NVlabs/ParallelInversion
Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation (ICRA 2023)
This project helps robotics engineers and computer vision researchers precisely locate a camera in 3D space relative to an object or scene using just a single image. It takes an observed RGB image and a pre-trained Neural Radiance Field (NeRF) model of the target, then outputs the camera's exact 6-DoF position and orientation. This is useful for tasks requiring highly accurate camera pose estimation, especially in complex environments.
No commits in the last 6 months.
Use this if you need robust and efficient 6-DoF camera pose estimation from a single image for robotics or augmented reality applications, even in challenging conditions.
Not ideal if you only have traditional 2D images without a corresponding NeRF model of the scene, or if you need real-time performance on embedded systems without powerful GPUs.
Stars
35
Forks
4
Language
Cuda
License
—
Category
Last pushed
Oct 02, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/NVlabs/ParallelInversion"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
weiyithu/NerfingMVS
[ICCV 2021 Oral] NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo
Jumpat/SegmentAnythingin3D
Segment Anything in 3D with NeRFs (NeurIPS 2023 & IJCV 2025)
POSTECH-CVLab/SCNeRF
[ICCV21] Self-Calibrating Neural Radiance Fields
half-potato/nmf
Our method takes as input a collection of images (100 in our experiments) with known cameras,...
synthesiaresearch/humanrf
Official code for "HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion"