Prepare to unify with dither_dhr.pyx
This commit is contained in:
kris
parent
762a21556a
commit
d47defbd80
|
|
@ -9,6 +9,8 @@ from libc.stdlib cimport malloc, free
|
|||
|
||||
cimport common
|
||||
|
||||
import screen as screen_py
|
||||
|
||||
|
||||
# TODO: use a cdef class
|
||||
# C representation of dither_pattern.DitherPattern data, for efficient access.
|
||||
|
|
@ -98,6 +100,13 @@ cdef unsigned int compute_fat_pixels(unsigned int screen_byte, unsigned char las
|
|||
return result
|
||||
|
||||
|
||||
cdef struct Context:
|
||||
unsigned char bit_lookahead
|
||||
unsigned char pixel_lookahead
|
||||
unsigned char phase_shift
|
||||
unsigned char is_hgr
|
||||
|
||||
|
||||
# Look ahead a number of pixels and compute choice for next pixel with lowest total squared error after dithering.
|
||||
#
|
||||
# Args:
|
||||
|
|
@ -113,32 +122,31 @@ cdef unsigned int compute_fat_pixels(unsigned int screen_byte, unsigned char las
|
|||
#
|
||||
# Returns: index from 0 .. 2**lookahead into options_nbit representing best available choice for position (x,y)
|
||||
#
|
||||
cdef int dither_lookahead(Dither* dither, float[:, :, ::1] palette_cam16, float[:, :, ::1] palette_rgb,
|
||||
float[:, :, ::1] image_rgb, int x, int y, int lookahead, unsigned char last_pixels,
|
||||
int x_res, float[:,::1] rgb_to_cam16ucs, unsigned char palette_depth) nogil:
|
||||
cdef int candidate_pixels, i, j, fat_pixels
|
||||
cdef int dither_lookahead(Dither* dither, unsigned char palette_depth, float[:, :, ::1] palette_cam16,
|
||||
float[:, :, ::1] palette_rgb, float[:, :, ::1] image_rgb, int x, int y, unsigned char last_pixels,
|
||||
int x_res, float[:,::1] rgb_to_cam16ucs, Context context) nogil:
|
||||
cdef int candidate, next_pixels, i, j
|
||||
cdef float[3] quant_error
|
||||
cdef int best
|
||||
cdef float best_error = 2**31-1
|
||||
cdef float total_error
|
||||
cdef unsigned char next_pixels
|
||||
cdef unsigned char current_pixels
|
||||
cdef int phase
|
||||
cdef float[::1] lah_cam16ucs
|
||||
|
||||
# Don't bother dithering past the lookahead horizon or edge of screen.
|
||||
cdef int xxr = min(x + 15, x_res) # XXX
|
||||
cdef int xxr = min(x + context.pixel_lookahead, x_res)
|
||||
|
||||
cdef int lah_shape1 = xxr - x
|
||||
cdef int lah_shape2 = 3
|
||||
cdef float *lah_image_rgb = <float *> malloc(lah_shape1 * lah_shape2 * sizeof(float))
|
||||
|
||||
|
||||
# For each 2**lookahead possibilities for the on/off state of the next lookahead pixels, apply error diffusion
|
||||
# and compute the total squared error to the source image. Since we only have two possible colours for each
|
||||
# given pixel (dependent on the state already chosen for pixels to the left), we need to look beyond local minima.
|
||||
# i.e. it might be better to make a sub-optimal choice for this pixel if it allows access to much better pixel
|
||||
# colours at later positions.
|
||||
for candidate_pixels in range(1 << lookahead):
|
||||
for candidate in range(1 << context.bit_lookahead):
|
||||
# Working copy of input pixels
|
||||
for i in range(xxr - x):
|
||||
for j in range(3):
|
||||
|
|
@ -146,28 +154,34 @@ cdef int dither_lookahead(Dither* dither, float[:, :, ::1] palette_cam16, float[
|
|||
|
||||
total_error = 0
|
||||
|
||||
fat_pixels = compute_fat_pixels(candidate_pixels, last_pixels)
|
||||
if context.is_hgr:
|
||||
# A HGR screen byte controls 14 or 15 screen pixels
|
||||
next_pixels = compute_fat_pixels(candidate, last_pixels)
|
||||
else:
|
||||
# DHGR pixels are 1:1 with memory bits
|
||||
next_pixels = candidate
|
||||
|
||||
# Apply dithering to lookahead horizon or edge of screen
|
||||
for i in range(xxr - x):
|
||||
xl = dither_bounds_xl(dither, i)
|
||||
xr = dither_bounds_xr(dither, xxr - x, i)
|
||||
phase = (x + i + 3) % 4 # XXX
|
||||
phase = (x + i + context.phase_shift) % 4
|
||||
|
||||
next_pixels = shift_pixel_window(
|
||||
last_pixels, next_pixels=fat_pixels, shift_right_by=i+1, window_width=palette_depth)
|
||||
current_pixels = shift_pixel_window(
|
||||
last_pixels, next_pixels=next_pixels, shift_right_by=i+1, window_width=palette_depth)
|
||||
|
||||
# We don't update the input at position x (since we've already chosen fixed outputs), but we do propagate
|
||||
# quantization errors to positions >x so we can compensate for how good/bad these choices were. i.e. the
|
||||
# next_pixels choices are fixed, but we can still distribute quantization error from having made these
|
||||
# current_pixels choices are fixed, but we can still distribute quantization error from having made these
|
||||
# choices, in order to compute the total error.
|
||||
for j in range(3):
|
||||
quant_error[j] = lah_image_rgb[i * lah_shape2 + j] - palette_rgb[next_pixels, phase, j]
|
||||
quant_error[j] = lah_image_rgb[i * lah_shape2 + j] - palette_rgb[current_pixels, phase, j]
|
||||
apply_one_line(dither, xl, xr, i, lah_image_rgb, lah_shape2, quant_error)
|
||||
|
||||
lah_cam16ucs = common.convert_rgb_to_cam16ucs(
|
||||
rgb_to_cam16ucs, lah_image_rgb[i*lah_shape2], lah_image_rgb[i*lah_shape2+1],
|
||||
lah_image_rgb[i*lah_shape2+2])
|
||||
total_error += common.colour_distance_squared(lah_cam16ucs, palette_cam16[next_pixels, phase])
|
||||
total_error += common.colour_distance_squared(lah_cam16ucs, palette_cam16[current_pixels, phase])
|
||||
|
||||
if total_error >= best_error:
|
||||
# No need to continue
|
||||
|
|
@ -175,7 +189,7 @@ cdef int dither_lookahead(Dither* dither, float[:, :, ::1] palette_cam16, float[
|
|||
|
||||
if total_error < best_error:
|
||||
best_error = total_error
|
||||
best = candidate_pixels
|
||||
best = candidate
|
||||
|
||||
free(lah_image_rgb)
|
||||
return best
|
||||
|
|
@ -231,6 +245,7 @@ cdef void apply(Dither* dither, int x_res, int y_res, int x, int y, float[:,:,::
|
|||
for k in range(3):
|
||||
image[i,j,k] = common.clip(image[i,j,k] + error_fraction * quant_error[k], 0, 1)
|
||||
|
||||
|
||||
cdef image_nbit_to_bitmap(
|
||||
(unsigned char)[:, ::1] image_nbit, unsigned int x_res, unsigned int y_res, unsigned char palette_depth):
|
||||
cdef unsigned int x, y
|
||||
|
|
@ -257,10 +272,9 @@ def dither_image(
|
|||
screen, float[:, :, ::1] image_rgb, dither, int lookahead, unsigned char verbose, float[:,::1] rgb_to_cam16ucs):
|
||||
cdef int y, x
|
||||
cdef unsigned char i, j, pixels_nbit, phase
|
||||
# cdef float[3] input_pixel_rgb
|
||||
cdef float[3] quant_error
|
||||
cdef unsigned char output_pixel_nbit
|
||||
cdef unsigned int best_next_pixels
|
||||
cdef unsigned int next_pixels
|
||||
cdef float[3] output_pixel_rgb
|
||||
|
||||
# Hoist some python attribute accesses into C variables for efficient access during the main loop
|
||||
|
|
@ -298,28 +312,52 @@ def dither_image(
|
|||
# dot positions are used to determine the colour of a given pixel.
|
||||
cdef (unsigned char)[:, ::1] image_nbit = np.empty((image_rgb.shape[0], image_rgb.shape[1]), dtype=np.uint8)
|
||||
|
||||
cdef Context context
|
||||
if screen.MODE == screen_py.Mode.HI_RES:
|
||||
context.is_hgr = 1
|
||||
context.bit_lookahead = 8
|
||||
context.pixel_lookahead = 15
|
||||
# HGR and DHGR have a timing phase shift which rotates the effective mappings from screen dots to colours
|
||||
context.phase_shift = 3
|
||||
else:
|
||||
context.is_hgr = 0
|
||||
context.bit_lookahead = lookahead
|
||||
context.pixel_lookahead = lookahead
|
||||
context.phase_shift = 0
|
||||
|
||||
cdef (unsigned char)[:, ::1] linear_bytemap = np.zeros((192, 40), dtype=np.uint8)
|
||||
cdef unsigned int fat_pixels
|
||||
|
||||
# After performing lookahead, move ahead this many pixels at once.
|
||||
cdef int apply_batch_size
|
||||
if context.is_hgr:
|
||||
# For HGR we have to apply an entire screen byte at a time, which controls 14 or 15 pixels (see
|
||||
# compute_fat_pixels above). This is because the high bit shifts this entire group of 14 pixels at once,
|
||||
# so we have to make a single decision about whether or not to enable it.
|
||||
apply_batch_size = 14
|
||||
else:
|
||||
# For DHGR we can choose each pixel state independently, so we get better results if we apply one pixel at
|
||||
# a time.
|
||||
apply_batch_size = 1
|
||||
|
||||
for y in range(yres):
|
||||
if verbose:
|
||||
print("%d/%d" % (y, yres))
|
||||
output_pixel_nbit = 0
|
||||
for x in range(xres):
|
||||
if x % 14 == 0:
|
||||
if x % apply_batch_size == 0:
|
||||
# Compute all possible 2**N choices of n-bit pixel colours for positions x .. x + lookahead
|
||||
# lookahead_palette_choices_nbit = lookahead_options(lookahead, output_pixel_nbit)
|
||||
# Apply error diffusion for each of these 2**N choices, and compute which produces the closest match
|
||||
# to the source image over the succeeding N pixels
|
||||
best_next_pixels = dither_lookahead(
|
||||
&cdither, palette_cam16, palette_rgb, image_rgb, x, y, lookahead, output_pixel_nbit, xres,
|
||||
rgb_to_cam16ucs, palette_depth)
|
||||
linear_bytemap[y, x // 14] = best_next_pixels
|
||||
fat_pixels = compute_fat_pixels(best_next_pixels, output_pixel_nbit)
|
||||
next_pixels = dither_lookahead(
|
||||
&cdither, palette_depth, palette_cam16, palette_rgb, image_rgb, x, y, output_pixel_nbit, xres,
|
||||
rgb_to_cam16ucs, context)
|
||||
if context.is_hgr:
|
||||
linear_bytemap[y, x // 14] = next_pixels
|
||||
next_pixels = compute_fat_pixels(next_pixels, output_pixel_nbit)
|
||||
|
||||
# Apply best choice for next 1 pixel
|
||||
output_pixel_nbit = shift_pixel_window(
|
||||
output_pixel_nbit, fat_pixels, shift_right_by=x%14 + 1, window_width=palette_depth)
|
||||
output_pixel_nbit, next_pixels, shift_right_by=x % apply_batch_size + 1, window_width=palette_depth)
|
||||
# Apply error diffusion from chosen output pixel value
|
||||
for i in range(3):
|
||||
output_pixel_rgb[i] = palette_rgb[output_pixel_nbit, x % 4, i]
|
||||
|
|
|
|||
Loading…
Reference in New Issue