[To be updated]
Project Tirtha is an academic initiative to create 3D models of heritage sites, using crowdsourced images. The word Tirtha is Sanskrit for "a place of pilgrimage", and is commonly used to refer to the sacred sites of Hinduism, Jainism and Buddhism. Our goal is to preserve and showcase the beauty and cultural significance of heritage sites. We believe that by allowing the general public to contribute to the creation of these models, and by providing open access to these models, we can increase awareness and appreciation of these important cultural landmarks and inspire future generations to maintain them for years to come.
This project is open-source under the GNU Affero General Public License v3.0 and is under active development. You can find the source code on our GitHub repo. All contributions are welcome. Please read CONTRIBUTING for more details. You can report bugs or suggest features, submit images via "Contribute", or suggest heritage sites via "Request site". Please read How do I contribute? before proceeding. A slideshow with video instructions for the project can be found here, while a slidedeck presented at ACM Web3D 2023 can be found here.
Please cite the following paper if you use this software in your work:
@inproceedings{10.1145/3611314.3615904, author = {Shivottam, Jyotirmaya and Mishra, Subhankar}, title = {Tirtha - An Automated Platform to Crowdsource Images and Create 3D Models of Heritage Sites}, year = {2023}, isbn = {9798400703249}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3611314.3615904}, doi = {10.1145/3611314.3615904}, booktitle = {Proceedings of the 28th International ACM Conference on 3D Web Technology}, articleno = {11}, numpages = {15}, keywords = {photogrammetry, open source, digital heritage, crowdsourcing, 3D dataset}, location = {San Sebastian, Spain}, series = {Web3D '23} }
Before you begin, please read the following instructions:
If you encounter errors, try the following:
This project utilizes open-source libraries and automated pipelines for photogrammetry (based on AliceVision) and 3D Gaussian Splatting to create 3D models from crowdsourced images of heritage sites. On the photogrammetry side, we broadly perform the steps described at AliceVision | Photogrammetry Pipeline. The generated textured mesh is denoised, decimated, and converted to a .glb
file using obj2gltf
. This file is optimized for web use with meshoptimizer
. Finally, the 3D model is rendered in the browser using <model-viewer>
.
For 3D Gaussian Splatting, we use the splatfacto implementation present in the excellent nerfstudio, which produces a Gaussian point cloud. This is then compressed and filtered and converted to .splat
file for viewing on the web using a WebGL-based 3D Gaussian Splat Viewer. The fuzz / floaters present in the Gaussian Splat models are artifacts of the splatting process and are not part of the original model.
Please note that the models displayed here are low-poly, compressed versions due to web & mobile device constraints.
We thank the following individuals for their contributions to the project's development:
We are grateful to the developers of the following open-source libraries, which help make this project a reality:
obj2gltf
gltfpack
<model-viewer>
We also thank Odisha State Archaeology for their support.
[Effective: July 15, 2023] By accessing this website or uploading images to Project Tirtha ("use"), you agree to be legally and contractually bound by these terms of use and our Privacy Policy. If you do not agree to these terms or our privacy policy, do not access or use Tirtha.
[Effective: September 18, 2024] Please read our privacy policy carefully before using Tirtha. Do not access or use Tirtha if you do not agree with any part of this policy.