|
1 | 1 | # High Resolution Depth Maps for Stable Diffusion WebUI
|
2 | 2 | This program is an addon for [AUTOMATIC1111's Stable Diffusion WebUI](https://github.com/AUTOMATIC1111/stable-diffusion-webui) that creates depth maps. Using either generated or custom depth maps, it can also create 3D stereo image pairs (side-by-side or anaglyph), normalmaps and 3D meshes. The outputs of the script can be viewed directly or used as an asset for a 3D engine. Please see [wiki](https://github.com/thygate/stable-diffusion-webui-depthmap-script/wiki/Viewing-Results) to learn more. The program has integration with [Rembg](https://github.com/danielgatis/rembg). It also supports batch processing, processing of videos, and can also be run in standalone mode, without Stable Diffusion WebUI.
|
3 | 3 |
|
4 |
| -To generate realistic depth maps from individual images, this script uses code and models from the [MiDaS](https://github.com/isl-org/MiDaS) and [ZoeDepth](https://github.com/isl-org/ZoeDepth) repositories by Intel ISL, or LeReS from the [AdelaiDepth](https://github.com/aim-uofa/AdelaiDepth) repository by Advanced Intelligent Machines. Multi-resolution merging as implemented by [BoostingMonocularDepth](https://github.com/compphoto/BoostingMonocularDepth) is used to generate high resolution depth maps. |
| 4 | +To generate realistic depth maps from individual images, this script uses code and models from the [Marigold](https://github.com/prs-eth/Marigold/) repository, from the [MiDaS](https://github.com/isl-org/MiDaS) and [ZoeDepth](https://github.com/isl-org/ZoeDepth) repositories by Intel ISL, or LeReS from the [AdelaiDepth](https://github.com/aim-uofa/AdelaiDepth) repository by Advanced Intelligent Machines. Multi-resolution merging as implemented by [BoostingMonocularDepth](https://github.com/compphoto/BoostingMonocularDepth) is used to generate high resolution depth maps. |
5 | 5 |
|
6 | 6 | Stereoscopic images are created using a custom-written algorithm.
|
7 | 7 |
|
@@ -94,7 +94,7 @@ Feel free to comment and share in the discussions and submit issues.
|
94 | 94 |
|
95 | 95 | ## Acknowledgements
|
96 | 96 |
|
97 |
| -This project relies on code and information from following papers : |
| 97 | +This project relies on code and information from the following papers : |
98 | 98 |
|
99 | 99 | MiDaS :
|
100 | 100 |
|
@@ -198,3 +198,29 @@ ZoeDepth :
|
198 | 198 | copyright = {arXiv.org perpetual, non-exclusive license}
|
199 | 199 | }
|
200 | 200 | ```
|
| 201 | + |
| 202 | +Marigold - Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation: |
| 203 | + |
| 204 | +``` |
| 205 | +@misc{ke2023repurposing, |
| 206 | + title={Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation}, |
| 207 | + author={Bingxin Ke and Anton Obukhov and Shengyu Huang and Nando Metzger and Rodrigo Caye Daudt and Konrad Schindler}, |
| 208 | + year={2023}, |
| 209 | + eprint={2312.02145}, |
| 210 | + archivePrefix={arXiv}, |
| 211 | + primaryClass={cs.CV} |
| 212 | +} |
| 213 | +``` |
| 214 | + |
| 215 | +Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data |
| 216 | + |
| 217 | +``` |
| 218 | +@misc{yang2024depth, |
| 219 | + title={Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data}, |
| 220 | + author={Lihe Yang and Bingyi Kang and Zilong Huang and Xiaogang Xu and Jiashi Feng and Hengshuang Zhao}, |
| 221 | + year={2024}, |
| 222 | + eprint={2401.10891}, |
| 223 | + archivePrefix={arXiv}, |
| 224 | + primaryClass={cs.CV} |
| 225 | +} |
| 226 | +``` |
0 commit comments