Scene Segmentation
120 papers with code • 5 benchmarks • 7 datasets
Scene segmentation is the task of splitting a scene into its various object components.
Image adapted from Temporally coherent 4D reconstruction of complex dynamic scenes.
Benchmarks
These leaderboards are used to track progress in Scene Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Scene Segmentation models and implementations
ScanNet
NYUv2
SUN RGB-D
UAVid
StreetHazards
Mila Simulated Floods
Berkeley DeepDrive Video
Most implemented papers
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
charlesq34/pointnet
•
•
CVPR 2017
Point cloud is an important type of geometric data structure.
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
We show that SegNet provides good performance with competitive inference time and more efficient inference memory-wise as compared to other architectures.
Fully Convolutional Networks for Semantic Segmentation
Convolutional networks are powerful visual models that yield hierarchies of features.
Point Transformer
Pointcept/Pointcept
•
•
ICCV 2021
For example, on the challenging S3DIS dataset for large-scale semantic scene segmentation, the Point Transformer attains an mIoU of 70. 4% on Area 5, outperforming the strongest prior model by 3. 3 absolute percentage points and crossing the 70% mIoU threshold for the first time.
Dual Attention Network for Scene Segmentation
Specifically, we append two types of attention modules on top of traditional dilated FCN, which model the semantic interdependencies in spatial and channel dimensions respectively.
Panoptic Segmentation
We propose and study a task we name panoptic segmentation (PS).
KPConv: Flexible and Deformable Convolution for Point Clouds
HuguesTHOMAS/KPConv
•
•
ICCV 2019
Furthermore, these locations are continuous in space and can be learned by the network.
Index Network
poppinace/indexnet_matting
•
•
By viewing the indices as a function of the feature map, we introduce the concept of "learning to index", and present a novel index-guided encoder-decoder framework where indices are self-learned adaptively from data and are used to guide the downsampling and upsampling stages, without extra training supervision.
Seamless Scene Segmentation
mapillary/seamseg
•
•
CVPR 2019
In this work we introduce a novel, CNN-based architecture that can be trained end-to-end to deliver seamless scene segmentation results.
Point-Voxel CNN for Efficient 3D Deep Learning
mit-han-lab/pvcnn
•
•
NeurIPS 2019
The computation cost and memory footprints of the voxel-based models grow cubically with the input resolution, making it memory-prohibitive to scale up the resolution.
