mirror of
https://github.com/tangerineturtle1/NX2navi.git
synced 2026-11-15 19:19:58 -04:00
385734dcc0
FSR 3.1 was soft at Performance and Ultra Performance, most of all in motion. On a village save, while the camera turned at a steady rate (present screenshots every 0.4 s, the mean absolute Laplacian of the scene's luminance): FSR 3.1 Native AA 6.7, FSR 4 Performance 5.9 and Ultra Performance 5.4, FSR 3.1 Performance 4.0 and Ultra Performance 3.3. The library's own input checks found nothing wrong, and its tuning constants (velocity factor, accumulation per frame, shading change scale, behind the test switch NX2NAVI_FFX_KEYS) gave nothing or took detail away. Its own sharpening at 100 instead of the default 80 gave 5.0 and 4.1. Now the share of extra sharpening grows from none at three quarters of the output's width to all of it at half (vk_dlaa_fsr3_boost). FSR 3.1's own sharpness goes that share of the way to its maximum, and its picture gets a second RCAS pass (shaders/dlaa_sharpen.comp, AMD's FSR 1 header with the linear light taken through c / (1 + max c) and back), before the HUD is drawn. Both follow the sharpness slider; 0 turns them off, and NX2NAVI_FSR3_SHARPEN=0 leaves the second pass out. At RCAS's full strength the pass took Performance to 8.2, past Native AA, with grain on every surface, so it runs 1.5 stops weaker: Performance 5.7, Ultra Performance 4.7, Quality 5.2. 63.4 fps against 65.1 without the pass. The HDR picture is clean. FSR 4 is untouched. Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
52 lines
1.8 KiB
Plaintext
52 lines
1.8 KiB
Plaintext
// A second pass of AMD's robust contrast-adaptive sharpening (RCAS) over FSR 3.1's picture in its scaling modes
|
|
// (runtime/vk_dlaa.c fsr3_sharpen). ffx/ffx_a.h and ffx/ffx_fsr1.h are AMD's headers, unmodified (MIT,
|
|
// ffx/LICENSE.txt). The picture is linear scene light without an upper bound, and RCAS limits its sharpening by each
|
|
// channel's distance from 0 and from 1: every texel is taken through c / (1 + max(c)) on the way in, which keeps hue
|
|
// and maps any light into 0..1, and through the inverse on the way out.
|
|
#version 450
|
|
#extension GL_GOOGLE_include_directive : require
|
|
|
|
layout(local_size_x = 64, local_size_y = 1, local_size_z = 1) in;
|
|
|
|
layout(set = 0, binding = 0) uniform sampler2D src;
|
|
layout(set = 0, binding = 1, rgba16f) uniform writeonly image2D dst;
|
|
|
|
layout(push_constant) uniform Params {
|
|
vec4 size; // width, height, sharpness in stops (0 = most), unused
|
|
} pc;
|
|
|
|
#define A_GPU 1
|
|
#define A_GLSL 1
|
|
#include "ffx/ffx_a.h"
|
|
#define FSR_RCAS_F 1
|
|
AF4 FsrRcasLoadF(ASU2 p) {
|
|
vec4 c = texelFetch(src, p, 0);
|
|
c.rgb = max(c.rgb, vec3(0.0));
|
|
c.rgb /= 1.0 + max(c.r, max(c.g, c.b));
|
|
return c;
|
|
}
|
|
void FsrRcasInputF(inout AF1 r, inout AF1 g, inout AF1 b) {}
|
|
#include "ffx/ffx_fsr1.h"
|
|
|
|
void put(AU2 p, AU4 con) {
|
|
if (p.x >= uint(pc.size.x) || p.y >= uint(pc.size.y)) return;
|
|
AF3 c;
|
|
FsrRcasF(c.r, c.g, c.b, p, con);
|
|
c = clamp(c, vec3(0.0), vec3(1.0));
|
|
c /= max(1.0 - max(c.r, max(c.g, c.b)), 1.0 / 16384.0); // light up to 16,383 comes back as it went in
|
|
imageStore(dst, ivec2(p), vec4(c, 1.0));
|
|
}
|
|
|
|
void main() {
|
|
AU4 con;
|
|
FsrRcasCon(con, pc.size.z);
|
|
AU2 p = ARmp8x8(gl_LocalInvocationID.x) + AU2(gl_WorkGroupID.x << 4u, gl_WorkGroupID.y << 4u);
|
|
put(p, con);
|
|
p.x += 8u;
|
|
put(p, con);
|
|
p.y += 8u;
|
|
put(p, con);
|
|
p.x -= 8u;
|
|
put(p, con);
|
|
}
|