yitongx/sinerf
SiNeRF: Sinusoidal Neural Radiance Fields for Joint Pose Estimation and Scene Reconstruction
This project helps computer vision researchers and 3D graphics professionals reconstruct complex 3D scenes from a series of 2D images. You input a collection of images of an object or scene taken from various angles. The output is a highly detailed 3D model of the scene and an accurate estimation of the camera positions (poses) where each input image was taken.
No commits in the last 6 months.
Use this if you need to create precise 3D models and simultaneously determine camera viewpoints from a collection of uncalibrated 2D images.
Not ideal if you're looking for a simple point-and-click solution for everyday photography or if you don't have experience with programming environments.
Stars
32
Forks
1
Language
Python
License
—
Category
Last pushed
Jul 09, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/yitongx/sinerf"
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"