根据官方的帖子实现的高斯模糊当前屏幕内容 点击打开链接

1.截屏缩小压缩，减小像素采样的优化算法。默认截屏后缩小到原来的1/4。

2.C++代码进行一次性高斯模糊。避免使用shader造成的渲染掉帧

以下是C++部分代码：

	/*
	* 高斯模糊接口  缩放因子：iScale，截图会把全屏压缩为1/iScale大
	*/
	static void gaussianBlur(const std::function<void(bool,cocos2d::Image*)>& afterCaptured,int iScale = 4);

// The Stack Blur Algorithm was invented by Mario Klingemann,// mario@quasimondo.com and described here:
// http://incubator.quasimondo.com/processing/fast_blur_deluxe.PHP
 
// This is C++ RGBA (32 bit color) multi-threaded version 
// by Victor Laskin (victor.laskin@gmail.com)
// More details: http://vitiy.info/stackblur-algorithm-multi-threaded-blur-for-cpp
 
// This code is using MVThread class from my cross-platform framework 
// You can exchange it with any thread implementation you like
// -------------------------------------- stackblur ----------------------------------------->
 
static unsigned short const stackblur_mul[255] =
{
	512,512,456,328,335,405,271,388,292,454,364,298,496,420,360,312,273,482,428,383,345,284,259,475,437,404,374,347,323,302,282,265,497,468,441,417,394,373,354,337,320,305,291,278,507,485,465,446,412,396,381,367,341,329,318,307,297,287,269,261,505,489,461,447,435,422,411,399,389,378,368,359,350,332,324,316,309,301,294,281,274,268,262,257,501,491,480,470,460,451,442,433,424,416,408,400,392,385,377,370,363,357,344,338,326,315,310,304,299,289,285,280,275,267,263,259
};
 
static unsigned char const stackblur_shr[255] =
{
	9,11,12,13,14,15,16,17,18,19,20,21,22,23,24,24
};
 
/// Stackblur algorithm body
void stackblurJob(unsigned char* src,///< input image data
	unsigned int w,///< image width
	unsigned int h,///< image height
	unsigned int radius,///< blur intensity (should be in 2..254 range)
	int cores,///< total number of working threads
	int core,///< current thread number
	int step,///< step of processing (1,2)
	unsigned char* stack				///< stack buffer
	)
{
	unsigned int x,y,xp,yp,i;
	unsigned int sp;
	unsigned int stack_start;
	unsigned char* stack_ptr;
 
	unsigned char* src_ptr;
	unsigned char* dst_ptr;
 
	unsigned long sum_r;
	unsigned long sum_g;
	unsigned long sum_b;
	unsigned long sum_a;
	unsigned long sum_in_r;
	unsigned long sum_in_g;
	unsigned long sum_in_b;
	unsigned long sum_in_a;
	unsigned long sum_out_r;
	unsigned long sum_out_g;
	unsigned long sum_out_b;
	unsigned long sum_out_a;
 
	unsigned int wm = w - 1;
	unsigned int hm = h - 1;
	unsigned int w4 = w * 4;
	unsigned int div = (radius * 2) + 1;
	unsigned int mul_sum = stackblur_mul[radius];
	unsigned char shr_sum = stackblur_shr[radius];
 
 
	if (step == 1)
	{
		int minY = core * h / cores;
		int maxY = (core + 1) * h / cores;
 
		for (y = minY; y < maxY; y++)
		{
			sum_r = sum_g = sum_b = sum_a =
				sum_in_r = sum_in_g = sum_in_b = sum_in_a =
				sum_out_r = sum_out_g = sum_out_b = sum_out_a = 0;
 
			src_ptr = src + w4 * y; // start of line (0,y)
 
			for (i = 0; i <= radius; i++)
			{
				stack_ptr = &stack[4 * i];
				stack_ptr[0] = src_ptr[0];
				stack_ptr[1] = src_ptr[1];
				stack_ptr[2] = src_ptr[2];
				stack_ptr[3] = src_ptr[3];
				sum_r += src_ptr[0] * (i + 1);
				sum_g += src_ptr[1] * (i + 1);
				sum_b += src_ptr[2] * (i + 1);
				sum_a += src_ptr[3] * (i + 1);
				sum_out_r += src_ptr[0];
				sum_out_g += src_ptr[1];
				sum_out_b += src_ptr[2];
				sum_out_a += src_ptr[3];
			}
 
 
			for (i = 1; i <= radius; i++)
			{
				if (i <= wm) src_ptr += 4;
				stack_ptr = &stack[4 * (i + radius)];
				stack_ptr[0] = src_ptr[0];
				stack_ptr[1] = src_ptr[1];
				stack_ptr[2] = src_ptr[2];
				stack_ptr[3] = src_ptr[3];
				sum_r += src_ptr[0] * (radius + 1 - i);
				sum_g += src_ptr[1] * (radius + 1 - i);
				sum_b += src_ptr[2] * (radius + 1 - i);
				sum_a += src_ptr[3] * (radius + 1 - i);
				sum_in_r += src_ptr[0];
				sum_in_g += src_ptr[1];
				sum_in_b += src_ptr[2];
				sum_in_a += src_ptr[3];
			}
 
 
			sp = radius;
			xp = radius;
			if (xp > wm) xp = wm;
			src_ptr = src + 4 * (xp + y * w); //   img.pix_ptr(xp,y);
			dst_ptr = src + y * w4; // img.pix_ptr(0,y);
			for (x = 0; x < w; x++)
			{
				dst_ptr[0] = (sum_r * mul_sum) >> shr_sum;
				dst_ptr[1] = (sum_g * mul_sum) >> shr_sum;
				dst_ptr[2] = (sum_b * mul_sum) >> shr_sum;
				dst_ptr[3] = (sum_a * mul_sum) >> shr_sum;
				dst_ptr += 4;
 
				sum_r -= sum_out_r;
				sum_g -= sum_out_g;
				sum_b -= sum_out_b;
				sum_a -= sum_out_a;
 
				stack_start = sp + div - radius;
				if (stack_start >= div) stack_start -= div;
				stack_ptr = &stack[4 * stack_start];
 
				sum_out_r -= stack_ptr[0];
				sum_out_g -= stack_ptr[1];
				sum_out_b -= stack_ptr[2];
				sum_out_a -= stack_ptr[3];
 
				if (xp < wm)
				{
					src_ptr += 4;
					++xp;
				}
 
				stack_ptr[0] = src_ptr[0];
				stack_ptr[1] = src_ptr[1];
				stack_ptr[2] = src_ptr[2];
				stack_ptr[3] = src_ptr[3];
 
				sum_in_r += src_ptr[0];
				sum_in_g += src_ptr[1];
				sum_in_b += src_ptr[2];
				sum_in_a += src_ptr[3];
				sum_r += sum_in_r;
				sum_g += sum_in_g;
				sum_b += sum_in_b;
				sum_a += sum_in_a;
 
				++sp;
				if (sp >= div) sp = 0;
				stack_ptr = &stack[sp * 4];
 
				sum_out_r += stack_ptr[0];
				sum_out_g += stack_ptr[1];
				sum_out_b += stack_ptr[2];
				sum_out_a += stack_ptr[3];
				sum_in_r -= stack_ptr[0];
				sum_in_g -= stack_ptr[1];
				sum_in_b -= stack_ptr[2];
				sum_in_a -= stack_ptr[3];
 
 
			}
 
		}
	}
 
	// step 2
	if (step == 2)
	{
		int minX = core * w / cores;
		int maxX = (core + 1) * w / cores;
 
		for (x = minX; x < maxX; x++)
		{
			sum_r = sum_g = sum_b = sum_a =
				sum_in_r = sum_in_g = sum_in_b = sum_in_a =
				sum_out_r = sum_out_g = sum_out_b = sum_out_a = 0;
 
			src_ptr = src + 4 * x; // x,0
			for (i = 0; i <= radius; i++)
			{
				stack_ptr = &stack[i * 4];
				stack_ptr[0] = src_ptr[0];
				stack_ptr[1] = src_ptr[1];
				stack_ptr[2] = src_ptr[2];
				stack_ptr[3] = src_ptr[3];
				sum_r += src_ptr[0] * (i + 1);
				sum_g += src_ptr[1] * (i + 1);
				sum_b += src_ptr[2] * (i + 1);
				sum_a += src_ptr[3] * (i + 1);
				sum_out_r += src_ptr[0];
				sum_out_g += src_ptr[1];
				sum_out_b += src_ptr[2];
				sum_out_a += src_ptr[3];
			}
			for (i = 1; i <= radius; i++)
			{
				if (i <= hm) src_ptr += w4; // +stride
 
				stack_ptr = &stack[4 * (i + radius)];
				stack_ptr[0] = src_ptr[0];
				stack_ptr[1] = src_ptr[1];
				stack_ptr[2] = src_ptr[2];
				stack_ptr[3] = src_ptr[3];
				sum_r += src_ptr[0] * (radius + 1 - i);
				sum_g += src_ptr[1] * (radius + 1 - i);
				sum_b += src_ptr[2] * (radius + 1 - i);
				sum_a += src_ptr[3] * (radius + 1 - i);
				sum_in_r += src_ptr[0];
				sum_in_g += src_ptr[1];
				sum_in_b += src_ptr[2];
				sum_in_a += src_ptr[3];
			}
 
			sp = radius;
			yp = radius;
			if (yp > hm) yp = hm;
			src_ptr = src + 4 * (x + yp * w); // img.pix_ptr(x,yp);
			dst_ptr = src + 4 * x; 			  // img.pix_ptr(x,0);
			for (y = 0; y < h; y++)
			{
				dst_ptr[0] = (sum_r * mul_sum) >> shr_sum;
				dst_ptr[1] = (sum_g * mul_sum) >> shr_sum;
				dst_ptr[2] = (sum_b * mul_sum) >> shr_sum;
				dst_ptr[3] = (sum_a * mul_sum) >> shr_sum;
				dst_ptr += w4;
 
				sum_r -= sum_out_r;
				sum_g -= sum_out_g;
				sum_b -= sum_out_b;
				sum_a -= sum_out_a;
 
				stack_start = sp + div - radius;
				if (stack_start >= div) stack_start -= div;
				stack_ptr = &stack[4 * stack_start];
 
				sum_out_r -= stack_ptr[0];
				sum_out_g -= stack_ptr[1];
				sum_out_b -= stack_ptr[2];
				sum_out_a -= stack_ptr[3];
 
				if (yp < hm)
				{
					src_ptr += w4; // stride
					++yp;
				}
 
				stack_ptr[0] = src_ptr[0];
				stack_ptr[1] = src_ptr[1];
				stack_ptr[2] = src_ptr[2];
				stack_ptr[3] = src_ptr[3];
 
				sum_in_r += src_ptr[0];
				sum_in_g += src_ptr[1];
				sum_in_b += src_ptr[2];
				sum_in_a += src_ptr[3];
				sum_r += sum_in_r;
				sum_g += sum_in_g;
				sum_b += sum_in_b;
				sum_a += sum_in_a;
 
				++sp;
				if (sp >= div) sp = 0;
				stack_ptr = &stack[sp * 4];
 
				sum_out_r += stack_ptr[0];
				sum_out_g += stack_ptr[1];
				sum_out_b += stack_ptr[2];
				sum_out_a += stack_ptr[3];
				sum_in_r -= stack_ptr[0];
				sum_in_g -= stack_ptr[1];
				sum_in_b -= stack_ptr[2];
				sum_in_a -= stack_ptr[3];
			}
		}
	}
 
}
 
 
class MVImageUtilsStackBlurTask
{
public:
	unsigned char* src;
	unsigned int w;
	unsigned int h;
	unsigned int radius;
	int cores;
	int core;
	int step;
	unsigned char* stack;
 
	inline MVImageUtilsStackBlurTask(unsigned char* src,unsigned int w,unsigned int h,unsigned int radius,int cores,int core,int step,unsigned char* stack)
	{
		this->src = src;
		this->w = w;
		this->h = h;
		this->radius = radius;
		this->cores = cores;
		this->core = core;
		this->step = step;
		this->stack = stack;
	}
 
	inline void run()
	{
		stackblurJob(src,w,h,radius,cores,core,step,stack);
	}
 
};
 
 
/// Stackblur algorithm by Mario Klingemann
/// Details here:
/// http://www.quasimondo.com/StackBlurForCanvas/StackBlurDemo.html
/// C++ implemenation base from:
/// https://gist.github.com/benjamin9999/3809142
/// http://www.antigrain.com/__code/include/agg_blur.h.html
/// This version works only with RGBA color
void 			   stackblur(unsigned char* src,///< blur intensity (should be in 2..254 range)
	int cores = 1						///< number of threads (1 - normal single thread)
	)
{
	if (radius > 254) return;
	if (radius < 2) return;
 
	unsigned int div = (radius * 2) + 1;
	unsigned char* stack = new unsigned char[div * 4 * cores];
 
	if (cores == 1)
	{
		// no multithreading
		stackblurJob(src,1,stack);
		stackblurJob(src,2,stack);
	}
 
 
	delete[] stack;
}
 
 
/**
* Capture screen implementation,don't use it directly.
*/
void onCaptureScreen(const std::function<void(bool,Image*)>& afterCaptured,int iScale)
{
	static bool startedCapture = false;
 
	if (startedCapture)
	{
		CCLOG("Screen capture is already working");
		if (afterCaptured)
		{
			afterCaptured(false,nullptr);
		}
		return;
	}
	else
	{
		startedCapture = true;
	}
 
 
	auto glView = Director::getInstance()->getOpenGLView();
	auto frameSize = glView->getFrameSize();
#if (CC_TARGET_PLATFORM == CC_PLATFORM_MAC) || (CC_TARGET_PLATFORM == CC_PLATFORM_WIN32) || (CC_TARGET_PLATFORM == CC_PLATFORM_LINUX)
	frameSize = frameSize * glView->getFrameZoomFactor() * glView->getRetinaFactor();
#endif
 
	int width = static_cast<int>(frameSize.width);
	int height = static_cast<int>(frameSize.height);
 
	do
	{
		std::shared_ptr<GLubyte> buffer(new GLubyte[width * height * 4],[](GLubyte* p){ CC_SAFE_DELETE_ARRAY(p); });
		if (!buffer)
		{
			break;
		}
 
		glPixelStorei(GL_PACK_ALIGNMENT,1);
		glReadPixels(0,width,height,GL_RGBA,GL_UNSIGNED_BYTE,buffer.get());
 
		std::shared_ptr<GLubyte> flippedBuffer(new GLubyte[width * height * 4],[](GLubyte* p) { CC_SAFE_DELETE_ARRAY(p); });
		if (!flippedBuffer)
		{
			break;
		}
 
		for (int row = 0; row < height; ++row)
		{
			memcpy(flippedBuffer.get() + (height - row - 1) * width * 4,buffer.get() + row * width * 4,width * 4);
		}
 
		/*-------------压缩start------------*/
		unsigned long dst_width = width / iScale;
		unsigned long dst_height = height / iScale;
 
		std::shared_ptr<GLubyte> zipFlippedBuffer(new GLubyte[dst_width * dst_height * 4],[](GLubyte* p) { CC_SAFE_DELETE_ARRAY(p); });
		if (!zipFlippedBuffer)
		{
			break;
		}
		unsigned long xrIntFloat_16 = (width << 16) / dst_width + 1;
		unsigned long yrIntFloat_16 = (height << 16) / dst_height + 1;
		unsigned long srcy_16 = 0;
 
		unsigned long byte_width = 4;//单个数据的物理宽度 4字节
		unsigned long byte_shift = 2;//单个数据的物理移位
 
		auto beginPos = zipFlippedBuffer.get();
 
		for (unsigned long y = 0; y < dst_height; ++y)
		{
			//auto pSrcLine = flippedBuffer.get() + width * byte_width * (srcy_16 >> 16);
			auto pSrcLine = flippedBuffer.get() + (width<<2)*(srcy_16>>16);
 
			unsigned long srcx_16 = 0;
			for (unsigned long x = 0; x < dst_width; ++x)
			{
				//memcpy(beginPos + x * byte_width,pSrcLine + (srcx_16 >> 16)*byte_width,byte_width);
				memcpy(beginPos + (x<<2),pSrcLine + ((srcx_16 >> 16)<<2),byte_width);
				srcx_16 += xrIntFloat_16;
			}
			srcy_16 += yrIntFloat_16;
			beginPos += (dst_width << byte_shift);
		}
		/*-------------压缩end------------*/
 
		//使用算法一次性对图片进行高斯模糊
		stackblur(zipFlippedBuffer.get(),dst_width,dst_height,5);
 
		Image* image = new (std::nothrow) Image;
		if (image)
		{
			image->initWithRawData(zipFlippedBuffer.get(),dst_width * dst_height * 4,8);
			image->autorelease();
			if (afterCaptured)
			{
				afterCaptured(true,image);
			}
		}
		else
		{
			CCLOG("Malloc Image memory Failed!");
			if (afterCaptured)
			{
				afterCaptured(false,nullptr);
			}
			delete image;
			image = nullptr;
		}
		startedCapture = false;
	} while (0);
}
 
 
/*
* 高斯模糊接口  缩放因子：iScale，截图会把全屏压缩为1/iScale大
*/
static EventListenerCustom* s_captureScreenListener;
static CustomCommand s_captureScreenCommand;
void Util::gaussianBlur(const std::function<void(bool,int iScale /*= 4*/)
{
	if (s_captureScreenListener)
	{
		CCLOG("Warning: CaptureScreen has been called already,don't call more than once in one frame.");
		return;
	}
	s_captureScreenCommand.init(std::numeric_limits<float>::max());
	s_captureScreenCommand.func = std::bind(onCaptureScreen,afterCaptured,iScale);
	s_captureScreenListener = Director::getInstance()->getEventDispatcher()->addCustomEventListener(Director::EVENT_AFTER_DRAW,[](EventCustom *event) {
		auto director = Director::getInstance();
		director->getEventDispatcher()->removeEventListener((EventListener*)(s_captureScreenListener));
		s_captureScreenListener = nullptr;
		director->getRenderer()->addCommand(&s_captureScreenCommand);
		director->getRenderer()->render();
	});
}

以下是导出的lua接口：

#include "base/ccConfig.h"
#ifndef __game_custom_h__
#define __game_custom_h__
 
#ifdef __cplusplus
extern "C" {
#endif
#include "tolua++.h"
#ifdef __cplusplus
}
#endif
 
int register_all_game_custom(lua_State* tolua_S);
 
#endif // __game_custom_h__

static int tolua_pf_common_gaussianBlur(lua_State* tolua_S)
{
	LUA_FUNCTION callbackHander = toluafix_ref_function(tolua_S,0);
	if (callbackHander == 0)
	{
		CCLOG("tolua_pf_common_gaussianBlur : toluafix_ref_function,error");
		return 0;
	}
 
	auto capture_callback = [=](bool succeed,Image* img){
		auto luastack = LuaEngine::getInstance()->getLuaStack();
 
		luastack->pushBoolean(succeed);
		if (succeed){
			luastack->pushObject(img,"cc.Image");
		}
		else{
			luastack->pushNil();
		}
		luastack->executeFunctionByHandler(callbackHander,2);
	};
 
 
	int argc = lua_gettop(tolua_S) - 1;
	if (argc == 2)
	{
		int q = 4;
		if (!luaval_to_int32(tolua_S,3,&q))
		{
			CCLOG("tolua_pf_common_gaussianBlur : luaval_to_number,error");
			return 0;
		}
		Util::gaussianBlur(capture_callback,q);
	}
	else
	{
		Util::gaussianBlur(capture_callback);
	}
	return 0;
}
 
TOLUA_API int register_all_game_custom(lua_State* tolua_S)
{
	tolua_open(tolua_S);
 
	tolua_module(tolua_S,"pf",0);
	tolua_beginmodule(tolua_S,"pf");
 
		tolua_module(tolua_S,"Common",0);
		tolua_beginmodule(tolua_S,"Common");
		{
			tolua_function(tolua_S,"GaussianBlur",tolua_pf_common_gaussianBlur);
		}
		tolua_endmodule(tolua_S);
 
	tolua_endmodule(tolua_S);
	return 1;
}

使用方法:

            local function onFinishCapture(ret,img)
                if ret then
                    local texture = cc.Director:getInstance():getTextureCache():addImage(img,"capriteadu")
                    local spriteBlur = cc.Sprite:createWithTexture(texture)
                    local wSize = cc.Director:getInstance():getWinSize()
                    spriteBlur:setPosition(cc.p(wSize.width/2,wSize.height/2))
                    self:addChild(spriteBlur)
                    PF.UIEx.nodeToScaleForFixedSize(spriteBlur,wSize)
                end
            end
            pf.Common:GaussianBlur(onFinishCapture,4)