FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation

PhysInOne: Visual Physics Learning and Reasoning in One Suite

EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision

GrowSP++: Growing Superpoints and Primitives for Unsupervised 3D Semantic Segmentation

GrabS: Generative Embodied Agent for 3D Object Segmentation without Scene Supervision

LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Clouds

unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning

Boundary-aware Multiclass Spinal Cord Tumor Segmentation on 3D MRI Scans

Adaptive Representation Learning and Sample Weighting for Low-Quality 3D Face Recognition

GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds

Meta-learning-based adversarial training for deep 3D face recognition on point clouds

Learning Flexibly Distributional Representation for Low-quality 3D Face Recognition

Learning Distribution Independent Latent Representation for 3D Face Disentanglement