-
Ronald S. Bultje authored
This patch introduces the concept of dual inter16x16 prediction. A 16x16 inter-predicted macroblock can use 2 references instead of 1, where both references use the same mvmode (new, near/est, zero). In the case of newmv, this means that two MVs are coded instead of one. The frame can be encoded in 3 ways: all MBs single-prediction, all MBs dual prediction, or per-MB single/dual prediction selection ("hybrid"), in which case a single bit is coded per-MB to indicate whether the MB uses single or dual inter prediction. In the future, we can (maybe?) get further gains by mixing this with Adrian's 32x32 work, per-segment dual prediction settings, or adding support for dual splitmv/8x8mv inter prediction. Gain (on derf-set, CQ mode) is ~2.8% (SSIM) or ~3.6% (glb PSNR). Most gain is at medium/high bitrates, but there's minor gains at low bitrates also. Output was confirmed to match between encoder and decoder. Note for optimization people: this patch introduces a 2nd version of 16x16/8x8 sixtap/bilin functions, which does an avg instead of a store. They may want to look and make sure this is implemented to their satisfaction so we can optimize it best in the future. Change-ID: I59dc84b07cbb3ccf073ac0f756d03d294cb1928160cb39da
/* * Copyright (c) 2010 The WebM project authors. All Rights Reserved. * * Use of this source code is governed by a BSD-style license * that can be found in the LICENSE file in the root of the source * tree. An additional intellectual property rights grant can be found * in the file PATENTS. All contributing project authors may * be found in the AUTHORS file in the root of the source tree. */#ifndef SUBPIXEL_H#define SUBPIXEL_H#define prototype_subpixel_predict(sym) \ void sym(unsigned char *src, int src_pitch, int xofst, int yofst, \ unsigned char *dst, int dst_pitch)#if ARCH_X86 || ARCH_X86_64#include "x86/subpixel_x86.h"#endif#if ARCH_ARM#include "arm/subpixel_arm.h"#endif#ifndef vp8_subpix_sixtap16x16#define vp8_subpix_sixtap16x16 vp8_sixtap_predict16x16_c#endifextern prototype_subpixel_predict(vp8_subpix_sixtap16x16);#ifndef vp8_subpix_sixtap8x8#define vp8_subpix_sixtap8x8 vp8_sixtap_predict8x8_c#endifextern prototype_subpixel_predict(vp8_subpix_sixtap8x8);#if CONFIG_DUALPRED#ifndef vp8_subpix_sixtap_avg16x16#define vp8_subpix_sixtap_avg16x16 vp8_sixtap_predict_avg16x16_c#endifextern prototype_subpixel_predict(vp8_subpix_sixtap_avg16x16);#ifndef vp8_subpix_sixtap_avg8x8#define vp8_subpix_sixtap_avg8x8 vp8_sixtap_predict_avg8x8_c#endifextern prototype_subpixel_predict(vp8_subpix_sixtap_avg8x8);#endif /* CONFIG_DUALPRED */#ifndef vp8_subpix_sixtap8x4#define vp8_subpix_sixtap8x4 vp8_sixtap_predict8x4_c#endifextern prototype_subpixel_predict(vp8_subpix_sixtap8x4);#ifndef vp8_subpix_sixtap4x4#define vp8_subpix_sixtap4x4 vp8_sixtap_predict_c#endifextern prototype_subpixel_predict(vp8_subpix_sixtap4x4);#ifndef vp8_subpix_bilinear16x16#define vp8_subpix_bilinear16x16 vp8_bilinear_predict16x16_c#endifextern prototype_subpixel_predict(vp8_subpix_bilinear16x16);#ifndef vp8_subpix_bilinear8x8#define vp8_subpix_bilinear8x8 vp8_bilinear_predict8x8_c#endifextern prototype_subpixel_predict(vp8_subpix_bilinear8x8);#if CONFIG_DUALPRED#ifndef vp8_subpix_bilinear_avg16x167172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119
#define vp8_subpix_bilinear_avg16x16 vp8_bilinear_predict_avg16x16_c
#endif
extern prototype_subpixel_predict(vp8_subpix_bilinear_avg16x16);
#ifndef vp8_subpix_bilinear_avg8x8
#define vp8_subpix_bilinear_avg8x8 vp8_bilinear_predict_avg8x8_c
#endif
extern prototype_subpixel_predict(vp8_subpix_bilinear_avg8x8);
#endif /* CONFIG_DUALPRED */
#ifndef vp8_subpix_bilinear8x4
#define vp8_subpix_bilinear8x4 vp8_bilinear_predict8x4_c
#endif
extern prototype_subpixel_predict(vp8_subpix_bilinear8x4);
#ifndef vp8_subpix_bilinear4x4
#define vp8_subpix_bilinear4x4 vp8_bilinear_predict4x4_c
#endif
extern prototype_subpixel_predict(vp8_subpix_bilinear4x4);
typedef prototype_subpixel_predict((*vp8_subpix_fn_t));
typedef struct
{
vp8_subpix_fn_t sixtap16x16;
vp8_subpix_fn_t sixtap8x8;
#if CONFIG_DUALPRED
vp8_subpix_fn_t sixtap_avg16x16;
vp8_subpix_fn_t sixtap_avg8x8;
#endif /* CONFIG_DUALPRED */
vp8_subpix_fn_t sixtap8x4;
vp8_subpix_fn_t sixtap4x4;
vp8_subpix_fn_t bilinear16x16;
vp8_subpix_fn_t bilinear8x8;
#if CONFIG_DUALPRED
vp8_subpix_fn_t bilinear_avg16x16;
vp8_subpix_fn_t bilinear_avg8x8;
#endif /* CONFIG_DUALPRED */
vp8_subpix_fn_t bilinear8x4;
vp8_subpix_fn_t bilinear4x4;
} vp8_subpix_rtcd_vtable_t;
#if CONFIG_RUNTIME_CPU_DETECT
#define SUBPIX_INVOKE(ctx,fn) (ctx)->fn
#else
#define SUBPIX_INVOKE(ctx,fn) vp8_subpix_##fn
#endif
#endif