POSTECH-CVLab/SCNeRF
[ICCV21] Self-Calibrating Neural Radiance Fields
This project helps create realistic 3D scenes from a collection of 2D images, even when the camera used has unusual distortions or its exact position is unknown. It takes uncalibrated photos as input and outputs a high-fidelity 3D representation of the scene, allowing for new views to be rendered accurately. This is ideal for researchers or practitioners in computer vision, virtual reality, or 3D reconstruction who work with diverse image sources.
473 stars. No commits in the last 6 months.
Use this if you need to build accurate 3D models or render new views from existing image sets where camera details like lens type or exact capture positions are unknown or imperfect.
Not ideal if you already have perfectly calibrated cameras and precise camera pose information for your image dataset.
Stars
473
Forks
43
Language
Python
License
MIT
Category
Last pushed
Aug 04, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/POSTECH-CVLab/SCNeRF"
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)
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"
HankYe/PAGCP
[T-PAMI'23] PAGCP for the compression of YOLOv5