diff --git a/video/out/opengl/context_glx.c b/video/out/opengl/context_glx.c
index 677260c197..6ca9f19d3e 100644
--- a/video/out/opengl/context_glx.c
+++ b/video/out/opengl/context_glx.c
@@ -223,6 +223,11 @@ static void update_vsync_oml(struct ra_ctx *ctx)
     oml_sync_swap(&p->sync, ust, msc, sbc);
 }
 
+static bool glx_check_visible(struct ra_ctx *ctx)
+{
+    return vo_x11_check_visible(ctx->vo);
+}
+
 static void glx_swap_buffers(struct ra_ctx *ctx)
 {
     struct priv *p = ctx->priv;
@@ -313,6 +318,7 @@ static bool glx_init(struct ra_ctx *ctx)
         goto uninit;
 
     struct ra_gl_ctx_params params = {
+        .check_visible = glx_check_visible,
         .swap_buffers = glx_swap_buffers,
         .get_vsync    = glx_get_vsync,
     };
diff --git a/video/out/opengl/context_x11egl.c b/video/out/opengl/context_x11egl.c
index f1596bcee4..4e0b277da7 100644
--- a/video/out/opengl/context_x11egl.c
+++ b/video/out/opengl/context_x11egl.c
@@ -75,6 +75,11 @@ static int pick_xrgba_config(void *user_data, EGLConfig *configs, int num_config
     return 0;
 }
 
+static bool mpegl_check_visible(struct ra_ctx *ctx)
+{
+    return vo_x11_check_visible(ctx->vo);
+}
+
 static void mpegl_swap_buffers(struct ra_ctx *ctx)
 {
     struct priv *p = ctx->priv;
@@ -169,6 +174,7 @@ static bool mpegl_init(struct ra_ctx *ctx)
     mpegl_load_functions(&p->gl, ctx->log);
 
     struct ra_gl_ctx_params params = {
+        .check_visible = mpegl_check_visible,
         .swap_buffers = mpegl_swap_buffers,
         .get_vsync    = mpegl_get_vsync,
     };
diff --git a/video/out/vo_x11.c b/video/out/vo_x11.c
index 67fac3c9a7..6b7a797412 100644
--- a/video/out/vo_x11.c
+++ b/video/out/vo_x11.c
@@ -315,6 +315,9 @@ static void draw_image(struct vo *vo, mp_image_t *mpi)
     struct priv *p = vo->priv;
 
     wait_for_completion(vo, 1);
+    bool render = vo_x11_check_visible(vo);
+    if (!render)
+        return;
 
     struct mp_image *img = &p->mp_ximages[p->current_buf];
 
diff --git a/video/out/vo_xv.c b/video/out/vo_xv.c
index 43fc046f9f..d93673493f 100644
--- a/video/out/vo_xv.c
+++ b/video/out/vo_xv.c
@@ -697,6 +697,9 @@ static void draw_image(struct vo *vo, mp_image_t *mpi)
     struct xvctx *ctx = vo->priv;
 
     wait_for_completion(vo, ctx->num_buffers - 1);
+    bool render = vo_x11_check_visible(vo);
+    if (!render)
+        return;
 
     struct mp_image xv_buffer = get_xv_buffer(vo, ctx->current_buf);
     if (mpi) {
diff --git a/video/out/vulkan/context_xlib.c b/video/out/vulkan/context_xlib.c
index 6278bc3c69..2d498723df 100644
--- a/video/out/vulkan/context_xlib.c
+++ b/video/out/vulkan/context_xlib.c
@@ -26,6 +26,11 @@ struct priv {
     struct mpvk_ctx vk;
 };
 
+static bool xlib_check_visible(struct ra_ctx *ctx)
+{
+    return vo_x11_check_visible(ctx->vo);
+}
+
 static void xlib_uninit(struct ra_ctx *ctx)
 {
     struct priv *p = ctx->priv;
@@ -56,7 +61,9 @@ static bool xlib_init(struct ra_ctx *ctx)
          .window = ctx->vo->x11->window,
     };
 
-    struct ra_vk_ctx_params params = {0};
+    struct ra_vk_ctx_params params = {
+        .check_visible = xlib_check_visible,
+    };
 
     VkInstance inst = vk->vkinst->instance;
     VkResult res = vkCreateXlibSurfaceKHR(inst, &xinfo, NULL, &vk->surface);
diff --git a/video/out/x11_common.c b/video/out/x11_common.c
index d1fb3b6f0a..d8cda687f8 100644
--- a/video/out/x11_common.c
+++ b/video/out/x11_common.c
@@ -1043,6 +1043,7 @@ static void vo_x11_check_net_wm_state_change(struct vo *vo)
         }
 
         opts->window_minimized = is_minimized;
+        x11->hidden = is_minimized;
         m_config_cache_write_opt(x11->opts_cache, &opts->window_minimized);
         opts->window_maximized = is_maximized;
         m_config_cache_write_opt(x11->opts_cache, &opts->window_maximized);
@@ -1863,6 +1864,14 @@ static void vo_x11_set_geometry(struct vo *vo)
     }
 }
 
+bool vo_x11_check_visible(struct vo *vo) {
+    struct vo_x11_state *x11 = vo->x11;
+    struct mp_vo_opts *opts = x11->opts;
+
+    bool render = !x11->hidden || VS_IS_DISP(opts->video_sync);
+    return render;
+}
+
 int vo_x11_control(struct vo *vo, int *events, int request, void *arg)
 {
     struct vo_x11_state *x11 = vo->x11;
diff --git a/video/out/x11_common.h b/video/out/x11_common.h
index 45c8d04d21..acc08f2ee0 100644
--- a/video/out/x11_common.h
+++ b/video/out/x11_common.h
@@ -80,6 +80,7 @@ struct vo_x11_state {
     Colormap colormap;
 
     int wm_type;
+    bool hidden; // _NET_WM_STATE_HIDDEN
     bool window_hidden; // the window was mapped at least once
     bool pseudo_mapped; // not necessarily mapped, but known window size
     int fs;     // whether we assume the window is in fullscreen mode
@@ -142,6 +143,7 @@ bool vo_x11_screen_is_composited(struct vo *vo);
 bool vo_x11_create_vo_window(struct vo *vo, XVisualInfo *vis,
                              const char *classname);
 void vo_x11_config_vo_window(struct vo *vo);
+bool vo_x11_check_visible(struct vo *vo);
 int vo_x11_control(struct vo *vo, int *events, int request, void *arg);
 void vo_x11_wakeup(struct vo *vo);
 void vo_x11_wait_events(struct vo *vo, int64_t until_time_us);