3D Semantic Scene Completion On Nyuv2

评估指标

mIoU

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
SG-SSC	55.4	2D Semantic-Guided Semantic Scene Completion	-
SISNet	52.4	Semantic Scene Completion via Integrating Instances and Scene in-the-Loop
SPAwN (SUNCG pretraining)	49.9	Data Augmented 3D Semantic Scene Completion with 2D Segmentation Priors
SPAwN	48	Data Augmented 3D Semantic Scene Completion with 2D Segmentation Priors
Point-Voxel Aggregation Network	46	Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspective	-
CCPNet (SUNCG pretraining)	41.3	Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion	-
3DSketch	41.1	3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior
ForkNet (SUNCG pretraining)	37.1	ForkNet: Multi-branch Volumetric Semantic Completion from a Single Depth Image	-
IPF-SPCNet: Semantic point completion network for 3D semantic scene completion	35.1	Semantic Point Completion Network for 3D Semantic Scene Completion	-
Real-time semantic scene completion via feature aggregation and conditioned prediction	34.4	3D Semantic Scene Completion: a Survey	-
TS3D	34.1	Two Stream 3D Semantic Scene Completion	-
EdgeNet (SUNCG pretraining)	33.7	3D Semantic Scene Completion: a Survey	-
AIC-Net	33.3	Anisotropic Convolutional Networks for 3D Semantic Scene Completion
AMFNet	33	Attention-based Multi-modal Fusion Network for Semantic Scene Completion	-
GRFNet	32.9	3D Gated Recurrent Fusion for Semantic Scene Completion	-
VD-CRF: Semantic scene completion with dense CRF from a single depth image. (SUNCG pretraining)	31.8	3D Semantic Scene Completion: a Survey	-
Am2fnet: Attention-based multiscale & multi-modality fused network	31.7	3D Semantic Scene Completion: a Survey	-
OccDepth	30.9	OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion
SSCNet (SUNCG pretraining)	30.5	Semantic Scene Completion from a Single Depth Image
DDRNet	30.4	RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion	-

0 of 28 row(s) selected.