GAP-LAB-CUHK-SZ/MVImgNet
CVPR2023 | MVImgNet: A Large-scale Dataset of Multi-view Images
This project provides a massive collection of multi-view images and associated data, useful for researchers and developers working on 3D computer vision. It offers millions of images of real-world objects from various angles, along with details like camera positions and 3D point clouds. Researchers in fields like robotics, virtual reality, or autonomous driving can use this dataset to train and test algorithms that understand and reconstruct 3D environments from 2D images.
482 stars. No commits in the last 6 months.
Use this if you need a very large, diverse dataset of real-world objects viewed from multiple perspectives, complete with camera parameters and sparse 3D point cloud annotations, for training advanced computer vision models.
Not ideal if you need a small, highly curated dataset for a very specific domain, or if you are looking for dense 3D models rather than sparse point clouds and multi-view images.
Stars
482
Forks
9
Language
—
License
—
Category
Last pushed
Jul 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/GAP-LAB-CUHK-SZ/MVImgNet"
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.