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.
Advances in neural information processing systems30(2017)
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.CV 5representative citing papers
CineMesh4D reconstructs personalized 4D whole-heart meshes directly from multi-view 2D cine MRI via cross-domain mapping with differentiable rendering and dual-context temporal blocks.
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.
MPL-MAE introduces recalibrated positional embedding and gated positional interface modules to reduce positional over-reliance in 3D masked autoencoders and improve semantic representation quality.
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.
-
CineMesh4D: Personalized 4D Whole Heart Reconstruction from Sparse Cine MRI
CineMesh4D reconstructs personalized 4D whole-heart meshes directly from multi-view 2D cine MRI via cross-domain mapping with differentiable rendering and dual-context temporal blocks.
-
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.
-
Mitigating Positional Leakage in 3D Masked Autoencoders for Robust Representation Learning
MPL-MAE introduces recalibrated positional embedding and gated positional interface modules to reduce positional over-reliance in 3D masked autoencoders and improve semantic representation quality.
- Bi-PT: Bidirectional Cross-Attention Point Transformers for Four-Chamber Heart Reconstruction from Sparse Cardiac MRI Data