Unverified50% confidenceFactExact time
The 3D model was trained on 186,000 aerial and ground images and 15 billion radar point cloud points, ultimately generating 6.2 billion Gaussian ellipsoids, with reconstruction geometric accuracy reaching the centimeter level and reconstruction error better than 2cm.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe Kepler Space Telescope accumulated continuous light curve data for more than 200,000 stars over the course of its mission.64% similarUnverifiedWorld Monitor aggregates more than 500 data sources onto a real-time map with AI briefings, is referred to as an open-source Palantir, can overlay more than 50 layers, and supports switching between 2D maps and a 3D globe.62% similarUnverifiedGrid-sampling the Earth's surface at 1-kilometer intervals yields approximately 510 million sample points.62% similarUnverifiedThe dataset from Ukraine's Avengers Labs data platform contains approximately 5 million annotated images; the system trained on it processes over 100,000 drone video streams per month, identifies enemy equipment with approximately 70% accuracy, and takes 2.2 seconds to identify a single target.60% similarUnverifiedSA-1B 数据集包含约 1100 万张图像和超过 10 亿个自动生成的高质量掩膜59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1016574API
curl https://kongchang.com/api/v1/knowledge/claims/1016574MCP
get_claim(id=1016574)