|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM362103674 |
| 003 |
DE-627 |
| 005 |
20231226090533.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2023.3316020
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1206.xml
|
| 035 |
|
|
|a (DE-627)NLM362103674
|
| 035 |
|
|
|a (NLM)37713217
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Li, Muyang
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models
|
| 264 |
|
1 |
|c 2023
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Revised 07.11.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a During image editing, existing deep generative models tend to re-synthesize the entire output from scratch, including the unedited regions. This leads to a significant waste of computation, especially for minor editing operations. In this work, we present Spatially Sparse Inference (SSI), a general-purpose technique that selectively performs computation for edited regions and accelerates various generative models, including both conditional GANs and diffusion models. Our key observation is that users prone to gradually edit the input image. This motivates us to cache and reuse the feature maps of the original image. Given an edited image, we sparsely apply the convolutional filters to the edited regions while reusing the cached features for the unedited areas. Based on our algorithm, we further propose Sparse Incremental Generative Engine (SIGE) to convert the computation reduction to latency reduction on off-the-shelf hardware. With about 1%-area edits, SIGE accelerates DDPM by 3.0× on NVIDIA RTX 3090 and 4.6× on Apple M1 Pro GPU, Stable Diffusion by 7.2× on 3090, and GauGAN by 5.6× on 3090 and 5.2× on M1 Pro GPU. Compared to our conference paper, we enhance SIGE to accommodate attention layers and apply it to Stable Diffusion. Additionally, we offer support for Apple M1 Pro GPU and include more results to substantiate the efficacy of our method
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Lin, Ji
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Meng, Chenlin
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Ermon, Stefano
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Han, Song
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhu, Jun-Yan
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 12 vom: 05. Dez., Seite 14465-14480
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:12
|g day:05
|g month:12
|g pages:14465-14480
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2023.3316020
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 45
|j 2023
|e 12
|b 05
|c 12
|h 14465-14480
|