mirror of https://git.ffmpeg.org/ffmpeg.git
libavcodec/zmbvenc: motion estimation improvements/bug fixes:
- Clamp ME range to -64..63 (prevents corruption when me_range is too high) - Allow MV's up to *and including* the positive range limit - Allow out-of-edge ME by padding the prev buffer with a border of 0's - Try previous MV before checking the rest (improves speed in some cases) - More robust logic in code - ensure *mx,*my,*xored are updated together
This commit is contained in:
parent
2d80b56ce0
commit
f2e89fe4d3
|
@ -45,11 +45,11 @@
|
||||||
typedef struct ZmbvEncContext {
|
typedef struct ZmbvEncContext {
|
||||||
AVCodecContext *avctx;
|
AVCodecContext *avctx;
|
||||||
|
|
||||||
int range;
|
int lrange, urange;
|
||||||
uint8_t *comp_buf, *work_buf;
|
uint8_t *comp_buf, *work_buf;
|
||||||
uint8_t pal[768];
|
uint8_t pal[768];
|
||||||
uint32_t pal2[256]; //for quick comparisons
|
uint32_t pal2[256]; //for quick comparisons
|
||||||
uint8_t *prev;
|
uint8_t *prev, *prev_buf;
|
||||||
int pstride;
|
int pstride;
|
||||||
int comp_size;
|
int comp_size;
|
||||||
int keyint, curfrm;
|
int keyint, curfrm;
|
||||||
|
@ -61,7 +61,6 @@ typedef struct ZmbvEncContext {
|
||||||
|
|
||||||
/** Block comparing function
|
/** Block comparing function
|
||||||
* XXX should be optimized and moved to DSPContext
|
* XXX should be optimized and moved to DSPContext
|
||||||
* TODO handle out of edge ME
|
|
||||||
*/
|
*/
|
||||||
static inline int block_cmp(ZmbvEncContext *c, uint8_t *src, int stride,
|
static inline int block_cmp(ZmbvEncContext *c, uint8_t *src, int stride,
|
||||||
uint8_t *src2, int stride2, int bw, int bh,
|
uint8_t *src2, int stride2, int bw, int bh,
|
||||||
|
@ -100,23 +99,42 @@ static inline int block_cmp(ZmbvEncContext *c, uint8_t *src, int stride,
|
||||||
static int zmbv_me(ZmbvEncContext *c, uint8_t *src, int sstride, uint8_t *prev,
|
static int zmbv_me(ZmbvEncContext *c, uint8_t *src, int sstride, uint8_t *prev,
|
||||||
int pstride, int x, int y, int *mx, int *my, int *xored)
|
int pstride, int x, int y, int *mx, int *my, int *xored)
|
||||||
{
|
{
|
||||||
int dx, dy, tx, ty, tv, bv, bw, bh;
|
int dx, dy, txored, tv, bv, bw, bh;
|
||||||
|
int mx0, my0;
|
||||||
|
|
||||||
*mx = *my = 0;
|
mx0 = *mx;
|
||||||
|
my0 = *my;
|
||||||
bw = FFMIN(ZMBV_BLOCK, c->avctx->width - x);
|
bw = FFMIN(ZMBV_BLOCK, c->avctx->width - x);
|
||||||
bh = FFMIN(ZMBV_BLOCK, c->avctx->height - y);
|
bh = FFMIN(ZMBV_BLOCK, c->avctx->height - y);
|
||||||
|
|
||||||
|
/* Try (0,0) */
|
||||||
bv = block_cmp(c, src, sstride, prev, pstride, bw, bh, xored);
|
bv = block_cmp(c, src, sstride, prev, pstride, bw, bh, xored);
|
||||||
|
*mx = *my = 0;
|
||||||
if(!bv) return 0;
|
if(!bv) return 0;
|
||||||
for(ty = FFMAX(y - c->range, 0); ty < FFMIN(y + c->range, c->avctx->height - bh); ty++){
|
|
||||||
for(tx = FFMAX(x - c->range, 0); tx < FFMIN(x + c->range, c->avctx->width - bw); tx++){
|
/* Try previous block's MV (if not 0,0) */
|
||||||
if(tx == x && ty == y) continue; // we already tested this block
|
if (mx0 || my0){
|
||||||
dx = tx - x;
|
tv = block_cmp(c, src, sstride, prev + mx0 + my0 * pstride, pstride, bw, bh, &txored);
|
||||||
dy = ty - y;
|
if(tv < bv){
|
||||||
tv = block_cmp(c, src, sstride, prev + dx + dy * pstride, pstride, bw, bh, xored);
|
bv = tv;
|
||||||
|
*mx = mx0;
|
||||||
|
*my = my0;
|
||||||
|
*xored = txored;
|
||||||
|
if(!bv) return 0;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Try other MVs from top-to-bottom, left-to-right */
|
||||||
|
for(dy = -c->lrange; dy <= c->urange; dy++){
|
||||||
|
for(dx = -c->lrange; dx <= c->urange; dx++){
|
||||||
|
if(!dx && !dy) continue; // we already tested this block
|
||||||
|
if(dx == mx0 && dy == my0) continue; // this one too
|
||||||
|
tv = block_cmp(c, src, sstride, prev + dx + dy * pstride, pstride, bw, bh, &txored);
|
||||||
if(tv < bv){
|
if(tv < bv){
|
||||||
bv = tv;
|
bv = tv;
|
||||||
*mx = dx;
|
*mx = dx;
|
||||||
*my = dy;
|
*my = dy;
|
||||||
|
*xored = txored;
|
||||||
if(!bv) return 0;
|
if(!bv) return 0;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
@ -181,7 +199,7 @@ FF_ENABLE_DEPRECATION_WARNINGS
|
||||||
int x, y, bh2, bw2, xored;
|
int x, y, bh2, bw2, xored;
|
||||||
uint8_t *tsrc, *tprev;
|
uint8_t *tsrc, *tprev;
|
||||||
uint8_t *mv;
|
uint8_t *mv;
|
||||||
int mx, my;
|
int mx = 0, my = 0;
|
||||||
|
|
||||||
bw = (avctx->width + ZMBV_BLOCK - 1) / ZMBV_BLOCK;
|
bw = (avctx->width + ZMBV_BLOCK - 1) / ZMBV_BLOCK;
|
||||||
bh = (avctx->height + ZMBV_BLOCK - 1) / ZMBV_BLOCK;
|
bh = (avctx->height + ZMBV_BLOCK - 1) / ZMBV_BLOCK;
|
||||||
|
@ -269,7 +287,7 @@ static av_cold int encode_end(AVCodecContext *avctx)
|
||||||
av_freep(&c->work_buf);
|
av_freep(&c->work_buf);
|
||||||
|
|
||||||
deflateEnd(&c->zstream);
|
deflateEnd(&c->zstream);
|
||||||
av_freep(&c->prev);
|
av_freep(&c->prev_buf);
|
||||||
|
|
||||||
return 0;
|
return 0;
|
||||||
}
|
}
|
||||||
|
@ -283,6 +301,7 @@ static av_cold int encode_init(AVCodecContext *avctx)
|
||||||
int zret; // Zlib return code
|
int zret; // Zlib return code
|
||||||
int i;
|
int i;
|
||||||
int lvl = 9;
|
int lvl = 9;
|
||||||
|
int prev_size, prev_offset;
|
||||||
|
|
||||||
/* Entropy-based score tables for comparing blocks.
|
/* Entropy-based score tables for comparing blocks.
|
||||||
* Suitable for blocks up to (ZMBV_BLOCK * ZMBV_BLOCK) bytes.
|
* Suitable for blocks up to (ZMBV_BLOCK * ZMBV_BLOCK) bytes.
|
||||||
|
@ -295,9 +314,13 @@ static av_cold int encode_init(AVCodecContext *avctx)
|
||||||
|
|
||||||
c->curfrm = 0;
|
c->curfrm = 0;
|
||||||
c->keyint = avctx->keyint_min;
|
c->keyint = avctx->keyint_min;
|
||||||
c->range = 8;
|
|
||||||
if(avctx->me_range > 0)
|
/* Motion estimation range: maximum distance is -64..63 */
|
||||||
c->range = FFMIN(avctx->me_range, 127);
|
c->lrange = c->urange = 8;
|
||||||
|
if(avctx->me_range > 0){
|
||||||
|
c->lrange = FFMIN(avctx->me_range, 64);
|
||||||
|
c->urange = FFMIN(avctx->me_range, 63);
|
||||||
|
}
|
||||||
|
|
||||||
if(avctx->compression_level >= 0)
|
if(avctx->compression_level >= 0)
|
||||||
lvl = avctx->compression_level;
|
lvl = avctx->compression_level;
|
||||||
|
@ -323,11 +346,23 @@ static av_cold int encode_init(AVCodecContext *avctx)
|
||||||
av_log(avctx, AV_LOG_ERROR, "Can't allocate compression buffer.\n");
|
av_log(avctx, AV_LOG_ERROR, "Can't allocate compression buffer.\n");
|
||||||
return AVERROR(ENOMEM);
|
return AVERROR(ENOMEM);
|
||||||
}
|
}
|
||||||
c->pstride = FFALIGN(avctx->width, 16);
|
|
||||||
if (!(c->prev = av_malloc(c->pstride * avctx->height))) {
|
/* Allocate prev buffer - pad around the image to allow out-of-edge ME:
|
||||||
|
* - The image should be padded with `lrange` rows before and `urange` rows
|
||||||
|
* after.
|
||||||
|
* - The stride should be padded with `lrange` pixels, then rounded up to a
|
||||||
|
* multiple of 16 bytes.
|
||||||
|
* - The first row should also be padded with `lrange` pixels before, then
|
||||||
|
* aligned up to a multiple of 16 bytes.
|
||||||
|
*/
|
||||||
|
c->pstride = FFALIGN(avctx->width + c->lrange, 16);
|
||||||
|
prev_size = FFALIGN(c->lrange, 16) + c->pstride * (c->lrange + avctx->height + c->urange);
|
||||||
|
prev_offset = FFALIGN(c->lrange, 16) + c->pstride * c->lrange;
|
||||||
|
if (!(c->prev_buf = av_mallocz(prev_size))) {
|
||||||
av_log(avctx, AV_LOG_ERROR, "Can't allocate picture.\n");
|
av_log(avctx, AV_LOG_ERROR, "Can't allocate picture.\n");
|
||||||
return AVERROR(ENOMEM);
|
return AVERROR(ENOMEM);
|
||||||
}
|
}
|
||||||
|
c->prev = c->prev_buf + prev_offset;
|
||||||
|
|
||||||
c->zstream.zalloc = Z_NULL;
|
c->zstream.zalloc = Z_NULL;
|
||||||
c->zstream.zfree = Z_NULL;
|
c->zstream.zfree = Z_NULL;
|
||||||
|
|
Loading…
Reference in New Issue