Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (6): 1941-1949.DOI: 10.11772/j.issn.1001-9081.2021040594
• Multimedia computing and computer simulation • Previous Articles Next Articles
Yingying ZHANG1, Chao REN2, Ce ZHU1()
Received:
2021-04-15
Revised:
2021-05-27
Accepted:
2021-05-27
Online:
2022-06-22
Published:
2022-06-10
Contact:
Ce ZHU
About author:
ZHANG Yingying,born in 1989,Ph. D. candidate. Her research interests include image super-resolution.Supported by:
通讯作者:
朱策
作者简介:
张莹莹(1989—),女,山东泰安人,博士研究生,主要研究方向:图像超分辨率基金资助:
CLC Number:
Yingying ZHANG, Chao REN, Ce ZHU. Depth image super-resolution based on shape-adaptive non-local regression and non-local gradient regularization[J]. Journal of Computer Applications, 2022, 42(6): 1941-1949.
张莹莹, 任超, 朱策. 基于形状自适应非局部回归和非局部梯度正则的深度图像超分辨[J]. 《计算机应用》唯一官方网站, 2022, 42(6): 1941-1949.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2021040594
方法 | Art | Book | Moebius | 平均值 | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
2× | 4× | 8× | 2× | 4× | 8× | 2× | 4× | 8× | 2× | 4× | 8× | |
MRF[ | 2.607 9 | 3.123 4 | 4.808 6 | 0.480 2 | 0.683 0 | 1.067 2 | 0.572 0 | 0.742 8 | 1.151 5 | 1.220 0 | 1.516 4 | 2.342 4 |
GF[ | 2.022 5 | 2.869 1 | 4.546 1 | 0.469 6 | 0.714 9 | 1.495 7 | 0.489 0 | 0.761 8 | 1.419 3 | 0.993 7 | 1.448 6 | 2.487 0 |
MSJF[ | 2.826 2 | 3.163 2 | 4.916 6 | 0.592 5 | 0.680 5 | 1.206 1 | 0.667 7 | 0.785 1 | 1.242 4 | 1.362 1 | 1.542 9 | 2.455 0 |
SDF[ | 2.316 9 | 2.667 9 | 3.337 7 | 0.462 3 | 0.582 0 | 0.612 6 | 0.577 1 | 0.686 6 | 0.904 2 | 1.118 8 | 1.312 2 | 1.618 2 |
AR[ | 2.706 8 | 2.805 0 | 3.531 9 | 0.616 3 | 0.805 5 | 1.224 2 | 0.662 8 | 0.738 5 | 0.845 0 | 1.328 6 | 1.449 7 | 1.867 0 |
TGV[ | 2.597 4 | 3.001 4 | 6.505 6 | 0.439 0 | 0.636 7 | 1.373 7 | 0.536 3 | 0.706 3 | 1.290 3 | 1.190 9 | 1.448 1 | 3.056 5 |
EIEM[ | 1.453 5 | 2.261 1 | 4.148 9 | 0.323 0 | 0.513 2 | 0.798 0 | 0.419 1 | 0.607 5 | 0.951 6 | 0.731 9 | 1.127 3 | 1.966 2 |
本文算法 | 0.900 5 | 1.333 1 | 2.442 1 | 0.188 5 | 0.335 6 | 0.791 6 | 0.227 5 | 0.365 2 | 0.720 6 | 0.438 8 | 0.678 0 | 1.318 1 |
Tab. 1 Comparison of MAD on dataset A
方法 | Art | Book | Moebius | 平均值 | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
2× | 4× | 8× | 2× | 4× | 8× | 2× | 4× | 8× | 2× | 4× | 8× | |
MRF[ | 2.607 9 | 3.123 4 | 4.808 6 | 0.480 2 | 0.683 0 | 1.067 2 | 0.572 0 | 0.742 8 | 1.151 5 | 1.220 0 | 1.516 4 | 2.342 4 |
GF[ | 2.022 5 | 2.869 1 | 4.546 1 | 0.469 6 | 0.714 9 | 1.495 7 | 0.489 0 | 0.761 8 | 1.419 3 | 0.993 7 | 1.448 6 | 2.487 0 |
MSJF[ | 2.826 2 | 3.163 2 | 4.916 6 | 0.592 5 | 0.680 5 | 1.206 1 | 0.667 7 | 0.785 1 | 1.242 4 | 1.362 1 | 1.542 9 | 2.455 0 |
SDF[ | 2.316 9 | 2.667 9 | 3.337 7 | 0.462 3 | 0.582 0 | 0.612 6 | 0.577 1 | 0.686 6 | 0.904 2 | 1.118 8 | 1.312 2 | 1.618 2 |
AR[ | 2.706 8 | 2.805 0 | 3.531 9 | 0.616 3 | 0.805 5 | 1.224 2 | 0.662 8 | 0.738 5 | 0.845 0 | 1.328 6 | 1.449 7 | 1.867 0 |
TGV[ | 2.597 4 | 3.001 4 | 6.505 6 | 0.439 0 | 0.636 7 | 1.373 7 | 0.536 3 | 0.706 3 | 1.290 3 | 1.190 9 | 1.448 1 | 3.056 5 |
EIEM[ | 1.453 5 | 2.261 1 | 4.148 9 | 0.323 0 | 0.513 2 | 0.798 0 | 0.419 1 | 0.607 5 | 0.951 6 | 0.731 9 | 1.127 3 | 1.966 2 |
本文算法 | 0.900 5 | 1.333 1 | 2.442 1 | 0.188 5 | 0.335 6 | 0.791 6 | 0.227 5 | 0.365 2 | 0.720 6 | 0.438 8 | 0.678 0 | 1.318 1 |
方法 | Laundry | Reindeer | Dolls | 平均值 | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
2× | 4× | 8× | 2× | 4× | 8× | 2× | 4× | 8× | 2× | 4× | 8× | |
MRF[ | 1.358 5 | 1.575 4 | 2.324 8 | 2.354 4 | 2.657 6 | 3.780 8 | 0.360 9 | 0.511 3 | 0.939 7 | 1.357 8 | 1.581 4 | 2.348 4 |
GF[ | 1.122 3 | 1.504 8 | 2.268 6 | 2.122 2 | 2.902 9 | 4.392 5 | 0.375 4 | 0.555 3 | 0.973 1 | 1.206 6 | 1.654 3 | 2.544 7 |
MSJF[ | 1.508 4 | 1.765 6 | 3.135 9 | 2.698 3 | 3.072 6 | 5.066 3 | 0.405 6 | 0.448 8 | 0.685 0 | 1.537 4 | 1.762 3 | 2.962 4 |
SDF[ | 1.260 9 | 1.396 2 | 2.087 8 | 2.164 7 | 2.284 9 | 2.444 7 | 0.378 2 | 0.554 0 | 0.942 2 | 1.267 9 | 1.411 7 | 1.824 9 |
AR[ | 1.397 0 | 1.560 6 | 2.524 7 | 2.510 2 | 2.711 1 | 3.324 9 | 0.436 3 | 0.518 8 | 0.716 4 | 1.447 8 | 1.596 8 | 2.188 7 |
TGV[ | 1.292 3 | 1.820 6 | 3.148 9 | 2.336 6 | 2.921 0 | 5.212 9 | 0.331 0 | 0.487 4 | 1.049 5 | 1.320 0 | 1.743 0 | 3.137 1 |
EIEM[ | 0.870 8 | 1.457 1 | 2.443 2 | 1.470 0 | 2.227 8 | 3.588 2 | 0.290 0 | 0.452 7 | 0.805 5 | 0.876 9 | 1.379 2 | 2.279 0 |
本文算法 | 0.554 7 | 0.958 8 | 2.084 4 | 0.768 1 | 1.182 4 | 2.531 1 | 0.204 9 | 0.277 2 | 0.569 9 | 0.509 2 | 0.806 1 | 1.728 5 |
Tab. 2 Comparison of MAD on dataset B
方法 | Laundry | Reindeer | Dolls | 平均值 | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
2× | 4× | 8× | 2× | 4× | 8× | 2× | 4× | 8× | 2× | 4× | 8× | |
MRF[ | 1.358 5 | 1.575 4 | 2.324 8 | 2.354 4 | 2.657 6 | 3.780 8 | 0.360 9 | 0.511 3 | 0.939 7 | 1.357 8 | 1.581 4 | 2.348 4 |
GF[ | 1.122 3 | 1.504 8 | 2.268 6 | 2.122 2 | 2.902 9 | 4.392 5 | 0.375 4 | 0.555 3 | 0.973 1 | 1.206 6 | 1.654 3 | 2.544 7 |
MSJF[ | 1.508 4 | 1.765 6 | 3.135 9 | 2.698 3 | 3.072 6 | 5.066 3 | 0.405 6 | 0.448 8 | 0.685 0 | 1.537 4 | 1.762 3 | 2.962 4 |
SDF[ | 1.260 9 | 1.396 2 | 2.087 8 | 2.164 7 | 2.284 9 | 2.444 7 | 0.378 2 | 0.554 0 | 0.942 2 | 1.267 9 | 1.411 7 | 1.824 9 |
AR[ | 1.397 0 | 1.560 6 | 2.524 7 | 2.510 2 | 2.711 1 | 3.324 9 | 0.436 3 | 0.518 8 | 0.716 4 | 1.447 8 | 1.596 8 | 2.188 7 |
TGV[ | 1.292 3 | 1.820 6 | 3.148 9 | 2.336 6 | 2.921 0 | 5.212 9 | 0.331 0 | 0.487 4 | 1.049 5 | 1.320 0 | 1.743 0 | 3.137 1 |
EIEM[ | 0.870 8 | 1.457 1 | 2.443 2 | 1.470 0 | 2.227 8 | 3.588 2 | 0.290 0 | 0.452 7 | 0.805 5 | 0.876 9 | 1.379 2 | 2.279 0 |
本文算法 | 0.554 7 | 0.958 8 | 2.084 4 | 0.768 1 | 1.182 4 | 2.531 1 | 0.204 9 | 0.277 2 | 0.569 9 | 0.509 2 | 0.806 1 | 1.728 5 |
方法 | Art | Book | Moebius | 平均值 | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
2× | 4× | 8× | 2× | 4× | 8× | 2× | 4× | 8× | 2× | 4× | 8× | |
MRF[ | 4.166 0 | 6.069 8 | 6.976 3 | 1.722 5 | 2.232 8 | 2.600 9 | 1.790 3 | 2.327 4 | 2.731 1 | 2.559 6 | 3.543 3 | 4.102 8 |
GF[ | 3.219 3 | 3.948 7 | 5.559 3 | 2.380 2 | 2.515 5 | 3.100 4 | 2.466 7 | 2.615 7 | 3.052 2 | 2.688 7 | 3.026 6 | 3.904 0 |
MSJF[ | 3.571 7 | 4.522 0 | 6.066 8 | 1.650 2 | 2.022 8 | 3.841 2 | 1.607 3 | 2.039 2 | 3.805 5 | 2.276 4 | 2.861 3 | 4.571 2 |
SDF[ | 3.256 9 | 3.557 60 | 4.534 1 | 1.056 4 | 1.509 8 | 1.626 0 | 1.299 3 | 1.654 4 | 1.895 9 | 1.870 9 | 2.240 6 | 2.685 3 |
AR[ | 3.705 2 | 3.779 0 | 4.886 1 | 1.864 8 | 2.043 1 | 2.639 5 | 1.822 7 | 2.075 0 | 2.441 2 | 2.464 2 | 2.632 4 | 3.322 3 |
TGV[ | 3.478 0 | 4.418 8 | 6.110 0 | 1.026 7 | 2.006 7 | 3.270 0 | 1.142 1 | 2.191 7 | 3.820 6 | 1.882 3 | 2.872 4 | 4.400 2 |
EIEM[ | 2.370 9 | 3.895 0 | 5.497 0 | 1.045 6 | 1.110 0 | 1.859 8 | 1.158 7 | 1.338 8 | 2.286 6 | 1.525 1 | 2.114 6 | 3.214 5 |
本文算法 | 2.123 2 | 2.812 0 | 4.005 5 | 1.014 9 | 1.446 2 | 2.016 0 | 1.114 3 | 1.561 5 | 2.131 2 | 1.417 5 | 1.939 9 | 2.717 6 |
Tab. 3 Comparison of MAD on dataset A with TOF-like degradation
方法 | Art | Book | Moebius | 平均值 | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
2× | 4× | 8× | 2× | 4× | 8× | 2× | 4× | 8× | 2× | 4× | 8× | |
MRF[ | 4.166 0 | 6.069 8 | 6.976 3 | 1.722 5 | 2.232 8 | 2.600 9 | 1.790 3 | 2.327 4 | 2.731 1 | 2.559 6 | 3.543 3 | 4.102 8 |
GF[ | 3.219 3 | 3.948 7 | 5.559 3 | 2.380 2 | 2.515 5 | 3.100 4 | 2.466 7 | 2.615 7 | 3.052 2 | 2.688 7 | 3.026 6 | 3.904 0 |
MSJF[ | 3.571 7 | 4.522 0 | 6.066 8 | 1.650 2 | 2.022 8 | 3.841 2 | 1.607 3 | 2.039 2 | 3.805 5 | 2.276 4 | 2.861 3 | 4.571 2 |
SDF[ | 3.256 9 | 3.557 60 | 4.534 1 | 1.056 4 | 1.509 8 | 1.626 0 | 1.299 3 | 1.654 4 | 1.895 9 | 1.870 9 | 2.240 6 | 2.685 3 |
AR[ | 3.705 2 | 3.779 0 | 4.886 1 | 1.864 8 | 2.043 1 | 2.639 5 | 1.822 7 | 2.075 0 | 2.441 2 | 2.464 2 | 2.632 4 | 3.322 3 |
TGV[ | 3.478 0 | 4.418 8 | 6.110 0 | 1.026 7 | 2.006 7 | 3.270 0 | 1.142 1 | 2.191 7 | 3.820 6 | 1.882 3 | 2.872 4 | 4.400 2 |
EIEM[ | 2.370 9 | 3.895 0 | 5.497 0 | 1.045 6 | 1.110 0 | 1.859 8 | 1.158 7 | 1.338 8 | 2.286 6 | 1.525 1 | 2.114 6 | 3.214 5 |
本文算法 | 2.123 2 | 2.812 0 | 4.005 5 | 1.014 9 | 1.446 2 | 2.016 0 | 1.114 3 | 1.561 5 | 2.131 2 | 1.417 5 | 1.939 9 | 2.717 6 |
方法 | Laundry | Reindeer | Dolls | 平均值 | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
2× | 4× | 8× | 2× | 4× | 8× | 2× | 4× | 8× | 2× | 4× | 8× | |
MRF[ | 3.242 2 | 3.744 8 | 4.311 9 | 4.153 1 | 5.998 4 | 6.513 7 | 1.657 2 | 2.163 8 | 2.489 8 | 3.017 5 | 3.969 0 | 4.438 5 |
GF[ | 2.677 4 | 2.982 3 | 3.689 7 | 3.438 7 | 4.083 5 | 5.305 4 | 2.099 2 | 2.151 1 | 2.608 7 | 2.738 4 | 3.072 3 | 3.867 9 |
MSJF[ | 2.326 2 | 3.127 1 | 4.561 8 | 3.514 1 | 4.278 4 | 6.296 1 | 1.283 6 | 1.842 2 | 2.719 0 | 2.374 6 | 3.082 6 | 4.525 6 |
SDF[ | 1.879 5 | 2.012 9 | 3.093 8 | 2.664 1 | 3.115 1 | 3.443 8 | 1.074 9 | 1.439 2 | 2.026 1 | 1.872 8 | 2.189 1 | 2.854 6 |
AR[ | 2.783 4 | 2.810 2 | 4.305 0 | 3.791 0 | 3.936 8 | 5.719 7 | 1.706 4 | 1.925 3 | 2.382 7 | 2.760 3 | 2.890 8 | 4.135 8 |
TGV[ | 1.808 0 | 2.904 7 | 6.260 3 | 3.095 4 | 3.917 7 | 7.154 7 | 0.930 1 | 1.860 6 | 3.353 7 | 1.944 5 | 2.894 5 | 5.589 6 |
EIEM[ | 2.033 0 | 2.676 8 | 4.495 4 | 3.030 6 | 3.638 5 | 6.051 4 | 1.015 3 | 1.415 8 | 2.111 1 | 2.026 3 | 2.577 0 | 4.219 3 |
本文算法 | 1.618 2 | 1.924 4 | 3.567 4 | 2.113 5 | 2.545 5 | 4.614 3 | 0.912 0 | 1.399 3 | 1.854 5 | 1.547 9 | 1.956 4 | 3.345 4 |
Tab. 4 Comparison of MAD on dataset B with TOF-like degradation
方法 | Laundry | Reindeer | Dolls | 平均值 | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
2× | 4× | 8× | 2× | 4× | 8× | 2× | 4× | 8× | 2× | 4× | 8× | |
MRF[ | 3.242 2 | 3.744 8 | 4.311 9 | 4.153 1 | 5.998 4 | 6.513 7 | 1.657 2 | 2.163 8 | 2.489 8 | 3.017 5 | 3.969 0 | 4.438 5 |
GF[ | 2.677 4 | 2.982 3 | 3.689 7 | 3.438 7 | 4.083 5 | 5.305 4 | 2.099 2 | 2.151 1 | 2.608 7 | 2.738 4 | 3.072 3 | 3.867 9 |
MSJF[ | 2.326 2 | 3.127 1 | 4.561 8 | 3.514 1 | 4.278 4 | 6.296 1 | 1.283 6 | 1.842 2 | 2.719 0 | 2.374 6 | 3.082 6 | 4.525 6 |
SDF[ | 1.879 5 | 2.012 9 | 3.093 8 | 2.664 1 | 3.115 1 | 3.443 8 | 1.074 9 | 1.439 2 | 2.026 1 | 1.872 8 | 2.189 1 | 2.854 6 |
AR[ | 2.783 4 | 2.810 2 | 4.305 0 | 3.791 0 | 3.936 8 | 5.719 7 | 1.706 4 | 1.925 3 | 2.382 7 | 2.760 3 | 2.890 8 | 4.135 8 |
TGV[ | 1.808 0 | 2.904 7 | 6.260 3 | 3.095 4 | 3.917 7 | 7.154 7 | 0.930 1 | 1.860 6 | 3.353 7 | 1.944 5 | 2.894 5 | 5.589 6 |
EIEM[ | 2.033 0 | 2.676 8 | 4.495 4 | 3.030 6 | 3.638 5 | 6.051 4 | 1.015 3 | 1.415 8 | 2.111 1 | 2.026 3 | 2.577 0 | 4.219 3 |
本文算法 | 1.618 2 | 1.924 4 | 3.567 4 | 2.113 5 | 2.545 5 | 4.614 3 | 0.912 0 | 1.399 3 | 1.854 5 | 1.547 9 | 1.956 4 | 3.345 4 |
方法 | Art | Book | Moebius | ||||||
---|---|---|---|---|---|---|---|---|---|
2× | 4× | 8× | 2× | 4× | 8× | 2× | 4× | 8× | |
NLG | t1.017 2 | 1.605 4 | 3.924 2 | 0.235 3 | 0.380 1 | 0.850 7 | 0.298 8 | 0.445 7 | 1.160 7 |
SA-NLR | 0.992 0 | 1.582 9 | 3.166 0 | 0.231 3 | 0.463 9 | 0.988 9 | 0.247 1 | 0.400 5 | 0.770 3 |
本文方法 | 0.900 5 | 1.333 1 | 2.442 1 | 0.188 5 | 0.335 6 | 0.791 6 | 0.227 5 | 0.365 2 | 0.720 6 |
Tab. 5 Effectiveness comparison of regularization terms on dataset A (MAD)
方法 | Art | Book | Moebius | ||||||
---|---|---|---|---|---|---|---|---|---|
2× | 4× | 8× | 2× | 4× | 8× | 2× | 4× | 8× | |
NLG | t1.017 2 | 1.605 4 | 3.924 2 | 0.235 3 | 0.380 1 | 0.850 7 | 0.298 8 | 0.445 7 | 1.160 7 |
SA-NLR | 0.992 0 | 1.582 9 | 3.166 0 | 0.231 3 | 0.463 9 | 0.988 9 | 0.247 1 | 0.400 5 | 0.770 3 |
本文方法 | 0.900 5 | 1.333 1 | 2.442 1 | 0.188 5 | 0.335 6 | 0.791 6 | 0.227 5 | 0.365 2 | 0.720 6 |
方法 | Laundry | Reindeer | Dolls | ||||||
---|---|---|---|---|---|---|---|---|---|
2× | 4× | 8× | 2× | 4× | 8× | 2× | 4× | 8× | |
NLG | 0.775 | 1.190 6 | 2.612 4 | 0.973 1 | 1.767 4 | 3.997 4 | 0.312 7 | 0.487 5 | 0.707 6 |
SA-NLR | 0.561 3 | 1.088 7 | 2.739 9 | 0.802 5 | 1.253 6 | 3.542 7 | 0.213 6 | 0.296 0 | 0.605 7 |
本文方法 | 0.554 7 | 0.958 8 | 2.084 4 | 0.768 1 | 1.182 4 | 2.531 1 | 0.204 9 | 0.277 2 | 0.569 9 |
Tab. 6 Effectiveness comparison of regularization terms on dataset B (MAD)
方法 | Laundry | Reindeer | Dolls | ||||||
---|---|---|---|---|---|---|---|---|---|
2× | 4× | 8× | 2× | 4× | 8× | 2× | 4× | 8× | |
NLG | 0.775 | 1.190 6 | 2.612 4 | 0.973 1 | 1.767 4 | 3.997 4 | 0.312 7 | 0.487 5 | 0.707 6 |
SA-NLR | 0.561 3 | 1.088 7 | 2.739 9 | 0.802 5 | 1.253 6 | 3.542 7 | 0.213 6 | 0.296 0 | 0.605 7 |
本文方法 | 0.554 7 | 0.958 8 | 2.084 4 | 0.768 1 | 1.182 4 | 2.531 1 | 0.204 9 | 0.277 2 | 0.569 9 |
1 | NDJIKI-NYA P, KÖPPEL M, DOSHKOV D, et al. Depth image based rendering with advanced texture synthesis[C]// Proceedings of the 2010 IEEE International Conference on Multimedia and Expo. Piscataway: IEEE, 2010: 424-429. 10.1109/icme.2010.5583559 |
2 | 李知菲,陈源. 基于联合双边滤波器的Kinect深度图像滤波算法[J]. 计算机应用, 2014, 34(8):2231-2234, 2242. 10.11772/j.issn.1001-9081.2014.08.2231 |
LI Z F, CHEN Y. Kinect depth image filtering based on joint bilateral filter[J]. Journal of Computer Applications, 2014, 34(8):2231-2234, 2242. 10.11772/j.issn.1001-9081.2014.08.2231 | |
3 | HE K M, SUN J, TANG X O. Guided image filtering[C]// Proceedings of the 2010 European Conference on Computer Vision, LNIP 6311. Berlin: Springer, 2010: 1-14. |
4 | SHEN X Y, ZHOU C, XU L, et al. Mutual-structure for joint filtering[J]. International Journal of Computer Vision, 2017, 125(1/2/3):19-33. 10.1007/s11263-017-1021-y |
5 | HAM B, CHO M, PONCE J. Robust image filtering using joint static and dynamic guidance[C]// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2015:4823-4831. 10.1109/cvpr.2015.7299115 |
6 | WANG J, XU W, CAI J F, et al. Multi-direction dictionary learning based depth map super-resolution with autoregressive modeling[J]. IEEE Transactions on Multimedia, 2020, 22(6):1470-1484. 10.1109/tmm.2019.2946075 |
7 | KWON H, TAI Y W, LIN S. Data-driven depth map refinement via multi-scale sparse representation[C]// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2015: 159-167. 10.1109/cvpr.2015.7298611 |
8 | ZUO Y F, FANG Y M, AN P, et al. Frequency-dependent depth map enhancement via iterative depth-guided affine transformation and intensity-guided refinement[J]. IEEE Transactions on Multimedia, 2020, 23: 772-783. 10.1109/TMM.2020.2987706 |
9 | ZUO Y F, FANG Y M, YANG Y, et al. Depth map enhancement by revisiting multi-scale intensity guidance within coarse-to-fine stages[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020, 30(12): 4676-4687. 10.1109/tcsvt.2019.2962867 |
10 | DIEBEL J, THRUN S. An application of Markov random fields to range sensing[C]// Proceedings of the 18th International Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2005: 291-298. |
11 | FERSTL D, REINBACHER C, RANFTL R, et al. Image guided depth upsampling using anisotropic total generalized variation[C]// Proceedings of the 2013 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2013: 993-1000. 10.1109/iccv.2013.127 |
12 | YANG J Y, YE X C, LI K, et al. Color-guided depth recovery from RGB-D data using an adaptive autoregressive model[J]. IEEE Transactions on Image Processing, 2014, 23(8):3443-3458. 10.1109/tip.2014.2329776 |
13 | DONG W S, SHI G M, LI X, et al. Color-guided depth recovery via joint local structural and nonlocal low-rank regularization[J]. IEEE Transactions on Multimedia, 2017, 19(2):293-301. 10.1109/tmm.2016.2613824 |
14 | ZHANG Y D, ZHOU Y, WANG A H, et al. Joint nonlocal sparse representation for depth map super-resolution[C]// Proceedings of the 2017 IEEE International Conference on Image Processing. Piscataway: IEEE, 2017: 972-976. 10.1109/icip.2017.8296426 |
15 | JIANG Z Y, HOU Y H, YUE H J, et al. Depth super-resolution from RGB-D pairs with transform and spatial domain regularization[J]. IEEE Transactions on Image Processing, 2018, 27(5): 2587-2602. 10.1109/tip.2018.2806089 |
16 | ZHANG H T, YU J, WANG Z F. Depth map super-resolution using nonlocal higher-order regularization with classified weights[C]// Proceedings of the 2017 IEEE International Conference on Image Processing. Piscataway: IEEE, 2017:4043-4047. 10.1109/icip.2017.8297042 |
17 | PARK J, KIM H, TAI Y W, et al. High quality depth map upsampling for 3D-TOF cameras[C]// Proceedings of the 2011 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2011: 1623-1630. 10.1109/iccv.2011.6126423 |
18 | REN C, HE X H, NGUYE T Q. Adjusted non-local regression and directional smoothness for image restoration[J]. IEEE Transactions on Multimedia, 2019, 21(3):731-745. 10.1109/tmm.2018.2866362 |
19 | LIU H F, XIONG R Q, ZHANG X F, et al. Nonlocal gradient sparsity regularization for image restoration[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2017, 27(9): 1909-1921. 10.1109/tcsvt.2016.2556498 |
20 | KATKOVNIK V, EGIAZARIAN K, ASTOLA J. Adaptive window size image de-noising based on Intersection of Confidence Intervals (ICI) rule[J]. Journal of Mathematical Imaging and Vision, 2002, 16(3):223-235. 10.1023/a:1020329726980 |
21 | GOLDSTEIN T, OSHER S. The split Bregman method for L1-regularized problems[J]. SIAM Journal on Imaging Sciences, 2009, 2(2): 323-343. 10.1137/080725891 |
22 | BECKER S R, CANDÈS E J, GRANT M C. Templates for convex cone problems with applications to sparse signal recovery[J]. Mathematical Programming Computation, 2011, 3(3): 165-218. 10.1007/s12532-011-0029-5 |
23 | Middlebury stereo datasets[DB/OL]. [2021-01-22]. . 10.26649/musci.2015.049 |
24 | ZUO Y F, WU Q, ZHANG J, al et, Explicit edge inconsistency evaluation model for color-guided depth map enhancement[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2018, 28(2):439-453. 10.1109/tcsvt.2016.2609438 |
[1] | Lin GUO, Kunhu LIU, Chenyang MA, Youxue LAI, Yingfen XU. Image super-resolution reconstruction based on residual attention network with receptive field expansion [J]. Journal of Computer Applications, 2024, 44(5): 1579-1587. |
[2] | Zihan LIU, Dengwen ZHOU, Yukai LIU. Image super-resolution network based on global dependency Transformer [J]. Journal of Computer Applications, 2024, 44(5): 1588-1596. |
[3] | Yang LIU, Rong LIU, Ke FANG, Xinyue ZHANG, Guangxu WANG. Video super-resolution reconstruction network based on frame straddling optical flow [J]. Journal of Computer Applications, 2024, 44(4): 1277-1284. |
[4] | Feng CAO, Xiaoling YANG, Jianbing YI, Jun LI. Contradiction separation super-deduction method and application [J]. Journal of Computer Applications, 2024, 44(10): 3074-3080. |
[5] | Hao CHEN, Zhenping XIA, Cheng CHENG, Xing LIN-LI, Bowen ZHANG. Lightweight image super-resolution reconstruction network based on Transformer-CNN [J]. Journal of Computer Applications, 2024, 44(1): 292-299. |
[6] | Min LIANG, Jiayi LIU, Jie LI. Image super-resolution reconstruction method based on iterative feedback and attention mechanism [J]. Journal of Computer Applications, 2023, 43(7): 2280-2287. |
[7] | Lihua SHEN, Bo LI. Super-resolution reconstruction of lung CT images based on feature pyramid network and dense network [J]. Journal of Computer Applications, 2023, 43(5): 1612-1619. |
[8] | Qi WANG, Hang LEI, Xupeng WANG. Deep face verification under pose interference [J]. Journal of Computer Applications, 2023, 43(2): 595-600. |
[9] | Ying LI, Chao HUANG, Chengdong SUN, Yong XU. Single image super-resolution method based on residual shrinkage network in real complex scenes [J]. Journal of Computer Applications, 2023, 43(12): 3903-3910. |
[10] | Yining WANG, Qingshan ZHAO, Pinle QIN, Yulan HU, Chunmei ZONG. Super-resolution reconstruction algorithm of medical image based on lightweight dense neural network [J]. Journal of Computer Applications, 2022, 42(8): 2586-2592. |
[11] | Jia LI, Yuanlin ZHENG, Kaiyang LIAO, Haojie LOU, Shiyu LI, Zehao CHEN. No-reference image quality assessment algorithm based on saliency deep features [J]. Journal of Computer Applications, 2022, 42(6): 1957-1964. |
[12] | Huifeng WANG, Yan XU, Yiming WEI, Huizhen WANG. Image super-resolution reconstruction based on parallel convolution and residual network [J]. Journal of Computer Applications, 2022, 42(5): 1570-1576. |
[13] | Ye ZHANG, Rong LIU, Ming LIU, Ming CHEN. Image super-resolution reconstruction network based on multi-channel attention mechanism [J]. Journal of Computer Applications, 2022, 42(5): 1563-1569. |
[14] | Pengwei LIU, Yuan GAO, Pinle QIN, Zhe YIN, Lifang WANG. Medical MRI image super-resolution reconstruction based on multi-receptive field generative adversarial network [J]. Journal of Computer Applications, 2022, 42(3): 938-945. |
[15] | Junbo LI, Pinle QIN, Jianchao ZENG, Meng LI. CT three-dimensional reconstruction algorithm based on super-resolution network [J]. Journal of Computer Applications, 2022, 42(2): 584-591. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||