3D Semantic Scene Completion On Nyuv2

المقاييس

mIoU

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	mIoU	Paper Title	Repository
SG-SSC	55.4	2D Semantic-Guided Semantic Scene Completion
Am2fnet: Attention-based multiscale & multi-modality fused network	31.7	3D Semantic Scene Completion: a Survey	-
SPAwN (SUNCG pretraining)	49.9	Data Augmented 3D Semantic Scene Completion with 2D Segmentation Priors
CCPNet (SUNCG pretraining)	41.3	Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion	-
AIC-Net	33.3	Anisotropic Convolutional Networks for 3D Semantic Scene Completion
EdgeNet (SUNCG pretraining)	33.7	3D Semantic Scene Completion: a Survey	-
3DSketch	41.1	3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior
GRFNet	32.9	3D Gated Recurrent Fusion for Semantic Scene Completion	-
VVNet	29.3	View-volume Network for Semantic Scene Completion from a Single Depth Image	-
VD-CRF: Semantic scene completion with dense CRF from a single depth image. (SUNCG pretraining)	31.8	3D Semantic Scene Completion: a Survey	-
3D semantic scene completion from a single depth image using adversarial training	22.7	3D Semantic Scene Completion: a Survey	-
Real-time semantic scene completion via feature aggregation and conditioned prediction	34.4	3D Semantic Scene Completion: a Survey	-
SPAwN	48	Data Augmented 3D Semantic Scene Completion with 2D Segmentation Priors
TS3D	34.1	Two Stream 3D Semantic Scene Completion	-
ESSCNet	26.7	Efficient Semantic Scene Completion Network with Spatial Group Convolution
IPF-SPCNet: Semantic point completion network for 3D semantic scene completion	35.1	Semantic Point Completion Network for 3D Semantic Scene Completion	-
EdgeNet	27.8	EdgeNet: Semantic Scene Completion from a Single RGB-D Image
LMSCNet-SS	28.4	LMSCNet: Lightweight Multiscale 3D Semantic Completion
ForkNet (SUNCG pretraining)	37.1	ForkNet: Multi-branch Volumetric Semantic Completion from a Single Depth Image	-
Point-Voxel Aggregation Network	46	Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspective	-

0 of 28 row(s) selected.