minor doc update fix #126

CHANGELOG.md

@@ -1,6 +1,6 @@
 # Change Log
 
-## [master] - 2020-04-08
+## [master] - 2020-05-01
 
 ### Changed
 
@@ -18,6 +18,7 @@
 - `SparseTensor.slice()` slicing features on discrete coordinates to continuous coordinates
 - CoordsManager.getKernelMapGPU returns long type tensors (Issue #125)
 - SyncBatchNorm error fix (Issue #129)
+- Sparse Tensor `dense()` doc update (Issue #126)
 
 
 ## [0.4.2] - 2020-03-13

MinkowskiEngine/SparseTensor.py

@@ -817,9 +817,10 @@ def dense(self, min_coords=None, max_coords=None, contract_coords=True):
 
         Returns:
             :attr:`spare_tensor` (torch.sparse.Tensor): the torch sparse tensor
-            representation of the self in `[Batch Dim, Spatial Dims..., Feature
-            Dim]`. The coordinate of each feature can be accessed via
-            `min_coord + tensor_stride * [the coordinate of the dense tensor]`.
+            representation of the self in `[Batch Dim, Feature Dim, Spatial
+            Dim..., Spatial Dim]`. The coordinate of each feature can be
+            accessed via `min_coord + tensor_stride * [the coordinate of the
+            dense tensor]`.
 
             :attr:`min_coords` (torch.IntTensor): the D-dimensional vector
             defining the minimum coordinate of the output sparse tensor. If

README.md

@@ -240,4 +240,6 @@ If you use the Minkowski Engine, please cite:
 
 - [3D and 4D Spatio-Temporal Semantic Segmentation, CVPR'19](https://github.com/chrischoy/SpatioTemporalSegmentation)
 - [Fully Convolutional Geometric Features, ICCV'19](https://github.com/chrischoy/FCGF)
-- [Learning multiview 3D point cloud registration](https://arxiv.org/abs/2001.05119)
+- [Learning multiview 3D point cloud registration, CVPR'20](https://arxiv.org/abs/2001.05119)
+- [Deep Global Registration, CVPR'20](https://arxiv.org/abs/2004.11540)
+- High-Dimensional Convolutional Networks for Geometric Pattern Recognition, CVPR'20