diff --git a/doc/gpu.tex b/doc/gpu.tex
index 65ecce6c37..666b1c74ea 100644
--- a/doc/gpu.tex
+++ b/doc/gpu.tex
@@ -1,10 +1,105 @@
 \ifCpp
 
-%\section{Per-element Operations}
+\section{Per-element Operations}
 
-%\section{Matrix Reductions}
+%can't make cvCppFunc work with underscore (even as \_)
+\cvfunc{cv::gpu::bitwise\_not}
+Performs per-element bitwise inversion.
 
-%\section{Image Processing}
+\cvdefCpp{void bitwise\_not(const GpuMat\& src, GpuMat\& dst,\par
+  const GpuMat\& mask=GpuMat());\newline
+void bitwise\_not(const GpuMat\& src, GpuMat\& dst,\par
+  const GpuMat\& mask, const Stream\& stream);}
+
+\begin{description}
+\cvarg{src}{Source matrix.}
+\cvarg{dst}{Destination matrix. Will have the same size and type as \texttt{src}.}
+\cvarg{mask}{Optional operation mask. 8-bit single channel image.}
+\cvarg{stream}{Stream for asynchronous version.}
+\end{description}
+
+\cvfunc{cv::gpu::bitwise\_or}
+Performs per-element bitwise disjunction of two matrixes.
+
+\cvdefCpp{void bitwise\_or(const GpuMat\& src1, const GpuMat\& src2, GpuMat\& dst,\par
+  const GpuMat\& mask=GpuMat());\newline
+void bitwise\_or(const GpuMat\& src1, const GpuMat\& src2, GpuMat\& dst,\par
+  const GpuMat\& mask, const Stream\& stream);}
+
+\begin{description}
+\cvarg{src1}{The first source matrix.}
+\cvarg{src2}{The second source matrix. It must have the same size and type as \texttt{src1}.}
+\cvarg{dst}{Destination matrix. Will have the same size and type as \texttt{src1}.}
+\cvarg{mask}{Optional operation mask. 8-bit single channel image.}
+\cvarg{stream}{Stream for asynchronous version.}
+\end{description}
+
+\cvfunc{cv::gpu::bitwise\_and}
+Performs per-element bitwise conjunction of two matrixes.
+
+\cvdefCpp{void bitwise\_and(const GpuMat\& src1, const GpuMat\& src2, GpuMat\& dst,\par
+  const GpuMat\& mask=GpuMat());\newline
+void bitwise\_and(const GpuMat\& src1, const GpuMat\& src2, GpuMat\& dst,\par
+  const GpuMat\& mask, const Stream\& stream);}
+
+\begin{description}
+\cvarg{src1}{The first source matrix.}
+\cvarg{src2}{The second source matrix. It must have the same size and type as \texttt{src1}.}
+\cvarg{dst}{Destination matrix. Will have the same size and type as \texttt{src1}.}
+\cvarg{mask}{Optional operation mask. 8-bit single channel image.}
+\cvarg{stream}{Stream for asynchronous version.}
+\end{description}
+
+\cvfunc{cv::gpu::bitwise\_xor}
+Performs per-element bitwise "exclusive or" of two matrixes.
+
+\cvdefCpp{void bitwise\_xor(const GpuMat\& src1, const GpuMat\& src2, GpuMat\& dst,\par
+  const GpuMat\& mask=GpuMat());\newline
+void bitwise\_xor(const GpuMat\& src1, const GpuMat\& src2, GpuMat\& dst,\par
+  const GpuMat\& mask, const Stream\& stream);}
+
+\begin{description}
+\cvarg{src1}{The first source matrix.}
+\cvarg{src2}{The second source matrix. It must have the same size and type as \texttt{src1}.}
+\cvarg{dst}{Destination matrix. Will have the same size and type as \texttt{src1}.}
+\cvarg{mask}{Optional operation mask. 8-bit single channel image.}
+\cvarg{stream}{Stream for asynchronous version.}
+\end{description}
+
+\section{Image Processing}
+
+\cvCppFunc{gpu::meanShiftFiltering}
+Performs mean-shift filtering.
+
+\cvdefCpp{void meanShiftFiltering(const GpuMat\& src, GpuMat\& dst,\par
+  int sp, int sr,\par
+  TermCriteria criteria = TermCriteria(TermCriteria::MAX\_ITER\par
+  + TermCriteria::EPS, 5, 1));}
+
+\begin{description}
+\cvarg{src}{Source image. Only 8UC4 images are supported for now.}
+\cvarg{dst}{Destination image. Will have the same size and type as \texttt{src}. Each pixel \texttt{(x,y)} of the destination image will contain color of converged point started from \texttt{(x,y)} pixel of the source image.}
+\cvarg{sp}{Spatial window radius.}
+\cvarg{sr}{Color window radius.}
+\cvarg{criteria}{Termination criteria. See \cross{TermCriteria}.}
+\end{description}
+
+\cvCppFunc{gpu::meanShiftProc}
+Performs mean-shift procedure and stores information about converged points in two images..
+
+\cvdefCpp{void meanShiftProc(const GpuMat\& src, GpuMat\& dstr, GpuMat\& dstsp,\par
+  int sp, int sr,\par
+  TermCriteria criteria = TermCriteria(TermCriteria::MAX\_ITER\par
+  + TermCriteria::EPS, 5, 1));}
+
+\begin{description}
+\cvarg{src}{Source image. Only 8UC4 images are supported for now.}
+\cvarg{dstr}{Destination image. Will have the same size and type as \texttt{src}. Each pixel \texttt{(x,y)} of the destination image will contain color of converged point started from \texttt{(x,y)} pixel of the source image.}
+\cvarg{dstsp}{16SC2 matrix, which will contain coordinates of converged points and have the same size as \texttt{src}.}
+\cvarg{sp}{Spatial window radius.}
+\cvarg{sr}{Color window radius.}
+\cvarg{criteria}{Termination criteria. See \cross{TermCriteria}.}
+\end{description}
 
 \section{Object Detection}
 
diff --git a/doc/opencv.pdf b/doc/opencv.pdf
index 774e724da5..20c2bfd34b 100644
Binary files a/doc/opencv.pdf and b/doc/opencv.pdf differ