Tech Xplore on MSN

One pull of a string is all it takes to deploy these complex structures

MIT researchers have developed a new method for designing 3D structures that can be transformed from a flat configuration into their curved, fully formed shape with only a single pull of a string.
IEEE

STFNET: Sparse Temporal Fusion for 3D Object Detection in LiDAR Point Cloud

Abstract: In autonomous driving and robotics, 3D object detection using LiDAR point clouds is a critical task. However, existing single-frame 3D object detection methods face challenges such as noise, ...
IEEE

TM2B: Transformer-Based Motion-to-Box Network for 3D Single Object Tracking on Point Clouds

Abstract: 3D single object tracking plays a crucial role in numerous applications such as autonomous driving. Recent trackers based on motion-centric paradigm perform well as they exploit motion cues ...
GitHub

Adding support for SpotLessSplats: Ignoring Distractors in 3D Gaussian Splatting

python spotless_trainer.py --data_dir [data directory] --data_factor 8 --result_dir [result directory] --loss_type robust --no-semantics --no-cluster --train_keyword ...
Scientific American

Two Möbius Strips Combine to Create a Bizarre Object That Only Exists in 4D

In geometry, there are surfaces that do without an inside or outside—and some need at least four dimensions to exist ...
GitHub

AML: Adversarial Meta-Learning for Few-Shot Object Detection

This package includes our codes for implementing "Adversarial Meta-Learning for Few-Shot Object Detection". (First Release Date: 2025-04-13) Please refer to mmfewshot ...