shariqfarooq123/AdaBins
Official implementation of Adabins: Depth Estimation using adaptive bins
AdaBins helps autonomous systems, robotics engineers, and computer vision researchers understand the three-dimensional world from a single camera image. It takes a standard RGB color image and outputs a detailed depth map, showing how far away each object in the scene is. This allows systems to perceive spatial relationships and navigate environments more effectively.
782 stars. No commits in the last 6 months.
Use this if you need to quickly and accurately estimate the distance of objects in a scene using only a single 2D camera image.
Not ideal if your application requires active depth sensing (like lidar or stereo cameras) for extremely precise measurements or operates in environments with very poor lighting where a standard RGB image would fail.
Stars
782
Forks
160
Language
Python
License
GPL-3.0
Category
Last pushed
May 29, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/shariqfarooq123/AdaBins"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
cvg/LightGlue
LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
amusi/CVPR2026-Papers-with-Code
CVPR 2026 论文和开源项目合集
isl-org/ZoeDepth
Metric depth estimation from a single image
daviddmc/NeSVoR
NeSVoR is a package for GPU-accelerated slice-to-volume reconstruction.
SkalskiP/top-cvpr-2023-papers
This repository is a curated collection of the most exciting and influential CVPR 2023 papers. 🔥...