# piiswrong/deep3d

Automatic 2D-to-3D Video Conversion with CNNs

Repository: https://github.com/piiswrong/deep3d
Canonical: https://ross.abutalabs.com/products/deep3d
Language: Jupyter Notebook
License Family: other
Last push: 2016-05-04T02:58:10+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": 3805, "days_push": 3773, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1299, forks 254 (observed 2026-08-28T04:04:17.376947+00:00)

## What it is
Deep3D is a CNN-based research project that automatically converts 2D images and videos into 3D by estimating per-pixel depth maps and generating stereo views. It is implemented as custom MXNet operators with Jupyter Notebook examples.

## Use cases
- convert 2d video to 3d automatically
- estimate depth map from a single image
- generate stereo image pairs from 2d photos
- make 3d gifs from regular photos
- research on single-image depth estimation with cnns

## When to avoid
- you need a maintained, production-ready 2D-to-3D converter
- you cannot build legacy MXNet with CUDA 7.0 and cuDNN 4
- you want modern deep learning frameworks or pretrained easy-to-use models

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, image-processing, video-processing, computer-vision
- domain: deep-learning, computer-vision, image-processing
- platform: python
- tags: depth-estimation, 2d-to-3d, mxnet, stereo-vision, research-code, cnn, video, gpu, linux

## Member repositories
- piiswrong/deep3d (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:17.376947+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 2026-08-30T04:53:27.201850+00:00, confidence not recorded.
  - readme: https://github.com/piiswrong/deep3d (fetched 2026-08-28T04:04:17.376947+00:00, sha 9de97694650a)
- Data as of 2026-08-30T08:39:29.467469+00:00.