bertjiazheng/Structured3D
[ECCV'20] Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling
This dataset offers 3.5K professionally designed house layouts, complete with comprehensive 3D structural annotations and photo-realistic 2D images. It provides detailed ground truth information like semantics, depth, and surface normals for each design. Architectural visualizers, interior designers, or researchers working on 3D modeling and reconstruction would find this valuable for developing and testing their algorithms.
654 stars. No commits in the last 6 months.
Use this if you need a diverse, large-scale collection of interior house designs with detailed 3D structural data and corresponding high-quality 2D renderings for training or evaluating computer vision models.
Not ideal if you are looking for outdoor scene data or real-world scanned environments rather than synthetic, designer-created interiors.
Stars
654
Forks
73
Language
Python
License
MIT
Category
Last pushed
Feb 24, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/bertjiazheng/Structured3D"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
drprojects/superpoint_transformer
Official PyTorch implementation of Superpoint Transformer introduced in [ICCV'23] "Efficient 3D...
yuxumin/PoinTr
[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
charlesq34/frustum-pointnets
Frustum PointNets for 3D Object Detection from RGB-D Data
drprojects/DeepViewAgg
[CVPR'22 Best Paper Finalist] Official PyTorch implementation of the method presented in...
facebookresearch/votenet
Deep Hough Voting for 3D Object Detection in Point Clouds