Neural networks for video intra prediction:
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Abschlussarbeit Buch |
| Sprache: | English |
| Veröffentlicht: |
Düren
Shaker Verlag
2024
|
| Schriftenreihe: | Aachen Series on Multimedia and Communications Engineering
Volume 25 |
| Schlagworte: | |
| Online-Zugang: | Inhaltsverzeichnis |
| Beschreibung: | xvii, 157 Seiten Illustrationen, Diagramme 21 cm x 14.8 cm, 263 g |
| ISBN: | 9783844094664 3844094660 |
Internformat
MARC
| LEADER | 00000nam a22000008cb4500 | ||
|---|---|---|---|
| 001 | BV049744479 | ||
| 003 | DE-604 | ||
| 005 | 20241007 | ||
| 007 | t| | ||
| 008 | 240617s2024 gw a||| m||| 00||| eng d | ||
| 015 | |a 24,N12 |2 dnb | ||
| 016 | 7 | |a 1323462031 |2 DE-101 | |
| 020 | |a 9783844094664 |9 978-3-8440-9466-4 | ||
| 020 | |a 3844094660 |9 3-8440-9466-0 | ||
| 035 | |a (OCoLC)1457097716 | ||
| 035 | |a (DE-599)DNB1323462031 | ||
| 040 | |a DE-604 |b ger |e rda | ||
| 041 | 0 | |a eng | |
| 044 | |a gw |c XA-DE-NW | ||
| 049 | |a DE-83 | ||
| 084 | |a ST 301 |0 (DE-625)143651: |2 rvk | ||
| 084 | |a ST 330 |0 (DE-625)143663: |2 rvk | ||
| 084 | |8 1\p |a 004 |2 23sdnb | ||
| 100 | 1 | |a Meyer, Maria |d 1989- |e Verfasser |0 (DE-588)1328250067 |4 aut | |
| 245 | 1 | 0 | |a Neural networks for video intra prediction |c Maria Meyer |
| 264 | 1 | |a Düren |b Shaker Verlag |c 2024 | |
| 300 | |a xvii, 157 Seiten |b Illustrationen, Diagramme |c 21 cm x 14.8 cm, 263 g | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 490 | 1 | |a Aachen Series on Multimedia and Communications Engineering |v Volume 25 | |
| 502 | |b Dissertation |c RWTH Aachen University |d 2023 | ||
| 650 | 0 | 7 | |a Digitale Videotechnik |0 (DE-588)4274176-2 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Neuronales Netz |0 (DE-588)4226127-2 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Prädiktive Codierung |0 (DE-588)7616015-4 |2 gnd |9 rswk-swf |
| 653 | |a Neural Networks | ||
| 653 | |a Intra Prediction | ||
| 653 | |a Video Coding | ||
| 655 | 7 | |0 (DE-588)4113937-9 |a Hochschulschrift |2 gnd-content | |
| 689 | 0 | 0 | |a Neuronales Netz |0 (DE-588)4226127-2 |D s |
| 689 | 0 | 1 | |a Digitale Videotechnik |0 (DE-588)4274176-2 |D s |
| 689 | 0 | 2 | |a Prädiktive Codierung |0 (DE-588)7616015-4 |D s |
| 689 | 0 | |5 DE-604 | |
| 830 | 0 | |a Aachen Series on Multimedia and Communications Engineering |v Volume 25 |w (DE-604)BV019760223 |9 25 | |
| 856 | 4 | 2 | |m DNB Datenaustausch |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=035086336&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
| 883 | 1 | |8 1\p |a vlb |d 20240314 |q DE-101 |u https://d-nb.info/provenance/plan#vlb | |
| 943 | 1 | |a oai:aleph.bib-bvb.de:BVB01-035086336 | |
Datensatz im Suchindex
| _version_ | 1817696426316005376 |
|---|---|
| adam_text |
CONTENTS
1
INTRODUCTION
1
2
VIDEO
CODING
AND
NEURAL
NETWORKS
7
2.1
FUNDAMENTALS
OF
VIDEO
CODING
.
7
2.1.1
REPRESENTATION
AND
PROPERTIES
OF
VIDEO
SEQUENCES
.
8
2.1.2
THE
HYBRID
CODING
APPROACH
.
9
2.1.3
PICTURE
PARTITIONING
.
11
2.1.4
PREDICTIVE
CODING
.
14
2.1.5
FURTHER
ESSENTIAL
CODING
TOOLS
.
15
2.1.6
ENCODER
OPTIMIZATION
AND
EVALUATION
METHODS
.
24
2.2
INTRA
PREDICTION
METHODS
.
30
2.2.1
CLASSIC
AND
WIDE-ANGLE
PREDICTION
.
31
2.2.2
MATRIX-BASED
INTRA
PREDICTION
.
37
2.2.3
FURTHER
VVC
INTRA
IMPROVEMENTS
.
40
2.2.4
CHROMA
INTRA
PREDICTION
.
43
2.2.5
INTRA
MODE
SIGNALING
.
45
2.3
NEURAL
NETWORKS
.
50
2.3.1
BASIC
MACHINE
LEARNING
TERMINOLOGY
.
50
2.3.2
COMMON
ARCHITECTURE
ELEMENTS
.
52
2.3.3
LOSS
FUNCTIONS
AND
EVALUATION
METRICS
.
57
2.3.4
LEARNING
METHODS
.
61
2.3.5
PRUNING
.
65
2.3.6
DEDICATED
NETWORK
TYPES
.
66
2.4
STATE
OF
THE
ART
IN
NN-BASED
INTRA
PREDICTION
.
76
2.4.1
A
HISTORY
OF
INTRA
NNS
.
76
2.4.2
NN-BASED
PREDECESSORS
AND
TRAINING
METHODS
OF
MIP
.
79
2.4.3
GAN-BASED
INTRA
APPROACHES
.
82
2.4.4
U-NETS
AND
AUTOENCODERS
.
84
2.4.5
NN-BASED
APPROACHES
FOR
RELATED
TASKS
.86
3
NON-ADAPTIVE
NN-BASED
INTRA
PREDICTION
89
3.1
PREDICTION
PROBLEM
ASSESSMENT
AND
REQUIREMENTS
.
89
3.1.1
INTRA
PREDICTION
OPTIMIZATION
AIM
.
89
3.1.2
PROBABILISTIC
MODELING
.
91
3.1.3
CODEC
INTEGRATION
REQUIREMENTS
.
93
3.2 TRAINING
CONSIDERATIONS
.
96
3.2.1
DATASETS
.
96
3.2.2
PREPROCESSING
.
111
3.2.3
TRAINING
METHODS
AND
HYPER
PARAMETERS
.
114
3.2.4
LOSS
FUNCTION
CHOICE
.
115
CON
TEN
TS
3.3
BASIC
NETWORK
ARCHITECTURES
.
121
3.3.1
SINGLE
OUTPUT
LUMA
PREDICTION
.
121
3.3.2
CHROMA
INTRA
PREDICTION
.
124
3.4
ARCHITECTURE
OPTIMIZATION
AND
NETWORK
PRUNING
.
127
3.4.1
NUMBER
OF
REFERENCE
LINES
.
128
3.4.2
ARCHITECTURAL
HYPERPARAMETERS
.
129
3.4.3
ADDING
DECONVOLUTIONAL
LAYERS
.
132
3.4.4
PRUNING
.
133
3.4.5
TRANSFERENCE
TO
OTHER
NETWORK
VERSIONS
.
135
3.4.6
COMBINED
RESULTS
.
136
3.4.7
VISUAL
EVALUATION
.
137
3.5
INTEGRATION
AND
SIGNALING
.
138
3.5.1
INTEGRATION
INTO
HEVC.
139
3.5.2
INTEGRATION
INTO
VVC
.
157
3.6
COMPARISON
TO
OTHER
WORKS
.
162
4
ADAPTIVE
PREDICTION
NETWORKS
167
4.1
PROBLEM
ANALYSIS
.
167
4.2
MULTIPLE
OUTPUT
NETWORKS
.
169
4.2.1
MULTIPLE
HYPOTHESES
TRAINING
.
170
4.2.2
HM
INTEGRATION
.
171
4.2.3
RESULTS
.
172
4.3
AUTOENCODER
ARCHITECTURES
.
176
4.3.1
CONDITIONAL
AUTOENCODER
MODEL
.
176
4.3.2
ARCHITECTURE
ADJUSTMENTS
.
178
4.3.3
RESULTS
ANALYSIS
.
181
4.4
GENERAL
VARIATIONAL
AUTOENCODER
MODELS
.
186
4.4.1
MODEL
DESCRIPTION
.
187
4.4.2
RESULTS
AND
ANALYSIS
.
188
4.5 VARIATIONAL
AUTOENCODERS
WITH
JOINT
VECTOR
QUANTIZATION
.
191
4.5.1
MODEL
SETUP
.
191
4.5.2
TRAINING
METHODS
AND
LOSS
ADAPTATION
.
192
4.5.3
RESULT
EVALUATION
.
202
4.6
VVC
INTEGRATION
AND
LATENT
SPACE
CODING
.
204
4.6.1
EMBEDDING
BINARIZATION
.
204
4.6.2
FURTHER
INTEGRATION
CONSIDERATIONS
.
208
4.6.3
FINAL
ANALYSIS
.
209
5
INTRA
MODE
PREDICTION
213
5.1
PRELIMINARY
CONSIDERATIONS
AND
PROBLEM
ANALYSIS
.
214
5.1.1
PROBLEM
ASSESSMENT
.
214
5.1.2
DATA
ANALYSIS
.
217
5.2
OCCURRING
PROBLEMS
AND
SOLUTION
IDEAS
.
220
5.2.1
GENERAL
APPROACH
SETUP
.
220
5.2.2
THE
DATA
IMBALANCE
PROBLEM
.223
5.2.3
FURTHER
GENERAL
CHALLENGES
.
227
CONTENTS
5.2.4
JOINT
MODE
AND
BLOCK
PREDICTION
.230
6
CONCLUSION
AND
OUTLOOK
235
6.1
SUMMARY
.
235
6.2
OUTLOOK
.237
A
SELF-ASSEMBLED
DATASET
DETAILS
241
B
TRAINING
RUNS
FOR
ARCHITECTURE
OPTIMIZATION
249
BIBLIOGRAPHY
257 |
| any_adam_object | 1 |
| author | Meyer, Maria 1989- |
| author_GND | (DE-588)1328250067 |
| author_facet | Meyer, Maria 1989- |
| author_role | aut |
| author_sort | Meyer, Maria 1989- |
| author_variant | m m mm |
| building | Verbundindex |
| bvnumber | BV049744479 |
| classification_rvk | ST 301 ST 330 |
| ctrlnum | (OCoLC)1457097716 (DE-599)DNB1323462031 |
| discipline | Informatik |
| format | Thesis Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>00000nam a22000008cb4500</leader><controlfield tag="001">BV049744479</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20241007</controlfield><controlfield tag="007">t|</controlfield><controlfield tag="008">240617s2024 gw a||| m||| 00||| eng d</controlfield><datafield tag="015" ind1=" " ind2=" "><subfield code="a">24,N12</subfield><subfield code="2">dnb</subfield></datafield><datafield tag="016" ind1="7" ind2=" "><subfield code="a">1323462031</subfield><subfield code="2">DE-101</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9783844094664</subfield><subfield code="9">978-3-8440-9466-4</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">3844094660</subfield><subfield code="9">3-8440-9466-0</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)1457097716</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DNB1323462031</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="044" ind1=" " ind2=" "><subfield code="a">gw</subfield><subfield code="c">XA-DE-NW</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-83</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ST 301</subfield><subfield code="0">(DE-625)143651:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ST 330</subfield><subfield code="0">(DE-625)143663:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="8">1\p</subfield><subfield code="a">004</subfield><subfield code="2">23sdnb</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Meyer, Maria</subfield><subfield code="d">1989-</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)1328250067</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Neural networks for video intra prediction</subfield><subfield code="c">Maria Meyer</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Düren</subfield><subfield code="b">Shaker Verlag</subfield><subfield code="c">2024</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">xvii, 157 Seiten</subfield><subfield code="b">Illustrationen, Diagramme</subfield><subfield code="c">21 cm x 14.8 cm, 263 g</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="490" ind1="1" ind2=" "><subfield code="a">Aachen Series on Multimedia and Communications Engineering</subfield><subfield code="v">Volume 25</subfield></datafield><datafield tag="502" ind1=" " ind2=" "><subfield code="b">Dissertation</subfield><subfield code="c">RWTH Aachen University</subfield><subfield code="d">2023</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Digitale Videotechnik</subfield><subfield code="0">(DE-588)4274176-2</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Neuronales Netz</subfield><subfield code="0">(DE-588)4226127-2</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Prädiktive Codierung</subfield><subfield code="0">(DE-588)7616015-4</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">Neural Networks</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">Intra Prediction</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">Video Coding</subfield></datafield><datafield tag="655" ind1=" " ind2="7"><subfield code="0">(DE-588)4113937-9</subfield><subfield code="a">Hochschulschrift</subfield><subfield code="2">gnd-content</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Neuronales Netz</subfield><subfield code="0">(DE-588)4226127-2</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Digitale Videotechnik</subfield><subfield code="0">(DE-588)4274176-2</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="2"><subfield code="a">Prädiktive Codierung</subfield><subfield code="0">(DE-588)7616015-4</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="830" ind1=" " ind2="0"><subfield code="a">Aachen Series on Multimedia and Communications Engineering</subfield><subfield code="v">Volume 25</subfield><subfield code="w">(DE-604)BV019760223</subfield><subfield code="9">25</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">DNB Datenaustausch</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=035086336&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield><datafield tag="883" ind1="1" ind2=" "><subfield code="8">1\p</subfield><subfield code="a">vlb</subfield><subfield code="d">20240314</subfield><subfield code="q">DE-101</subfield><subfield code="u">https://d-nb.info/provenance/plan#vlb</subfield></datafield><datafield tag="943" ind1="1" ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-035086336</subfield></datafield></record></collection> |
| genre | (DE-588)4113937-9 Hochschulschrift gnd-content |
| genre_facet | Hochschulschrift |
| id | DE-604.BV049744479 |
| illustrated | Illustrated |
| indexdate | 2024-12-06T13:06:36Z |
| institution | BVB |
| institution_GND | (DE-588)1064118135 |
| isbn | 9783844094664 3844094660 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-035086336 |
| oclc_num | 1457097716 |
| open_access_boolean | |
| owner | DE-83 |
| owner_facet | DE-83 |
| physical | xvii, 157 Seiten Illustrationen, Diagramme 21 cm x 14.8 cm, 263 g |
| publishDate | 2024 |
| publishDateSearch | 2024 |
| publishDateSort | 2024 |
| publisher | Shaker Verlag |
| record_format | marc |
| series | Aachen Series on Multimedia and Communications Engineering |
| series2 | Aachen Series on Multimedia and Communications Engineering |
| spelling | Meyer, Maria 1989- Verfasser (DE-588)1328250067 aut Neural networks for video intra prediction Maria Meyer Düren Shaker Verlag 2024 xvii, 157 Seiten Illustrationen, Diagramme 21 cm x 14.8 cm, 263 g txt rdacontent n rdamedia nc rdacarrier Aachen Series on Multimedia and Communications Engineering Volume 25 Dissertation RWTH Aachen University 2023 Digitale Videotechnik (DE-588)4274176-2 gnd rswk-swf Neuronales Netz (DE-588)4226127-2 gnd rswk-swf Prädiktive Codierung (DE-588)7616015-4 gnd rswk-swf Neural Networks Intra Prediction Video Coding (DE-588)4113937-9 Hochschulschrift gnd-content Neuronales Netz (DE-588)4226127-2 s Digitale Videotechnik (DE-588)4274176-2 s Prädiktive Codierung (DE-588)7616015-4 s DE-604 Aachen Series on Multimedia and Communications Engineering Volume 25 (DE-604)BV019760223 25 DNB Datenaustausch application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=035086336&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis 1\p vlb 20240314 DE-101 https://d-nb.info/provenance/plan#vlb |
| spellingShingle | Meyer, Maria 1989- Neural networks for video intra prediction Aachen Series on Multimedia and Communications Engineering Digitale Videotechnik (DE-588)4274176-2 gnd Neuronales Netz (DE-588)4226127-2 gnd Prädiktive Codierung (DE-588)7616015-4 gnd |
| subject_GND | (DE-588)4274176-2 (DE-588)4226127-2 (DE-588)7616015-4 (DE-588)4113937-9 |
| title | Neural networks for video intra prediction |
| title_auth | Neural networks for video intra prediction |
| title_exact_search | Neural networks for video intra prediction |
| title_full | Neural networks for video intra prediction Maria Meyer |
| title_fullStr | Neural networks for video intra prediction Maria Meyer |
| title_full_unstemmed | Neural networks for video intra prediction Maria Meyer |
| title_short | Neural networks for video intra prediction |
| title_sort | neural networks for video intra prediction |
| topic | Digitale Videotechnik (DE-588)4274176-2 gnd Neuronales Netz (DE-588)4226127-2 gnd Prädiktive Codierung (DE-588)7616015-4 gnd |
| topic_facet | Digitale Videotechnik Neuronales Netz Prädiktive Codierung Hochschulschrift |
| url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=035086336&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| volume_link | (DE-604)BV019760223 |
| work_keys_str_mv | AT meyermaria neuralnetworksforvideointraprediction |