Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
3
0
4
Open-vocabulary 3D LiDAR segmentation now leverages point transformers for outdoor scenes, achieving SOTA without manual annotation or geometric pre-training.
Adversarial patches can be optimized for maximum impact with minimal queries, revealing critical trade-offs in their design and effectiveness against object detectors.
You can achieve near state-of-the-art accuracy on 3D point cloud recognition with a model that's 5-28x smaller than current methods, thanks to a novel geometry-adaptive architecture.