RGBD-semantic-segmentation

A paper list of RGBD semantic segmentation (processing)
https://github.com/Yangzhangcst/RGBD-semantic-segmentation

Last synced: 2 days ago
JSON representation

Paper list
- ScanNet
  - 3M2RNet
  - MTF
  - UCTNet
  - 3M2RNet
  - UCTNet
  - DFormer - RGBD/DFormer)
  - AsymFormer
  - 3M2RNet
  - UCTNet
  - 3M2RNet
  - UCTNet
  - 3M2RNet
  - UCTNet
  - 3M2RNet
  - UCTNet
  - 3M2RNet
  - UCTNet
  - 3M2RNet
  - UCTNet
  - 3M2RNet
  - UCTNet
  - UCTNet
  - 3M2RNet
  - 3M2RNet
  - UCTNet
  - 3M2RNet
  - UCTNet
  - 3M2RNet
  - UCTNet
  - 3M2RNet
  - UCTNet
  - 3M2RNet
  - UCTNet
  - 3M2RNet
  - UCTNet
  - D-depth-reg
  - 3M2RNet
  - UCTNet
  - MTF
  - FRNet
  - DRD
  - SAMD
  - BFFNet-152
  - MQTransformer
  - GED
  - LDF
  - PCGNet
  - UCTNet
  - MGCNet
  - CMANet
  - DynMM
  - FAFNet
  - EMSANet - NICR/EMSANet)
  - WTNet
  - SANet
  - Zig-Zag Net
  - MCN-DRM
  - CANet
  - CEN
  - POR
  - RGBD R-CNN
  - CRF-RNN
  - Mutex Constraints
  - Multi-Scale CNN
  - DeconvNet
  - LSTM-CF - CF)
  - LCSF-Deconv
  - BI
  - E2S2 - calvin)
  - IFCN
  - CRF+RF+RFS
  - SegNet - segnet)
  - LSD-GF
  - LCR
  - RefineNet - pytorch)
  - FuseNet
  - STD2P
  - RDFNet
  - CFN(RefineNet)
  - 3D-GNN
  - DML-Res50
  - PBR-CNN
  - FC-CRF
  - HP-SPS - SPS)
  - LRN
  - G-FRNet-Res101
  - CCF-GMA
  - Context
  - D-Refine-152
  - D-depth-reg
  - RGBD-Geo
  - D-CNN
  - TRL-ResNet50/101
  - DeepLab-LFOV - public-ver2/src/master/)
  - PU-Loop - Scene-Parsing-with-Perspective-Understanding-in-the-loop)
  - PAD-Net
  - C-DCNN
  - EFCN-8s
  - 3M2RNet
  - RFBNet
  - MMAF-Net-152
  - LCR-RGBD
  - ACNet
  - DSNet
  - GAD
  - RTJ-AA - task-refinenet)
  - CTS-IM
  - 2.5D-Conv
  - DMFNet
  - PAP
  - FDNet-16s
  - JTRL-ResNet50/101
  - 3DN-Conv
  - SGNet
  - SCN-ResNet101
  - RefineNet-Res152-Pool4
  - CANet-ResNet101
  - CGBNet
  - TSNet
  - PSD-ResNet50
  - Malleable 2.5D
  - BCMFP+SA-Gate
  - MTI-Net - Task-Learning-PyTorch)
  - QGN
  - VCD+RedNet/ACNet
  - Z-ACN
  - AdapNet++
  - ESANet - NICR/ESANet)
  - LWM
  - GLPNet
  - ESOSD-Net
  - 3D-to-2D - to-2D-Distillation-for-Indoor-Scene-Parsing)
  - NANet
  - ARLoss
  - ATRC
  - FSFNet
  - CSNet
  - ShapeConv
  - CI-Net
  - UMT
  - RGBxD
  - TCD
  - RAFNet
  - MAMD
  - FuseNet-3DEF
  - GRBNet
  - RTLNet
  - [Paper
  - CANet
  - ADSD
  - HS3
  - InvPT
  - PGDENet
  - CMX
  - RFNet
  - DCANet
  - Link-RGBD
  - TransD-Fusion
  - GANDA
  - SupeRGB-D - d)
  - PDCNet - d)
  - PDCNet
  - BiFCNet
  - MMSI - MMSI)
  - SGACNet - HBUT/SGACNet)
Datasets
- `[Cityscapes - level annotations of 5 000 frames in addition to a larger set of 20 000 weakly annotated frames.
- `[2D-3D-S - 2D-3D-Semantic dataset contains 70496 RGB and depth images as well as 2D annotation with 13 object categories. Areas 1, 2, 3, 4, and 6 are utilized as the training and Area 5 is used as the testing set.
- `[ScanNet - D video dataset containing 2.5 million views in more than 1500 scans, annotated with 3D camera poses, surface reconstructions, and instance-level semantic segmentations.

Categories

Paper list 165 Datasets 3

Sub Categories