ai4ce/SSCBench
[IROS2024] SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving
SSCBench helps autonomous vehicle researchers develop and evaluate algorithms that understand the complete 3D environment around a self-driving car. It takes raw sensor data from street view scenes (like images and LiDAR scans) and produces a full 3D map where every point is classified (e.g., road, car, building). This benchmark is used by engineers and researchers working on perception systems for autonomous driving.
218 stars. No commits in the last 6 months.
Use this if you are developing or testing algorithms to reconstruct and semantically label entire 3D scenes from partial sensor data in autonomous driving applications.
Not ideal if you need a dataset for general object detection, pedestrian tracking, or other tasks not specifically focused on full 3D scene completion and semantic labeling.
Stars
218
Forks
14
Language
Python
License
—
Category
Last pushed
Apr 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ai4ce/SSCBench"
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