Abstract Delivers InstaLOD 2026: Redefining Geometry Optimization for Real-Time 3D

InstaLOD 2026 simplifies and scales 3D asset preparation, helping teams move from source data to production-ready ...
IEEE

Accurate Pose Refinement of Detected Vehicles Using LiDAR Point-to-Surfel ICP and Vehicle Shape Priors

Abstract: This letter proposes an accurate pose refinement system that integrates point cloud registration and vehicle prior shapes to improve LiDAR-based vehicle pose estimation. For safe autonomous ...
GitHub

Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors

Previous research has investigated the application of Multimodal Large Language Models (MLLMs) in understanding 3D scenes by interpreting them as videos. These approaches generally depend on ...
IEEE

Jianqiang Wang

School of Vehicle and Mobility, Tsinghua University, Beijing, China State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China 3D Bounding Box,3D Detection,3D ...

Ring denies being 'mass surveillance' but AI dog tracking will continue

Ring’s been in damage-control mode ever since its now-infamous “lost dog” Super Bowl ad, furiously spinning the sinister ...
GitHub

ProMi: An Efficient Prototype-Mixture Baseline for Few-Shot Segmentation with Bounding-Box Annotations

@article{chiaroni2025promi, title={ProMi: An Efficient Prototype-Mixture Baseline for Few-Shot Segmentation with Bounding-Box Annotations}, author={Chiaroni, Florent and Ayub, Ali and Ahmad, Ola}, ...