jspenmar/slowtv_monodepth

Official repository for the ICCV2023 paper "Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTV"

33
/ 100
Emerging

This project helps computer vision researchers and developers estimate the depth of objects in a single image. You input a standard 2D image or video frame, and it outputs a corresponding depth map, showing how far each part of the scene is from the camera. This is particularly useful for those working on 3D reconstruction and scene understanding without relying on expensive ground-truth depth data.

No commits in the last 6 months.

Use this if you need to generate accurate depth maps from single images, especially when ground-truth depth data for training is scarce or unavailable.

Not ideal if your primary goal is to perform 3D reconstruction using multiple views or stereo vision, or if you already have access to high-quality ground-truth depth sensors.

3D Reconstruction Computer Vision Monocular Depth Estimation Scene Understanding Image Analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

85

Forks

5

Language

Python

License

Last pushed

Mar 05, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/jspenmar/slowtv_monodepth"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.