diff --git a/wled00/FX.h b/wled00/FX.h
index 66e74860..106a6712 100644
--- a/wled00/FX.h
+++ b/wled00/FX.h
@@ -582,7 +582,7 @@ typedef struct Segment {
     #endif
     uint32_t getPixelColor(int i);
     // 1D support functions (some implement 2D as well)
-    void blur(uint8_t);
+    void blur(uint8_t, bool smear = false);
     void fill(uint32_t c);
     void fade_out(uint8_t r);
     void fadeToBlackBy(uint8_t fadeBy);
@@ -610,7 +610,7 @@ typedef struct Segment {
     inline void setPixelColorXY(float x, float y, byte r, byte g, byte b, byte w = 0, bool aa = true) { setPixelColorXY(x, y, RGBW32(r,g,b,w), aa); }
     inline void setPixelColorXY(float x, float y, CRGB c, bool aa = true)                             { setPixelColorXY(x, y, RGBW32(c.r,c.g,c.b,0), aa); }
     #endif
-    uint32_t getPixelColorXY(uint16_t x, uint16_t y);
+    uint32_t getPixelColorXY(int x, int y);
     // 2D support functions
     inline void blendPixelColorXY(uint16_t x, uint16_t y, uint32_t color, uint8_t blend) { setPixelColorXY(x, y, color_blend(getPixelColorXY(x,y), color, blend)); }
     inline void blendPixelColorXY(uint16_t x, uint16_t y, CRGB c, uint8_t blend)         { blendPixelColorXY(x, y, RGBW32(c.r,c.g,c.b,0), blend); }
@@ -619,8 +619,8 @@ typedef struct Segment {
     inline void addPixelColorXY(int x, int y, CRGB c, bool fast = false)                             { addPixelColorXY(x, y, RGBW32(c.r,c.g,c.b,0), fast); }
     inline void fadePixelColorXY(uint16_t x, uint16_t y, uint8_t fade)                               { setPixelColorXY(x, y, color_fade(getPixelColorXY(x,y), fade, true)); }
     void box_blur(uint16_t i, bool vertical, fract8 blur_amount); // 1D box blur (with weight)
-    void blurRow(uint16_t row, fract8 blur_amount);
-    void blurCol(uint16_t col, fract8 blur_amount);
+    void blurRow(uint32_t row, fract8 blur_amount, bool smear = false);
+    void blurCol(uint32_t col, fract8 blur_amount, bool smear = false);
     void moveX(int8_t delta, bool wrap = false);
     void moveY(int8_t delta, bool wrap = false);
     void move(uint8_t dir, uint8_t delta, bool wrap = false);
@@ -655,8 +655,8 @@ typedef struct Segment {
     inline void addPixelColorXY(int x, int y, CRGB c, bool fast = false)          { addPixelColor(x, RGBW32(c.r,c.g,c.b,0), fast); }
     inline void fadePixelColorXY(uint16_t x, uint16_t y, uint8_t fade)            { fadePixelColor(x, fade); }
     inline void box_blur(uint16_t i, bool vertical, fract8 blur_amount) {}
-    inline void blurRow(uint16_t row, fract8 blur_amount) {}
-    inline void blurCol(uint16_t col, fract8 blur_amount) {}
+    inline void blurRow(uint32_t row, fract8 blur_amount, bool smear = false) {}
+    inline void blurCol(uint32_t col, fract8 blur_amount, bool smear = false) {}
     inline void moveX(int8_t delta, bool wrap = false) {}
     inline void moveY(int8_t delta, bool wrap = false) {}
     inline void move(uint8_t dir, uint8_t delta, bool wrap = false) {}
diff --git a/wled00/FX_2Dfcn.cpp b/wled00/FX_2Dfcn.cpp
index b049ab6f..5a73792b 100644
--- a/wled00/FX_2Dfcn.cpp
+++ b/wled00/FX_2Dfcn.cpp
@@ -175,11 +175,7 @@ void IRAM_ATTR Segment::setPixelColorXY(int x, int y, uint32_t col)
 
   uint8_t _bri_t = currentBri();
   if (_bri_t < 255) {
-    byte r = scale8(R(col), _bri_t);
-    byte g = scale8(G(col), _bri_t);
-    byte b = scale8(B(col), _bri_t);
-    byte w = scale8(W(col), _bri_t);
-    col = RGBW32(r, g, b, w);
+    col = color_fade(col, _bri_t);
   }
 
   if (reverse  ) x = virtualWidth()  - x - 1;
@@ -265,7 +261,7 @@ void Segment::setPixelColorXY(float x, float y, uint32_t col, bool aa)
 #endif
 
 // returns RGBW values of pixel
-uint32_t IRAM_ATTR Segment::getPixelColorXY(uint16_t x, uint16_t y) {
+uint32_t IRAM_ATTR Segment::getPixelColorXY(int x, int y) {
   if (!isActive()) return 0; // not active
   if (x >= virtualWidth() || y >= virtualHeight() || x<0 || y<0) return 0;  // if pixel would fall out of virtual segment just exit
   if (reverse  ) x = virtualWidth()  - x - 1;
@@ -278,59 +274,71 @@ uint32_t IRAM_ATTR Segment::getPixelColorXY(uint16_t x, uint16_t y) {
 }
 
 // blurRow: perform a blur on a row of a rectangular matrix
-void Segment::blurRow(uint16_t row, fract8 blur_amount) {
+void Segment::blurRow(uint32_t row, fract8 blur_amount, bool smear){
   if (!isActive() || blur_amount == 0) return; // not active
   const uint_fast16_t cols = virtualWidth();
   const uint_fast16_t rows = virtualHeight();
 
   if (row >= rows) return;
   // blur one row
-  uint8_t keep = 255 - blur_amount;
+  uint8_t keep = smear ? 255 : 255 - blur_amount;
   uint8_t seep = blur_amount >> 1;
-  CRGB carryover = CRGB::Black;
+  uint32_t carryover = BLACK;
+  uint32_t lastnew;
+  uint32_t last;
+  uint32_t curnew;
   for (unsigned x = 0; x < cols; x++) {
-    CRGB cur = getPixelColorXY(x, row);
-    CRGB before = cur;     // remember color before blur
-    CRGB part = cur;
-    part.nscale8(seep);
-    cur.nscale8(keep);
-    cur += carryover;
-    if (x>0) {
-      CRGB prev = CRGB(getPixelColorXY(x-1, row)) + part;
-      setPixelColorXY(x-1, row, prev);
+    uint32_t cur = getPixelColorXY(x, row);
+    uint32_t part = color_fade(cur, seep);
+    curnew = color_fade(cur, keep);
+    if (x > 0) {
+      if (carryover)
+        curnew = color_add(curnew, carryover, true);
+      uint32_t prev = color_add(lastnew, part, true);
+      if (last != prev) // optimization: only set pixel if color has changed
+        setPixelColorXY(x - 1, row, prev);
     }
-    if (before != cur)         // optimization: only set pixel if color has changed
-      setPixelColorXY(x, row, cur);
+    else // first pixel
+      setPixelColorXY(x, row, curnew);
+    lastnew = curnew;
+    last = cur; // save original value for comparison on next iteration
     carryover = part;
   }
+  setPixelColorXY(cols-1, row, curnew); // set last pixel
 }
 
 // blurCol: perform a blur on a column of a rectangular matrix
-void Segment::blurCol(uint16_t col, fract8 blur_amount) {
+void Segment::blurCol(uint32_t col, fract8 blur_amount, bool smear) {
   if (!isActive() || blur_amount == 0) return; // not active
   const uint_fast16_t cols = virtualWidth();
   const uint_fast16_t rows = virtualHeight();
 
   if (col >= cols) return;
   // blur one column
-  uint8_t keep = 255 - blur_amount;
+  uint8_t keep = smear ? 255 : 255 - blur_amount;
   uint8_t seep = blur_amount >> 1;
-  CRGB carryover = CRGB::Black;
+  uint32_t carryover = BLACK;
+  uint32_t lastnew;
+  uint32_t last;
+  uint32_t curnew;
   for (unsigned y = 0; y < rows; y++) {
-    CRGB cur = getPixelColorXY(col, y);
-    CRGB part = cur;
-    CRGB before = cur;     // remember color before blur
-    part.nscale8(seep);
-    cur.nscale8(keep);
-    cur += carryover;
-    if (y>0) {
-      CRGB prev = CRGB(getPixelColorXY(col, y-1)) + part;
-      setPixelColorXY(col, y-1, prev);
+    uint32_t cur = getPixelColorXY(col, y);
+    uint32_t part = color_fade(cur, seep);
+    curnew = color_fade(cur, keep);
+    if (y > 0) {
+      if (carryover)
+        curnew = color_add(curnew, carryover, true);
+      uint32_t prev = color_add(lastnew, part, true);      
+      if (last != prev) // optimization: only set pixel if color has changed
+        setPixelColorXY(col, y - 1, prev);
     }
-    if (before != cur)         // optimization: only set pixel if color has changed
-      setPixelColorXY(col, y, cur);
-    carryover = part;
+    else // first pixel
+      setPixelColorXY(col, y, curnew);
+    lastnew = curnew;
+    last = cur; //save original value for comparison on next iteration
+    carryover = part;        
   }
+  setPixelColorXY(col, rows - 1, curnew);
 }
 
 // 1D Box blur (with added weight - blur_amount: [0=no blur, 255=max blur])
diff --git a/wled00/FX_fcn.cpp b/wled00/FX_fcn.cpp
index 9ab1f578..f3f74ba2 100644
--- a/wled00/FX_fcn.cpp
+++ b/wled00/FX_fcn.cpp
@@ -735,11 +735,7 @@ void IRAM_ATTR Segment::setPixelColor(int i, uint32_t col)
   uint16_t len = length();
   uint8_t _bri_t = currentBri();
   if (_bri_t < 255) {
-    byte r = scale8(R(col), _bri_t);
-    byte g = scale8(G(col), _bri_t);
-    byte b = scale8(B(col), _bri_t);
-    byte w = scale8(W(col), _bri_t);
-    col = RGBW32(r, g, b, w);
+    col = color_fade(col, _bri_t);
   }
 
   // expand pixel (taking into account start, grouping, spacing [and offset])
@@ -995,33 +991,43 @@ void Segment::fadeToBlackBy(uint8_t fadeBy) {
 /*
  * blurs segment content, source: FastLED colorutils.cpp
  */
-void Segment::blur(uint8_t blur_amount) {
+void Segment::blur(uint8_t blur_amount, bool smear) {
   if (!isActive() || blur_amount == 0) return; // optimization: 0 means "don't blur"
 #ifndef WLED_DISABLE_2D
   if (is2D()) {
     // compatibility with 2D
     const unsigned cols = virtualWidth();
     const unsigned rows = virtualHeight();
-    for (unsigned i = 0; i < rows; i++) blurRow(i, blur_amount); // blur all rows
-    for (unsigned k = 0; k < cols; k++) blurCol(k, blur_amount); // blur all columns
+    for (unsigned i = 0; i < rows; i++) blurRow(i, blur_amount, smear); // blur all rows
+    for (unsigned k = 0; k < cols; k++) blurCol(k, blur_amount, smear); // blur all columns
     return;
   }
 #endif
-  uint8_t keep = 255 - blur_amount;
+  uint8_t keep = smear ? 255 : 255 - blur_amount;
   uint8_t seep = blur_amount >> 1;
-  uint32_t carryover = BLACK;
   unsigned vlength = virtualLength();
+  uint32_t carryover = BLACK;
+  uint32_t lastnew;
+  uint32_t last;
+  uint32_t curnew;
   for (unsigned i = 0; i < vlength; i++) {
     uint32_t cur = getPixelColor(i);
     uint32_t part = color_fade(cur, seep);
-    cur = color_add(color_fade(cur, keep), carryover, true);
+    curnew = color_fade(cur, keep);
     if (i > 0) {
-      uint32_t c = getPixelColor(i-1);
-      setPixelColor(i-1, color_add(c, part, true));
+      if (carryover)
+        curnew = color_add(curnew, carryover, true);
+      uint32_t prev = color_add(lastnew, part, true);
+      if (last != prev) // optimization: only set pixel if color has changed
+        setPixelColor(i - 1, prev);
     }
-    setPixelColor(i, cur);
+    else // first pixel
+      setPixelColor(i, curnew);
+    lastnew = curnew;
+    last = cur; // save original value for comparison on next iteration
     carryover = part;
   }
+  setPixelColor(vlength - 1, curnew);
 }
 
 /*
diff --git a/wled00/colors.cpp b/wled00/colors.cpp
index 3ed54d95..30d2c069 100644
--- a/wled00/colors.cpp
+++ b/wled00/colors.cpp
@@ -65,24 +65,30 @@ uint32_t color_add(uint32_t c1, uint32_t c2, bool fast)
  * fades color toward black
  * if using "video" method the resulting color will never become black unless it is already black
  */
+
 uint32_t color_fade(uint32_t c1, uint8_t amount, bool video)
 {
-  uint8_t r = R(c1);
-  uint8_t g = G(c1);
-  uint8_t b = B(c1);
-  uint8_t w = W(c1);
-  if (video) {
-    r = scale8_video(r, amount);
-    g = scale8_video(g, amount);
-    b = scale8_video(b, amount);
-    w = scale8_video(w, amount);
-  } else {
-    r = scale8(r, amount);
-    g = scale8(g, amount);
-    b = scale8(b, amount);
-    w = scale8(w, amount);
+  uint32_t scaledcolor; // color order is: W R G B from MSB to LSB
+  uint32_t r = R(c1);
+  uint32_t g = G(c1);
+  uint32_t b = B(c1);
+  uint32_t w = W(c1);
+  if (video)  {
+    uint32_t scale = amount; // 32bit for faster calculation
+    scaledcolor = (((r * scale) >> 8) << 16) + ((r && scale) ? 1 : 0);
+    scaledcolor |= (((g * scale) >> 8) << 8) + ((g && scale) ? 1 : 0);
+    scaledcolor |= ((b * scale) >> 8) + ((b && scale) ? 1 : 0);
+    scaledcolor |= (((w * scale) >> 8) << 24) + ((w && scale) ? 1 : 0);
+    return scaledcolor;
+  }
+  else  {
+    uint32_t scale = 1 + amount;
+    scaledcolor = ((r * scale) >> 8) << 16;
+    scaledcolor |= ((g * scale) >> 8) << 8;
+    scaledcolor |= (b * scale) >> 8;
+    scaledcolor |= ((w * scale) >> 8) << 24;
+    return scaledcolor;
   }
-  return RGBW32(r, g, b, w);
 }
 
 void setRandomColor(byte* rgb)