UnderOneFacade is a large-scale cross-continent 3D facade point cloud benchmark with harmonized labels that reveals existing segmentation models achieve at most 33 IoU on fine-grained architectural elements and degrade across geographic domains.
In: Proceed- ings of the IEEE/CVF international conference on computer vision
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CV 4representative citing papers
COSY uses independent per-component 3DGS generators plus context tokens to achieve disentangled semantic editing of human heads without masks or classifiers.
A bidirectional cross-attention point transformer deforms a heart atlas into a 3D four-chamber mesh from sparse cardiac MRI point clouds using locally affine diffeomorphic flows.
Presents an SSM-based hierarchical feature learning method for medical point clouds that reports superior performance on classification, completion, and segmentation using a new dataset MedPointS.
citing papers explorer
-
UnderOneFacade: Worldwide Facade Semantic Segmentation Benchmark Dataset
UnderOneFacade is a large-scale cross-continent 3D facade point cloud benchmark with harmonized labels that reveals existing segmentation models achieve at most 33 IoU on fine-grained architectural elements and degrade across geographic domains.
-
COSY: Compositional 3DGS Synthesis for Disentangled Human Head Editing
COSY uses independent per-component 3DGS generators plus context tokens to achieve disentangled semantic editing of human heads without masks or classifiers.
-
Bi-PT: Bidirectional Cross-Attention Point Transformers for Four-Chamber Heart Reconstruction from Sparse Cardiac MRI Data
A bidirectional cross-attention point transformer deforms a heart atlas into a 3D four-chamber mesh from sparse cardiac MRI point clouds using locally affine diffeomorphic flows.
-
Hierarchical Feature Learning for Medical Point Clouds via State Space Model
Presents an SSM-based hierarchical feature learning method for medical point clouds that reports superior performance on classification, completion, and segmentation using a new dataset MedPointS.