Merge branch 'master' of github.com:facebookresearch/SparseConvNet

README.md

@@ -257,3 +257,4 @@ pip install git+https://github.com/pytorch/tnt.git@master
 6. [Kaggle Diabetic Retinopathy Detection, 2015](https://www.kaggle.com/c/diabetic-retinopathy-detection/) First place in the Kaggle Diabetic Retinopathy Detection competition.
 7. [Submanifold Sparse Convolutional Networks, 2017](https://arxiv.org/abs/1706.01307) Introduces deep 'submanifold' SparseConvNets.
 8. [Workshop on Learning to See from 3D Data, 2017](https://shapenet.cs.stanford.edu/iccv17workshop/) First place in the [semantic segmentation](https://shapenet.cs.stanford.edu/iccv17/) competition. [Report](https://arxiv.org/pdf/1710.06104)
+9. [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks, 2017](https://arxiv.org/abs/1711.10275) Semantic segmentation for the ShapeNet Core55 and NYU-DepthV2 datasets

Torch/C.lua

@@ -221,7 +221,7 @@ void scn_ARCH_REAL_DIMENSIONMaxPooling_updateGradInput(
 // SparseToDense
 void scn_ARCH_REAL_DIMENSIONSparseToDense_updateOutput(
   THLongTensor *inputSize, void **m, THTensor *input_features,
-  THTensor *output_features, THITensor *rulesBuffer);
+  THTensor *output_features, THITensor *rulesBuffer, long nPlanes);
 void scn_ARCH_REAL_DIMENSIONSparseToDense_updateGradInput(
   THLongTensor *inputSize, void **m, THTensor *input_features,
   THTensor *d_input_features, THTensor *d_output_features,

Torch/SparseToDense.lua

@@ -36,7 +36,7 @@ return function(sparseconvnet)
       input.features:cdata(),
       self.output:cdata(),
       self.shared.rulesBuffer and self.shared.rulesBuffer:cdata(),
-      self.nPlanes or input.features.size(2))
+      self.nPlanes or input.features:size(2))
     return self.output
   end