vo_opengl: add tscale-clamp option

This significantly reduces the amount of noticeable flashing when using
tscale kernels with negative lobes, by cutting them off completely.

I'm not sure if this has any negative effects. It needs a bit of
subjective testing over a period of time, so I just made it an option.

Fixes #2155.

4 files changed, 9 insertions, 2 deletions

diff --git a/video/out/filter_kernels.c b/video/out/filter_kernels.c
index a748ac10ab..0f6d5a98bc 100644
--- a/video/out/filter_kernels.c
+++ b/video/out/filter_kernels.c
@@ -113,7 +113,8 @@ static double sample_filter(struct filter_kernel *filter,
     double w = window->weight ? window->weight(window, x/bw * window->radius
                                                             / filter->f.radius)
                               : 1.0;
-    return c < filter->f.radius ? w * filter->f.weight(&filter->f, c) : 0.0;
+    double v = c < filter->f.radius ? w * filter->f.weight(&filter->f, c) : 0.0;
+    return filter->clamp ? fmax(0.0, fmin(1.0, v)) : v;
 }
 
 // Calculate the 1D filtering kernel for N sample points.
diff --git a/video/out/filter_kernels.h b/video/out/filter_kernels.h
index 9e6176293f..7b101cdd35 100644
--- a/video/out/filter_kernels.h
+++ b/video/out/filter_kernels.h
@@ -33,6 +33,7 @@ struct filter_window {
 struct filter_kernel {
     struct filter_window f; // the kernel itself
     struct filter_window w; // window storage
+    bool clamp; // clamp to the range [0-1]
     // Constant values
     const char *window; // default window
     bool polar;         // whether or not the filter uses polar coordinates
diff --git a/video/out/gl_video.c b/video/out/gl_video.c
index a1d100f4dc..4eb4030244 100644
--- a/video/out/gl_video.c
+++ b/video/out/gl_video.c
@@ -415,6 +415,7 @@ const struct m_sub_options gl_video_conf = {
         OPT_FLOATRANGE("dscale-antiring", scaler[1].antiring, 0, 0.0, 1.0),
         OPT_FLOATRANGE("cscale-antiring", scaler[2].antiring, 0, 0.0, 1.0),
         OPT_FLOATRANGE("tscale-antiring", scaler[3].antiring, 0, 0.0, 1.0),
+        OPT_FLAG("tscale-clamp", scaler[3].clamp, 0),
         OPT_FLAG("scaler-resizes-only", scaler_resizes_only, 0),
         OPT_FLAG("linear-scaling", linear_scaling, 0),
         OPT_FLAG("fancy-downscaling", fancy_downscaling, 0),
@@ -950,7 +951,8 @@ static bool scaler_conf_eq(struct scaler_config a, struct scaler_config b)
     // generation
     return scaler_fun_eq(a.kernel, b.kernel) &&
            scaler_fun_eq(a.window, b.window) &&
-           a.radius == b.radius;
+           a.radius == b.radius &&
+           a.clamp == b.clamp;
 }
 
 static void reinit_scaler(struct gl_video *p, struct scaler *scaler,
@@ -1001,6 +1003,8 @@ static void reinit_scaler(struct gl_video *p, struct scaler *scaler,
     if (scaler->kernel->f.resizable && conf->radius > 0.0)
         scaler->kernel->f.radius = conf->radius;
 
+    scaler->kernel->clamp = conf->clamp;
+
     scaler->insufficient = !mp_init_filter(scaler->kernel, sizes, scale_factor);
 
     if (scaler->kernel->polar) {
diff --git a/video/out/gl_video.h b/video/out/gl_video.h
index 0881025a14..385477e051 100644
--- a/video/out/gl_video.h
+++ b/video/out/gl_video.h
@@ -39,6 +39,7 @@ struct scaler_config {
     struct scaler_fun window;
     float radius;
     float antiring;
+    int clamp;
 };
 
 struct gl_video_opts {