, sha 9650cde213d6)
  - homepage: https://arxiv.org/abs/1812.11941 (fetched 2026-08-29T11:23:53.846555+00:00, sha a6201f48098d)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T11:23:53.855702+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T11:23:53.859695+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T11:23:53.861792+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T11:23:53.857479+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.