diff --git a/python/tvm/relay/frontend/paddlepaddle.py b/python/tvm/relay/frontend/paddlepaddle.py
index f771e605cafd..d170d1b12015 100755
--- a/python/tvm/relay/frontend/paddlepaddle.py
+++ b/python/tvm/relay/frontend/paddlepaddle.py
@@ -400,6 +400,60 @@ def convert_conv2d_transpose(g, op, block):
     g.add_node(op.output("Output")[0], out)
 
 
+def convert_conv3d(g, op, block):
+    """Operator converter for conv3d."""
+
+    dilations = op.attr("dilations")
+    groups = op.attr("groups")
+    paddings = op.attr("paddings")
+    padding_algorithm = op.attr("padding_algorithm")
+    strides = op.attr("strides")
+
+    kernel = g.get_node(op.input("Filter")[0])
+    input_x = g.get_node(op.input("Input")[0])
+    out_channels, _, k_d, k_h, k_w = infer_shape(kernel)
+    if padding_algorithm == "VALID":
+        paddings = [0, 0, 0]
+    elif padding_algorithm == "SAME":
+        dilations = [1, 1, 1]
+        input_x = autopad(input_x, strides, [k_d, k_h, k_w], dilations)
+        paddings = [0, 0, 0]
+    elif padding_algorithm == "EXPLICIT":
+        if len(paddings) == 3:
+            paddings = [
+                paddings[0],
+                paddings[1],
+                paddings[2],
+                paddings[0],
+                paddings[1],
+                paddings[2],
+            ]
+        elif len(paddings) == 6:
+            paddings = [
+                paddings[0],
+                paddings[3],
+                paddings[1],
+                paddings[4],
+                paddings[2],
+                paddings[5],
+            ]
+    else:
+        msg = 'Value {} in attribute "padding" of operator Conv is not "valid."'
+        raise tvm.error.OpAttributeInvalid(msg.format(padding_algorithm))
+
+    out = _op.nn.conv3d(
+        input_x,
+        kernel,
+        strides=strides,
+        padding=paddings,
+        dilation=dilations,
+        groups=groups,
+        channels=out_channels,
+        kernel_size=[k_d, k_h, k_w],
+    )
+    g.add_node(op.output("Output")[0], out)
+
+
 def convert_dist(g, op, block):
     """Operator converter for dist."""
 
@@ -2414,6 +2468,7 @@ def convert_where_index(g, op, block):
     "concat": convert_concat,
     "conv2d": convert_conv2d,
     "conv2d_transpose": convert_conv2d_transpose,
+    "conv3d": convert_conv3d,
     "cos": convert_unary_op,
     "cosh": convert_unary_op,
     "cumsum": convert_cumsum,
diff --git a/tests/python/frontend/paddlepaddle/test_forward.py b/tests/python/frontend/paddlepaddle/test_forward.py
index 612c43bb1617..5bdbd68842fb 100755
--- a/tests/python/frontend/paddlepaddle/test_forward.py
+++ b/tests/python/frontend/paddlepaddle/test_forward.py
@@ -554,6 +554,49 @@ def forward(self, inputs):
         verify_model(Conv2DTranspose(stride=3, padding="SAME", groups=1), input_data=input_data)
 
 
+@tvm.testing.uses_gpu
+def test_forward_conv3d():
+    class Conv3D(nn.Layer):
+        def __init__(self, stride=1, padding=0, dilation=1, groups=1, padding_mode="zeros"):
+            super(Conv3D, self).__init__()
+            self.conv = nn.Conv3D(
+                3,
+                6,
+                3,
+                stride=stride,
+                padding=padding,
+                dilation=dilation,
+                groups=groups,
+                padding_mode=padding_mode,
+            )
+            self.softmax = nn.Softmax()
+
+        @paddle.jit.to_static
+        def forward(self, inputs):
+            return self.softmax(self.conv(inputs))
+
+    input_shapes = [[1, 3, 10, 10, 10], [1, 3, 12, 12, 12]]
+
+    for input_shape in input_shapes:
+        input_data = paddle.rand(input_shape, dtype="float32")
+        verify_model(Conv3D(), input_data=input_data)
+        verify_model(Conv3D(stride=2, padding="VALID", dilation=3), input_data=input_data)
+        verify_model(Conv3D(stride=2, padding="SAME", dilation=3), input_data=input_data)
+        verify_model(
+            Conv3D(stride=2, padding=(3, 3, 4, 4, 2, 2), dilation=3),
+            input_data=input_data,
+        )
+        verify_model(
+            Conv3D(stride=2, padding=3, dilation=3, padding_mode="reflect"),
+            input_data=input_data,
+        )
+        verify_model(
+            Conv3D(stride=2, padding=3, dilation=3, padding_mode="replicate"),
+            input_data=input_data,
+        )
+        verify_model(Conv3D(stride=2, padding="SAME", dilation=2, groups=3), input_data=input_data)
+
+
 @tvm.testing.uses_gpu
 def test_forward_dot():
     class Dot(nn.Layer):