diff --git a/Source/Core/VideoBackends/D3D/D3DUtil.cpp b/Source/Core/VideoBackends/D3D/D3DUtil.cpp
index 57524a49d3..89bdbcee97 100644
--- a/Source/Core/VideoBackends/D3D/D3DUtil.cpp
+++ b/Source/Core/VideoBackends/D3D/D3DUtil.cpp
@@ -422,20 +422,20 @@ int CD3DFont::DrawTextScaled(float x, float y, float size, float spacing, u32 dw
 ID3D11SamplerState* linear_copy_sampler = nullptr;
 ID3D11SamplerState* point_copy_sampler = nullptr;
 
-struct STQVertex   { float x, y, z, u, v, w; };
-struct STSQVertex  { float x, y, z, u, v, w; };
+struct STQVertex   { float x, y, z, u, v, w, g; };
+struct STSQVertex  { float x, y, z, u, v, w, g; };
 struct ClearVertex { float x, y, z; u32 col; };
 struct ColVertex   { float x, y, z; u32 col; };
 
 struct
 {
-	float u1, v1, u2, v2, G;
+	float u1, v1, u2, v2, S, G;
 } tex_quad_data;
 
 struct
 {
 	MathUtil::Rectangle<float> rdest;
-	float u1, v1, u2, v2, G;
+	float u1, v1, u2, v2, S, G;
 } tex_sub_quad_data;
 
 struct
@@ -512,7 +512,8 @@ void drawShadedTexQuad(ID3D11ShaderResourceView* texture,
 						ID3D11PixelShader* PShader,
 						ID3D11VertexShader* Vshader,
 						ID3D11InputLayout* layout,
-						float Gamma)
+						float Gamma,
+						u32 slice)
 {
 	float sw = 1.0f /(float) SourceWidth;
 	float sh = 1.0f /(float) SourceHeight;
@@ -520,19 +521,21 @@ void drawShadedTexQuad(ID3D11ShaderResourceView* texture,
 	float u2 = ((float)rSource->right) * sw;
 	float v1 = ((float)rSource->top) * sh;
 	float v2 = ((float)rSource->bottom) * sh;
+	float S = (float)slice;
 	float G = 1.0f / Gamma;
 
 	STQVertex coords[4] = {
-		{-1.0f, 1.0f, 0.0f,  u1, v1, G},
-		{ 1.0f, 1.0f, 0.0f,  u2, v1, G},
-		{-1.0f,-1.0f, 0.0f,  u1, v2, G},
-		{ 1.0f,-1.0f, 0.0f,  u2, v2, G},
+		{-1.0f, 1.0f, 0.0f,  u1, v1, S, G},
+		{ 1.0f, 1.0f, 0.0f,  u2, v1, S, G},
+		{-1.0f,-1.0f, 0.0f,  u1, v2, S, G},
+		{ 1.0f,-1.0f, 0.0f,  u2, v2, S, G},
 	};
 
 	// only upload the data to VRAM if it changed
 	if (stq_observer ||
 		tex_quad_data.u1 != u1 || tex_quad_data.v1 != v1 ||
-		tex_quad_data.u2 != u2 || tex_quad_data.v2 != v2 || tex_quad_data.G != G)
+		tex_quad_data.u2 != u2 || tex_quad_data.v2 != v2 ||
+		tex_quad_data.S  != S  || tex_quad_data.G  != G)
 	{
 		stq_offset = util_vbuf->AppendData(coords, sizeof(coords), sizeof(STQVertex));
 		stq_observer = false;
@@ -541,7 +544,8 @@ void drawShadedTexQuad(ID3D11ShaderResourceView* texture,
 		tex_quad_data.v1 = v1;
 		tex_quad_data.u2 = u2;
 		tex_quad_data.v2 = v2;
-		tex_quad_data.G  =  G;
+		tex_quad_data.S  = S;
+		tex_quad_data.G  = G;
 	}
 	UINT stride = sizeof(STQVertex);
 	UINT offset = 0;
@@ -568,7 +572,8 @@ void drawShadedTexSubQuad(ID3D11ShaderResourceView* texture,
 							ID3D11PixelShader* PShader,
 							ID3D11VertexShader* Vshader,
 							ID3D11InputLayout* layout,
-							float Gamma)
+							float Gamma,
+							u32 slice)
 {
 	float sw = 1.0f /(float) SourceWidth;
 	float sh = 1.0f /(float) SourceHeight;
@@ -576,20 +581,22 @@ void drawShadedTexSubQuad(ID3D11ShaderResourceView* texture,
 	float u2 = (rSource->right ) * sw;
 	float v1 = (rSource->top   ) * sh;
 	float v2 = (rSource->bottom) * sh;
+	float S = (float)slice;
 	float G = 1.0f / Gamma;
 
 	STSQVertex coords[4] = {
-		{ rDest->left , rDest->bottom, 0.0f, u1, v2, G},
-		{ rDest->right, rDest->bottom, 0.0f, u2, v2, G},
-		{ rDest->left , rDest->top   , 0.0f, u1, v1, G},
-		{ rDest->right, rDest->top   , 0.0f, u2, v1, G},
+		{ rDest->left , rDest->bottom, 0.0f, u1, v2, S, G},
+		{ rDest->right, rDest->bottom, 0.0f, u2, v2, S, G},
+		{ rDest->left , rDest->top   , 0.0f, u1, v1, S, G},
+		{ rDest->right, rDest->top   , 0.0f, u2, v1, S, G},
 	};
 
 	// only upload the data to VRAM if it changed
 	if (stsq_observer ||
 		memcmp(rDest, &tex_sub_quad_data.rdest, sizeof(*rDest)) != 0 ||
 		tex_sub_quad_data.u1 != u1 || tex_sub_quad_data.v1 != v1 ||
-		tex_sub_quad_data.u2 != u2 || tex_sub_quad_data.v2 != v2 || tex_sub_quad_data.G != G)
+		tex_sub_quad_data.u2 != u2 || tex_sub_quad_data.v2 != v2 ||
+		tex_sub_quad_data.S  != S  || tex_sub_quad_data.G  != G)
 	{
 		stsq_offset = util_vbuf->AppendData(coords, sizeof(coords), sizeof(STSQVertex));
 		stsq_observer = false;
@@ -598,6 +605,7 @@ void drawShadedTexSubQuad(ID3D11ShaderResourceView* texture,
 		tex_sub_quad_data.v1 = v1;
 		tex_sub_quad_data.u2 = u2;
 		tex_sub_quad_data.v2 = v2;
+		tex_sub_quad_data.S  = S;
 		tex_sub_quad_data.G  = G;
 		memcpy(&tex_sub_quad_data.rdest, &rDest, sizeof(rDest));
 	}
diff --git a/Source/Core/VideoBackends/D3D/D3DUtil.h b/Source/Core/VideoBackends/D3D/D3DUtil.h
index bd47d9ff0e..53706847c2 100644
--- a/Source/Core/VideoBackends/D3D/D3DUtil.h
+++ b/Source/Core/VideoBackends/D3D/D3DUtil.h
@@ -62,7 +62,8 @@ namespace D3D
 						ID3D11PixelShader* PShader,
 						ID3D11VertexShader* VShader,
 						ID3D11InputLayout* layout,
-						float Gamma = 1.0f);
+						float Gamma = 1.0f,
+						u32 slice = 0);
 	void drawShadedTexSubQuad(ID3D11ShaderResourceView* texture,
 							const MathUtil::Rectangle<int>* rSource,
 							int SourceWidth,
@@ -71,7 +72,8 @@ namespace D3D
 							ID3D11PixelShader* PShader,
 							ID3D11VertexShader* Vshader,
 							ID3D11InputLayout* layout,
-							float Gamma = 1.0f);
+							float Gamma = 1.0f,
+							u32 slice = 0);
 	void drawClearQuad(u32 Color, float z, ID3D11PixelShader* PShader, ID3D11VertexShader* Vshader, ID3D11InputLayout* layout);
 	void drawColorQuad(u32 Color, float x1, float y1, float x2, float y2);
 }
diff --git a/Source/Core/VideoBackends/D3D/PixelShaderCache.cpp b/Source/Core/VideoBackends/D3D/PixelShaderCache.cpp
index a42d1a4103..94c53beda3 100644
--- a/Source/Core/VideoBackends/D3D/PixelShaderCache.cpp
+++ b/Source/Core/VideoBackends/D3D/PixelShaderCache.cpp
@@ -51,11 +51,11 @@ const char clear_program_code[] = {
 // TODO: Find some way to avoid having separate shaders for non-MSAA and MSAA...
 const char color_copy_program_code[] = {
 	"sampler samp0 : register(s0);\n"
-	"Texture2D Tex0 : register(t0);\n"
+	"Texture2DArray Tex0 : register(t0);\n"
 	"void main(\n"
 	"out float4 ocol0 : SV_Target,\n"
 	"in float4 pos : SV_Position,\n"
-	"in float2 uv0 : TEXCOORD0){\n"
+	"in float3 uv0 : TEXCOORD0){\n"
 	"ocol0 = Tex0.Sample(samp0,uv0);\n"
 	"}\n"
 };
@@ -63,16 +63,16 @@ const char color_copy_program_code[] = {
 // TODO: Improve sampling algorithm!
 const char color_copy_program_code_msaa[] = {
 	"sampler samp0 : register(s0);\n"
-	"Texture2DMS<float4, %d> Tex0 : register(t0);\n"
+	"Texture2DMSArray<float4, %d> Tex0 : register(t0);\n"
 	"void main(\n"
 	"out float4 ocol0 : SV_Target,\n"
 	"in float4 pos : SV_Position,\n"
-	"in float2 uv0 : TEXCOORD0){\n"
+	"in float3 uv0 : TEXCOORD0,\n"
 	"int width, height, samples;\n"
 	"Tex0.GetDimensions(width, height, samples);\n"
 	"ocol0 = 0;\n"
 	"for(int i = 0; i < samples; ++i)\n"
-	"	ocol0 += Tex0.Load(int2(uv0.x*(width), uv0.y*(height)), i);\n"
+	"	ocol0 += Tex0.Load(int3(uv0.x*(width), uv0.y*(height), uv0.z), i);\n"
 	"ocol0 /= samples;\n"
 	"}\n"
 };
diff --git a/Source/Core/VideoBackends/D3D/Render.cpp b/Source/Core/VideoBackends/D3D/Render.cpp
index 9d5802ebd8..7593d2810f 100644
--- a/Source/Core/VideoBackends/D3D/Render.cpp
+++ b/Source/Core/VideoBackends/D3D/Render.cpp
@@ -761,7 +761,25 @@ void Renderer::SwapImpl(u32 xfbAddr, u32 fbWidth, u32 fbStride, u32 fbHeight, co
 
 		// TODO: Improve sampling algorithm for the pixel shader so that we can use the multisampled EFB texture as source
 		D3DTexture2D* read_texture = FramebufferManager::GetResolvedEFBColorTexture();
-		D3D::drawShadedTexQuad(read_texture->GetSRV(), targetRc.AsRECT(), Renderer::GetTargetWidth(), Renderer::GetTargetHeight(), PixelShaderCache::GetColorCopyProgram(false),VertexShaderCache::GetSimpleVertexShader(), VertexShaderCache::GetSimpleInputLayout(), Gamma);
+
+		if (g_ActiveConfig.iStereoMode == STEREO_SBS || g_ActiveConfig.iStereoMode == STEREO_TAB)
+		{
+			TargetRectangle leftRc, rightRc;
+			ConvertStereoRectangle(GetTargetRectangle(), leftRc, rightRc);
+
+			D3D11_VIEWPORT leftVp = CD3D11_VIEWPORT((float)leftRc.left, (float)leftRc.top, (float)leftRc.GetWidth(), (float)leftRc.GetHeight());
+			D3D11_VIEWPORT rightVp = CD3D11_VIEWPORT((float)rightRc.left, (float)rightRc.top, (float)rightRc.GetWidth(), (float)rightRc.GetHeight());
+
+			D3D::context->RSSetViewports(1, &leftVp);
+			D3D::drawShadedTexQuad(read_texture->GetSRV(), targetRc.AsRECT(), Renderer::GetTargetWidth(), Renderer::GetTargetHeight(), PixelShaderCache::GetColorCopyProgram(false), VertexShaderCache::GetSimpleVertexShader(), VertexShaderCache::GetSimpleInputLayout(), Gamma, 0);
+
+			D3D::context->RSSetViewports(1, &rightVp);
+			D3D::drawShadedTexQuad(read_texture->GetSRV(), targetRc.AsRECT(), Renderer::GetTargetWidth(), Renderer::GetTargetHeight(), PixelShaderCache::GetColorCopyProgram(false), VertexShaderCache::GetSimpleVertexShader(), VertexShaderCache::GetSimpleInputLayout(), Gamma, 1);
+		}
+		else
+		{
+			D3D::drawShadedTexQuad(read_texture->GetSRV(), targetRc.AsRECT(), Renderer::GetTargetWidth(), Renderer::GetTargetHeight(), PixelShaderCache::GetColorCopyProgram(false), VertexShaderCache::GetSimpleVertexShader(), VertexShaderCache::GetSimpleInputLayout(), Gamma);
+		}
 	}
 
 	// done with drawing the game stuff, good moment to save a screenshot
diff --git a/Source/Core/VideoBackends/D3D/VertexShaderCache.cpp b/Source/Core/VideoBackends/D3D/VertexShaderCache.cpp
index d565d50c03..0abe6f1586 100644
--- a/Source/Core/VideoBackends/D3D/VertexShaderCache.cpp
+++ b/Source/Core/VideoBackends/D3D/VertexShaderCache.cpp
@@ -73,15 +73,15 @@ const char simple_shader_code[] = {
 	"struct VSOUTPUT\n"
 	"{\n"
 	"float4 vPosition : POSITION;\n"
-	"float2 vTexCoord : TEXCOORD0;\n"
+	"float3 vTexCoord : TEXCOORD0;\n"
 	"float  vTexCoord1 : TEXCOORD1;\n"
 	"};\n"
-	"VSOUTPUT main(float4 inPosition : POSITION,float3 inTEX0 : TEXCOORD0)\n"
+	"VSOUTPUT main(float4 inPosition : POSITION,float4 inTEX0 : TEXCOORD0)\n"
 	"{\n"
 	"VSOUTPUT OUT;\n"
 	"OUT.vPosition = inPosition;\n"
-	"OUT.vTexCoord = inTEX0.xy;\n"
-	"OUT.vTexCoord1 = inTEX0.z;\n"
+	"OUT.vTexCoord = inTEX0.xyz;\n"
+	"OUT.vTexCoord1 = inTEX0.w;\n"
 	"return OUT;\n"
 	"}\n"
 };