T. Schüppstuhl

AQ3D: Adaptive Query Transformer for 3D Instance Segmentation

This work presents AQ3D, which is designed to handle scenes of various sizes during training and inference and sets a new state-of-the-art on validation and hidden test splits across the datasets ScanNetV2, ScanNet200, and ScanNet++V2 among decoder methods trained without additional data augmentation.