FFmpeg  4.4.5
vf_derain.c
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2019 Xuewei Meng
3  *
4  * This file is part of FFmpeg.
5  *
6  * FFmpeg is free software; you can redistribute it and/or
7  * modify it under the terms of the GNU Lesser General Public
8  * License as published by the Free Software Foundation; either
9  * version 2.1 of the License, or (at your option) any later version.
10  *
11  * FFmpeg is distributed in the hope that it will be useful,
12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14  * Lesser General Public License for more details.
15  *
16  * You should have received a copy of the GNU Lesser General Public
17  * License along with FFmpeg; if not, write to the Free Software
18  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
19  */
20 
21 /**
22  * @file
23  * Filter implementing image derain filter using deep convolutional networks.
24  * http://openaccess.thecvf.com/content_ECCV_2018/html/Xia_Li_Recurrent_Squeeze-and-Excitation_Context_ECCV_2018_paper.html
25  */
26 
27 #include "libavformat/avio.h"
28 #include "libavutil/opt.h"
29 #include "avfilter.h"
30 #include "dnn_filter_common.h"
31 #include "formats.h"
32 #include "internal.h"
33 
34 typedef struct DRContext {
35  const AVClass *class;
38 } DRContext;
39 
40 #define OFFSET(x) offsetof(DRContext, x)
41 #define FLAGS AV_OPT_FLAG_FILTERING_PARAM | AV_OPT_FLAG_VIDEO_PARAM
42 static const AVOption derain_options[] = {
43  { "filter_type", "filter type(derain/dehaze)", OFFSET(filter_type), AV_OPT_TYPE_INT, { .i64 = 0 }, 0, 1, FLAGS, "type" },
44  { "derain", "derain filter flag", 0, AV_OPT_TYPE_CONST, { .i64 = 0 }, 0, 0, FLAGS, "type" },
45  { "dehaze", "dehaze filter flag", 0, AV_OPT_TYPE_CONST, { .i64 = 1 }, 0, 0, FLAGS, "type" },
46  { "dnn_backend", "DNN backend", OFFSET(dnnctx.backend_type), AV_OPT_TYPE_INT, { .i64 = 0 }, 0, 1, FLAGS, "backend" },
47  { "native", "native backend flag", 0, AV_OPT_TYPE_CONST, { .i64 = 0 }, 0, 0, FLAGS, "backend" },
48 #if (CONFIG_LIBTENSORFLOW == 1)
49  { "tensorflow", "tensorflow backend flag", 0, AV_OPT_TYPE_CONST, { .i64 = 1 }, 0, 0, FLAGS, "backend" },
50 #endif
51  { "model", "path to model file", OFFSET(dnnctx.model_filename), AV_OPT_TYPE_STRING, { .str = NULL }, 0, 0, FLAGS },
52  { "input", "input name of the model", OFFSET(dnnctx.model_inputname), AV_OPT_TYPE_STRING, { .str = "x" }, 0, 0, FLAGS },
53  { "output", "output name of the model", OFFSET(dnnctx.model_outputname), AV_OPT_TYPE_STRING, { .str = "y" }, 0, 0, FLAGS },
54  { NULL }
55 };
56 
58 
60 {
62  const enum AVPixelFormat pixel_fmts[] = {
65  };
66 
67  formats = ff_make_format_list(pixel_fmts);
68 
70 }
71 
72 static int filter_frame(AVFilterLink *inlink, AVFrame *in)
73 {
74  AVFilterContext *ctx = inlink->dst;
75  AVFilterLink *outlink = ctx->outputs[0];
76  DRContext *dr_context = ctx->priv;
77  DNNReturnType dnn_result;
78  AVFrame *out;
79 
80  out = ff_get_video_buffer(outlink, outlink->w, outlink->h);
81  if (!out) {
82  av_log(ctx, AV_LOG_ERROR, "could not allocate memory for output frame\n");
83  av_frame_free(&in);
84  return AVERROR(ENOMEM);
85  }
87 
88  dnn_result = ff_dnn_execute_model(&dr_context->dnnctx, in, out);
89  if (dnn_result != DNN_SUCCESS){
90  av_log(ctx, AV_LOG_ERROR, "failed to execute model\n");
91  av_frame_free(&in);
92  return AVERROR(EIO);
93  }
94 
95  av_frame_free(&in);
96 
97  return ff_filter_frame(outlink, out);
98 }
99 
101 {
102  DRContext *dr_context = ctx->priv;
103  return ff_dnn_init(&dr_context->dnnctx, DFT_PROCESS_FRAME, ctx);
104 }
105 
107 {
108  DRContext *dr_context = ctx->priv;
109  ff_dnn_uninit(&dr_context->dnnctx);
110 }
111 
112 static const AVFilterPad derain_inputs[] = {
113  {
114  .name = "default",
115  .type = AVMEDIA_TYPE_VIDEO,
116  .filter_frame = filter_frame,
117  },
118  { NULL }
119 };
120 
121 static const AVFilterPad derain_outputs[] = {
122  {
123  .name = "default",
124  .type = AVMEDIA_TYPE_VIDEO,
125  },
126  { NULL }
127 };
128 
130  .name = "derain",
131  .description = NULL_IF_CONFIG_SMALL("Apply derain filter to the input."),
132  .priv_size = sizeof(DRContext),
133  .init = init,
134  .uninit = uninit,
138  .priv_class = &derain_class,
140 };
static const AVFilterPad inputs[]
Definition: af_acontrast.c:193
static const AVFilterPad outputs[]
Definition: af_acontrast.c:203
#define av_cold
Definition: attributes.h:88
uint8_t pi<< 24) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_U8, uint8_t,(*(const uint8_t *) pi - 0x80) *(1.0f/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_U8, uint8_t,(*(const uint8_t *) pi - 0x80) *(1.0/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S16, int16_t,(*(const int16_t *) pi >> 8)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S16, int16_t, *(const int16_t *) pi *(1.0f/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S16, int16_t, *(const int16_t *) pi *(1.0/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S32, int32_t,(*(const int32_t *) pi >> 24)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S32, int32_t, *(const int32_t *) pi *(1.0f/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S32, int32_t, *(const int32_t *) pi *(1.0/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_FLT, float, av_clip_uint8(lrintf(*(const float *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_FLT, float, av_clip_int16(lrintf(*(const float *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_FLT, float, av_clipl_int32(llrintf(*(const float *) pi *(1U<< 31)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_DBL, double, av_clip_uint8(lrint(*(const double *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_DBL, double, av_clip_int16(lrint(*(const double *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_DBL, double, av_clipl_int32(llrint(*(const double *) pi *(1U<< 31)))) #define SET_CONV_FUNC_GROUP(ofmt, ifmt) static void set_generic_function(AudioConvert *ac) { } void ff_audio_convert_free(AudioConvert **ac) { if(! *ac) return;ff_dither_free(&(*ac) ->dc);av_freep(ac);} AudioConvert *ff_audio_convert_alloc(AVAudioResampleContext *avr, enum AVSampleFormat out_fmt, enum AVSampleFormat in_fmt, int channels, int sample_rate, int apply_map) { AudioConvert *ac;int in_planar, out_planar;ac=av_mallocz(sizeof(*ac));if(!ac) return NULL;ac->avr=avr;ac->out_fmt=out_fmt;ac->in_fmt=in_fmt;ac->channels=channels;ac->apply_map=apply_map;if(avr->dither_method !=AV_RESAMPLE_DITHER_NONE &&av_get_packed_sample_fmt(out_fmt)==AV_SAMPLE_FMT_S16 &&av_get_bytes_per_sample(in_fmt) > 2) { ac->dc=ff_dither_alloc(avr, out_fmt, in_fmt, channels, sample_rate, apply_map);if(!ac->dc) { av_free(ac);return NULL;} return ac;} in_planar=ff_sample_fmt_is_planar(in_fmt, channels);out_planar=ff_sample_fmt_is_planar(out_fmt, channels);if(in_planar==out_planar) { ac->func_type=CONV_FUNC_TYPE_FLAT;ac->planes=in_planar ? ac->channels :1;} else if(in_planar) ac->func_type=CONV_FUNC_TYPE_INTERLEAVE;else ac->func_type=CONV_FUNC_TYPE_DEINTERLEAVE;set_generic_function(ac);if(ARCH_AARCH64) ff_audio_convert_init_aarch64(ac);if(ARCH_ARM) ff_audio_convert_init_arm(ac);if(ARCH_X86) ff_audio_convert_init_x86(ac);return ac;} int ff_audio_convert(AudioConvert *ac, AudioData *out, AudioData *in) { int use_generic=1;int len=in->nb_samples;int p;if(ac->dc) { av_log(ac->avr, AV_LOG_TRACE, "%d samples - audio_convert: %s to %s (dithered)\n", len, av_get_sample_fmt_name(ac->in_fmt), av_get_sample_fmt_name(ac->out_fmt));return ff_convert_dither(ac-> in
int ff_filter_frame(AVFilterLink *link, AVFrame *frame)
Send a frame of data to the next filter.
Definition: avfilter.c:1096
Main libavfilter public API header.
Buffered I/O operations.
#define flags(name, subs,...)
Definition: cbs_av1.c:572
#define NULL
Definition: coverity.c:32
void ff_dnn_uninit(DnnContext *ctx)
DNNReturnType ff_dnn_execute_model(DnnContext *ctx, AVFrame *in_frame, AVFrame *out_frame)
int ff_dnn_init(DnnContext *ctx, DNNFunctionType func_type, AVFilterContext *filter_ctx)
common functions for the dnn based filters
DNNReturnType
Definition: dnn_interface.h:33
@ DNN_SUCCESS
Definition: dnn_interface.h:33
@ DFT_PROCESS_FRAME
Definition: dnn_interface.h:53
int ff_set_common_formats(AVFilterContext *ctx, AVFilterFormats *formats)
A helper for query_formats() which sets all links to the same list of formats.
Definition: formats.c:587
AVFilterFormats * ff_make_format_list(const int *fmts)
Create a list of supported formats.
Definition: formats.c:286
@ AV_OPT_TYPE_CONST
Definition: opt.h:234
@ AV_OPT_TYPE_INT
Definition: opt.h:225
@ AV_OPT_TYPE_STRING
Definition: opt.h:229
#define AVFILTER_FLAG_SUPPORT_TIMELINE_GENERIC
Some filters support a generic "enable" expression option that can be used to enable or disable a fil...
Definition: avfilter.h:126
#define AVERROR(e)
Definition: error.h:43
void av_frame_free(AVFrame **frame)
Free the frame and any dynamically allocated objects in it, e.g.
Definition: frame.c:203
int av_frame_copy_props(AVFrame *dst, const AVFrame *src)
Copy only "metadata" fields from src to dst.
Definition: frame.c:658
#define AV_LOG_ERROR
Something went wrong and cannot losslessly be recovered.
Definition: log.h:194
@ AVMEDIA_TYPE_VIDEO
Definition: avutil.h:201
common internal API header
#define NULL_IF_CONFIG_SMALL(x)
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification.
Definition: internal.h:117
AVOptions.
AVPixelFormat
Pixel format.
Definition: pixfmt.h:64
@ AV_PIX_FMT_NONE
Definition: pixfmt.h:65
@ AV_PIX_FMT_RGB24
packed RGB 8:8:8, 24bpp, RGBRGB...
Definition: pixfmt.h:68
formats
Definition: signature.h:48
Describe the class of an AVClass context structure.
Definition: log.h:67
An instance of a filter.
Definition: avfilter.h:341
A list of supported formats for one end of a filter link.
Definition: formats.h:65
A filter pad used for either input or output.
Definition: internal.h:54
const char * name
Pad name.
Definition: internal.h:60
Filter definition.
Definition: avfilter.h:145
const char * name
Filter name.
Definition: avfilter.h:149
This structure describes decoded (raw) audio or video data.
Definition: frame.h:318
AVOption.
Definition: opt.h:248
int filter_type
Definition: vf_derain.c:37
DnnContext dnnctx
Definition: vf_derain.c:36
#define av_log(a,...)
FILE * out
Definition: movenc.c:54
AVFormatContext * ctx
Definition: movenc.c:48
static const AVFilterPad derain_outputs[]
Definition: vf_derain.c:121
static int query_formats(AVFilterContext *ctx)
Definition: vf_derain.c:59
#define FLAGS
Definition: vf_derain.c:41
static int filter_frame(AVFilterLink *inlink, AVFrame *in)
Definition: vf_derain.c:72
AVFILTER_DEFINE_CLASS(derain)
static av_cold int init(AVFilterContext *ctx)
Definition: vf_derain.c:100
AVFilter ff_vf_derain
Definition: vf_derain.c:129
static av_cold void uninit(AVFilterContext *ctx)
Definition: vf_derain.c:106
#define OFFSET(x)
Definition: vf_derain.c:40
static const AVFilterPad derain_inputs[]
Definition: vf_derain.c:112
static const AVOption derain_options[]
Definition: vf_derain.c:42
AVFrame * ff_get_video_buffer(AVFilterLink *link, int w, int h)
Request a picture buffer with a specific set of permissions.
Definition: video.c:104