worldbench/U4D
[CVPR 2026] U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences
This project helps autonomous systems and robotics engineers create detailed, dynamic 3D models of environments over time from raw LiDAR sensor data. It takes sequences of LiDAR scans as input and generates a comprehensive 4D (3D space + time) representation of the world, identifying and specifically improving areas where the sensor data might be uncertain. This is for engineers and researchers building self-driving cars, drones, or other robots that need to understand and navigate complex, changing surroundings.
Use this if you need to build highly reliable, temporally consistent 4D models of dynamic environments using LiDAR, especially in situations where sensor uncertainty is a significant challenge.
Not ideal if you are working with static environments, need 2D mapping, or primarily use camera-based vision systems instead of LiDAR.
Stars
13
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 20, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/worldbench/U4D"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ZiYang-xie/WorldGen
🌍 WorldGen - Generate Any 3D Scene in Seconds
aioz-ai/AIOZ-GDANCE
AIOZ-GDANCE: a large-scale dataset & baseline for music-driven group dance generation. (CVPR 2023)
worldbench/WorldLens
[CVPR 2026] WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World
Kobaayyy/Awesome-CVPR2026-CVPR2025-ICCV2025-CVPR2024-ECCV2024-AIGC
A Collection of Papers and Codes for CVPR2026/CVPR2025/ICCV2025/CVPR2024/ECCV2024 AIGC
nv-tlabs/XCube
[CVPR 2024 Highlight] XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies