ucaszyp/STEPS
This is the official repository for ICRA-2023 paper "STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation"
This tool helps autonomous navigation and robotics engineers improve the perception capabilities of self-driving vehicles or robots operating in low-light conditions. It takes nighttime camera images as input and simultaneously enhances their visibility while estimating the distance to objects in the scene. This is crucial for applications where reliable depth information is needed for safe navigation after dark.
194 stars. No commits in the last 6 months.
Use this if you need to perform accurate depth estimation and image enhancement from a single camera's nighttime footage, especially for autonomous driving or robotic navigation tasks.
Not ideal if your primary need is general-purpose photo enhancement for human viewing rather than precise spatial understanding for machine perception.
Stars
194
Forks
11
Language
Python
License
MIT
Category
Last pushed
Feb 13, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ucaszyp/STEPS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
3DOM-FBK/deep-image-matching
Multiview matching with deep-learning and hand-crafted local features for COLMAP and other SfM...
suhangpro/mvcnn
Multi-view CNN (MVCNN) for shape recognition
zouchuhang/LayoutNet
Torch implementation of our CVPR 18 paper: "LayoutNet: Reconstructing the 3D Room Layout from a...
andyzeng/tsdf-fusion-python
Python code to fuse multiple RGB-D images into a TSDF voxel volume.
andyzeng/tsdf-fusion
Fuse multiple depth frames into a TSDF voxel volume.