diff --git a/modules/dnn/src/layers/batch_norm_layer.cpp b/modules/dnn/src/layers/batch_norm_layer.cpp
index 4c69c247c4..6c1fc6ef29 100644
--- a/modules/dnn/src/layers/batch_norm_layer.cpp
+++ b/modules/dnn/src/layers/batch_norm_layer.cpp
@@ -29,6 +29,8 @@ class BatchNormLayerImpl CV_FINAL : public BatchNormLayer
 public:
     Mat weights_, bias_;
     UMat umat_weight, umat_bias;
+    mutable int dims;
+
 
     BatchNormLayerImpl(const LayerParams& params)
     {
@@ -142,6 +144,7 @@ public:
                          std::vector<MatShape> &outputs,
                          std::vector<MatShape> &internals) const CV_OVERRIDE
     {
+        dims = inputs[0].size();
         if (!useGlobalStats && inputs[0][0] != 1)
             CV_Error(Error::StsNotImplemented, "Batch normalization in training mode with batch size > 1");
         Layer::getMemoryShapes(inputs, requiredOutputs, outputs, internals);
@@ -150,9 +153,9 @@ public:
 
     virtual bool supportBackend(int backendId) CV_OVERRIDE
     {
-        return backendId == DNN_BACKEND_OPENCV ||
+        return (backendId == DNN_BACKEND_OPENCV && (dims == 4 || dims == 2)) ||
                (backendId == DNN_BACKEND_HALIDE && haveHalide()) ||
-               (backendId == DNN_BACKEND_INFERENCE_ENGINE && haveInfEngine());
+               (backendId == DNN_BACKEND_INFERENCE_ENGINE && haveInfEngine() && (preferableTarget == DNN_TARGET_CPU || dims == 4));
     }
 
 #ifdef HAVE_OPENCL
diff --git a/modules/dnn/test/test_onnx_importer.cpp b/modules/dnn/test/test_onnx_importer.cpp
index f1b0a81e8e..10402a3dda 100644
--- a/modules/dnn/test/test_onnx_importer.cpp
+++ b/modules/dnn/test/test_onnx_importer.cpp
@@ -167,6 +167,13 @@ TEST_P(Test_ONNX_layers, BatchNormalization)
     testONNXModels("batch_norm");
 }
 
+TEST_P(Test_ONNX_layers, BatchNormalization3D)
+{
+    if (backend != DNN_BACKEND_INFERENCE_ENGINE || target != DNN_TARGET_CPU)
+       throw SkipTestException("Only DLIE backend on CPU is supported");
+    testONNXModels("batch_norm_3d");
+}
+
 TEST_P(Test_ONNX_layers, Transpose)
 {
     if (backend == DNN_BACKEND_INFERENCE_ENGINE &&
diff --git a/modules/dnn/test/test_tf_importer.cpp b/modules/dnn/test/test_tf_importer.cpp
index e662da53e7..64a56ee94f 100644
--- a/modules/dnn/test/test_tf_importer.cpp
+++ b/modules/dnn/test/test_tf_importer.cpp
@@ -188,6 +188,13 @@ TEST_P(Test_TensorFlow_layers, batch_norm)
     runTensorFlowNet("mvn_batch_norm_1x1");
 }
 
+TEST_P(Test_TensorFlow_layers, batch_norm3D)
+{
+    if (backend != DNN_BACKEND_INFERENCE_ENGINE || target != DNN_TARGET_CPU)
+       throw SkipTestException("Only DLIE backend on CPU is supported");
+    runTensorFlowNet("batch_norm3d");
+}
+
 TEST_P(Test_TensorFlow_layers, slim_batch_norm)
 {
     if (backend == DNN_BACKEND_INFERENCE_ENGINE)