HyperAIHyperAI超神经
首页算力平台文档资讯论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAIHyperAI超神经

Command Palette

Search for a command to run...

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 TitleRepository
SG-SSC55.42D Semantic-Guided Semantic Scene Completion-
SISNet52.4Semantic Scene Completion via Integrating Instances and Scene in-the-Loop
SPAwN (SUNCG pretraining)49.9Data Augmented 3D Semantic Scene Completion with 2D Segmentation Priors
SPAwN48Data Augmented 3D Semantic Scene Completion with 2D Segmentation Priors
Point-Voxel Aggregation Network46Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspective-
CCPNet (SUNCG pretraining)41.3Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion-
3DSketch41.13D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior
ForkNet (SUNCG pretraining)37.1ForkNet: Multi-branch Volumetric Semantic Completion from a Single Depth Image-
IPF-SPCNet: Semantic point completion network for 3D semantic scene completion35.1Semantic Point Completion Network for 3D Semantic Scene Completion-
Real-time semantic scene completion via feature aggregation and conditioned prediction34.43D Semantic Scene Completion: a Survey-
TS3D34.1Two Stream 3D Semantic Scene Completion-
EdgeNet (SUNCG pretraining)33.73D Semantic Scene Completion: a Survey-
AIC-Net33.3Anisotropic Convolutional Networks for 3D Semantic Scene Completion
AMFNet33Attention-based Multi-modal Fusion Network for Semantic Scene Completion-
GRFNet32.93D Gated Recurrent Fusion for Semantic Scene Completion-
VD-CRF: Semantic scene completion with dense CRF from a single depth image. (SUNCG pretraining)31.83D Semantic Scene Completion: a Survey-
Am2fnet: Attention-based multiscale & multi-modality fused network31.73D Semantic Scene Completion: a Survey-
OccDepth30.9OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion
SSCNet (SUNCG pretraining)30.5Semantic Scene Completion from a Single Depth Image
DDRNet30.4RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion-
0 of 28 row(s) selected.