{"id":228,"date":"2024-05-12T23:30:43","date_gmt":"2024-05-12T23:30:43","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/?page_id=228"},"modified":"2024-12-14T04:49:16","modified_gmt":"2024-12-14T04:49:16","slug":"conclusion-aviral-agrawal","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/conclusion-aviral-agrawal\/","title":{"rendered":"Conclusion"},"content":{"rendered":"\n

Conclusion and Future Work<\/strong><\/p>\n\n\n

\n
\n
\n

In this work, we study the performance of using Gaussian Splatting [10] (3DGS) for transparent object depth perception.<\/p>\n

We propose Clear-Splatting<\/strong><\/em>, a method to leverage a strong scene prior to improving depth perception of transparent objects using 3DGS. Clear-Splatting begins by learning background Splats of the entire scene without transparent objects. Following this, residual Splats are trained to complement the background Splats. The results suggest that Clear-Splatting learns a competitive depth reconstruction.<\/p>\n

This work could be improved by comparing against more Multi View Synthesis methods non-specific to transparent objects. Future also includes combining Clear-Splatting with recent advances in depth map completion. Future research could explore the performance across different transparent objects and scene conditions.<\/p>\n

We also propose ClearSplatting-2.0<\/strong><\/em>, a method of robustly using imperfect \u2018world\u2019 models to work robustly with transparency. In particular, we integrate Depth Anything V2 model to obtain pseudo ground truth depth maps for depth supervision in two stages of training of the 3DGS model.<\/span><\/p>\n

Future work for ClearSplatting-2.0 includes extending on real-life dataset and learning a network to better deal with scale shift in monocular depth estimates rather than the 0-1 normalization technique adopted in the current method.<\/span><\/p>\n<\/div>\n<\/div>\n<\/div>\n\n\n

References<\/strong><\/h1>\n\n\n
\n
\n
\n

[1] J. Ichnowski*, Y. Avigal*, J. Kerr, and K. Goldberg, \u201cDex-NeRF: Us- ing a neural radiance field to grasp transparent objects,\u201d in Conference on Robot Learning (CoRL), 2020.<\/p>\n

[2] \u00a0X. Chen, H. Zhang, Z. Yu, A. Opipari, and O. C. Jenkins, \u201cClearpose: Large-scale transparent object dataset and benchmark,\u201d in European Conference on Computer Vision, 2022.<\/p>\n

[3] \u00a0C.Phillips,M.Lecce,andK.Daniilidis,\u201cSeeingglassware:fromedge detection to pose estimation and shape recovery,\u201d 06 2016.<\/p>\n

[4] \u00a0C. Xu, J. Chen, M. Yao, J. Zhou, L. Zhang, and Y. Liu, \u201c6dof pose estimation of transparent object from a single rgb- d image,\u201d Sensors, vol. 20, no. 23, 2020. [Online]. Available: https:\/\/www.mdpi.com\/1424- 8220\/20\/23\/6790<\/p>\n

[5] \u00a0L. Yang, B. Kang, Z. Huang, X. Xu, J. Feng, and H. Zhao, \u201cDepth anything: Unleashing the power of large-scale unlabeled data,\u201d arXiv preprint arXiv:2401.10891, 2024.<\/p>\n

[6] \u00a0J.L.Scho \u0308nbergerandJ.-M.Frahm,\u201cStructure-from-motionrevisited,\u201d in Conference on Computer Vision and Pattern Recognition (CVPR), 2016.<\/p>\n

[7] \u00a0B.Mildenhall,P.P.Srinivasan,M.Tancik,J.T.Barron,R.Ramamoor- thi, and R. Ng, \u201cNerf: Representing scenes as neural radiance fields for view synthesis,\u201d in ECCV, 2020.<\/p>\n

[8] \u00a0J. Kerr, L. Fu, H. Huang, Y. Avigal, M. Tancik, J. Ichnowski, A. Kanazawa, and K. Goldberg, \u201cEvo-nerf: Evolving nerf for sequential robot grasping of transparent objects,\u201d in Proceedings of The 6th Conference on Robot Learning, ser. Proceedings of Machine Learning Research, K. Liu, D. Kulic, and J. Ichnowski, Eds., vol.205. PMLR, 14\u201318 Dec 2023, pp. 353\u2013367. [Online]. Available: https:\/\/proceedings.mlr.press\/v205\/kerr23a.html<\/p>\n

[9] \u00a0B. P. Duisterhof, Y. Mao, S. H. Teng, and J. Ichnowski, \u201cResidual- nerf: Learning residual nerfs for transparent object manipulation,\u201d in ICRA, 2024.<\/p>\n

[10] \u00a0B. Kerbl, G. Kopanas, T. Leimku \u0308hler, and G. Drettakis, \u201c3d gaussian splatting for real-time radiance field rendering,\u201d ACM Transactions on Graphics, vol. 42, no. 4, July 2023. [Online]. Available: https:\/\/repo- sam.inria.fr\/fungraph\/3d- gaussian- splatting\/<\/p>\n

[11] \u00a0T. Mu \u0308ller, A. Evans, C. Schied, and A. Keller, \u201cInstant neural graphics primitives with a multiresolution hash encoding,\u201d ACM Trans. Graph., vol. 41, no. 4, pp. 102:1\u2013102:15, Jul. 2022. [Online]. Available: https:\/\/doi.org\/10.1145\/3528223.3530127<\/p>\n

[12] \u00a0C. Reiser, S. Peng, Y. Liao, and A. Geiger, \u201cKilonerf: Speeding up neural radiance fields with thousands of tiny mlps,\u201d CoRR, vol. abs\/2103.13744, 2021. [Online]. Available: https:\/\/arxiv.org\/abs\/2103. 13744<\/p>\n

[13] \u00a0L. Liu, J. Gu, K. Z. Lin, T.-S. Chua, and C. Theobalt, \u201cNeural sparse voxel fields,\u201d NeurIPS, 2020.<\/p>\n

[14] \u00a0A.Yu,R.Li,M.Tancik,H.Li,R.Ng,andA.Kanazawa,\u201cPlenOctrees for real-time rendering of neural radiance fields,\u201d in ICCV, 2021.<\/p>\n

[15] \u00a0C. Sun, M. Sun, and H. Chen, \u201cDirect voxel grid optimization: Super- fast convergence for radiance fields reconstruction,\u201d in CVPR, 2022.<\/p>\n

\n
\n
\n

[16] S.J.Garbin,M.Kowalski,M.Johnson,J.Shotton,andJ.Valentin,\u201cFastnerf: High-fidelity neural rendering at 200fps,\u201d in 2021 IEEE\/CVF International Conference on Computer Vision (ICCV). Los Alamitos, CA, USA: IEEE Computer Society, oct 2021, pp. 14326\u201314335. [Online]. Available: https:\/\/doi.ieeecomputersociety. org\/10.1109\/ICCV48922.2021.01408<\/span><\/p>\n

\n
\n
\n

[17] \u00a0S. Lombardi, T. Simon, G. Schwartz, M. Zollhoefer, Y. Sheikh, and J. Saragih, \u201cMixture of volumetric primitives for efficient neural rendering,\u201d ACM Trans. Graph., vol. 40, no. 4, jul 2021. [Online]. Available: https:\/\/doi.org\/10.1145\/3450626.3459863<\/p>\n

[18] \u00a0M. H. Mubarik, R. Kanungo, T. Zirr, and R. Kumar, \u201cHardware acceleration of neural graphics,\u201d 2023.<\/p>\n

[19] \u00a0K. Deng, A. Liu, J. Zhu, and D. Ramanan, \u201cDepth-supervised nerf: Fewer views and faster training for free,\u201d in 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Los Alamitos, CA, USA: IEEE Computer Society, jun 2022, pp. 12872\u201312881. [Online]. Available: https:\/\/doi.ieeecomputersociety. org\/10.1109\/CVPR52688.2022.01254<\/p>\n

[20] \u00a0B. Attal, E. Laidlaw, A. Gokaslan, C. Kim, C. Richardt, J. Tompkin, and M. O\u2019Toole, \u201cTo \u0308rf: Time-of-flight radiance fields for dynamic scene view synthesis,\u201d Advances in Neural Information Processing Systems, vol. 34, 2021.<\/p>\n

[21] \u00a0Y. Wei, S. Liu, Y. Rao, W. Zhao, J. Lu, and J. Zhou, \u201cNerfingmvs: Guided optimization of neural radiance fields for indoor multi-view stereo,\u201d in ICCV, 2021.<\/p>\n

\n
\n
\n

[22] T. Neff, P. Stadlbauer, M. Parger, A. Kurz, J. H. Mueller, C. R. A. Chaitanya, A. S. Kaplanyan, and M. Steinberger, \u201cDONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networks,\u201d Computer Graphics Forum, vol. 40, no. 4, 2021. [Online]. Available: https:\/\/doi.org\/10.1111\/cgf.14340<\/p>\n

[23] E. Sucar, S. Liu, J. Ortiz, and A. Davison, \u201ciMAP: Implicit mapping and positioning in real-time,\u201d in Proceedings of the International Conference on Computer Vision (ICCV), 2021.<\/p>\n

[24] J. Y. Zhang, G. Yang, S. Tulsiani, and D. Ramanan, \u201cNeRS: Neural reflectance surfaces for sparse-view 3d reconstruction in the wild,\u201d in Conference on Neural Information Processing Systems, 2021.<\/p>\n

[25] J. Chibane, A. Bansal, V. Lazova, and G. Pons-Moll, \u201cStereo ra- diance fields (srf): Learning view synthesis from sparse views of novel scenes,\u201d in IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, jun 2021.<\/p>\n

[26] P. Truong, M.-J. Rakotosaona, F. Manhardt, and F. Tombari, \u201cSparf: Neural radiance fields from sparse and noisy poses.\u201d IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2023.<\/p>\n

[27] M.Niemeyer,J.T.Barron,B.Mildenhall,M.S.M.Sajjadi,A.Geiger, and N. Radwan, \u201cRegnerf: Regularizing neural radiance fields for view synthesis from sparse inputs,\u201d in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2022.<\/p>\n

[28] C.-H. Lin, W.-C. Ma, A. Torralba, and S. Lucey, \u201cBarf: Bundle- adjusting neural radiance fields,\u201d in IEEE International Conference on Computer Vision (ICCV), 2021.<\/p>\n

[29] L. Yen-Chen, P. Florence, J. T. Barron, A. Rodriguez, P. Isola, and T.- Y. Lin, \u201ciNeRF: Inverting neural radiance fields for pose estimation,\u201d in IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021.<\/p>\n

[30] Y. Chen, X. Chen, X. Wang, Q. Zhang, Y. Guo, Y. Shan, and F. Wang, \u201cLocal-to-global registration for bundle-adjusting neural radiance fields,\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 8264\u20138273.<\/p>\n

[31] Y. Jeong, S. Ahn, C. Choy, A. Anandkumar, M. Cho, and J. Park, \u201cSelf-calibrating neural radiance fields,\u201d in Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), October 2021, pp. 5846\u20135854.<\/p>\n

[32] D. Verbin, P. Hedman, B. Mildenhall, T. Zickler, J. T. Barron, and P. P. Srinivasan, \u201cRef-NeRF: Structured view-dependent appearance for neural radiance fields,\u201d CVPR, 2022.<\/p>\n

[33] E. Xie, W. Wang, W. Wang, P. Sun, H. Xu, D. Liang, and P. Luo, \u201cSegmenting transparent objects in the wild with transformer,\u201d 08 2021, pp. 1194\u20131200.<\/p>\n

[34] Y. R. Wang, Y. Zhao, H. Xu, S. Eppel, A. Aspuru-Guzik, F. Shkurti, and A. Garg, \u201cMvtrans: Multi-view perception of transparent objects,\u201d 2023.<\/p>\n

[35] J. Kerr, L. Fu, H. Huang, Y. Avigal, M. Tancik, J. Ichnowski, A. Kanazawa, and K. Goldberg, \u201cEvo-nerf: Evolving nerf for sequential robot grasping of transparent objects,\u201d in 6th Annual Conference on Robot Learning, 2022.<\/span><\/p>\n

[36] W.Yifan,F.Serena,S.Wu,C.O \u0308ztireli,andO.Sorkine-Hornung,<\/span>\u201cDifferentiable surface splatting for point-based geometry processing,\u201d ACM Transactions on Graphics, vol. 38, no. 6, p. 1\u201314, Nov. 2019. [Online]. Available: http:\/\/dx.doi.org\/10.1145\/3355089.3356513<\/span><\/p>\n

\n
\n
\n

[37] \u00a0G. Wu, T. Yi, J. Fang, L. Xie, X. Zhang, W. Wei, W. Liu, Q. Tian, and W. Xinggang, \u201c4d gaussian splatting for real-time dynamic scene rendering,\u201d arXiv preprint arXiv:2310.08528, 2023.<\/p>\n

[38] \u00a0Z.Yang,X.Gao,W.Zhou,S.Jiao,Y.Zhang,andX.Jin,\u201cDeformable 3d gaussians for high-fidelity monocular dynamic scene reconstruc- tion,\u201d arXiv preprint arXiv:2309.13101, 2023.<\/p>\n

[39] \u00a0J. Luiten, G. Kopanas, B. Leibe, and D. Ramanan, \u201cDynamic 3d gaussians: Tracking by persistent dynamic view synthesis,\u201d in 3DV, 2024.<\/p>\n

[40] \u00a0J. Tang, \u201cTorch-ngp: a pytorch implementation of instant-ngp,\u201d 2022, https:\/\/github.com\/ashawkey\/torch-ngp.<\/p>\n

[41] \u00a0B. O. Community, \u201cBlender – a 3d modelling and rendering package,\u201d 2018. [Online]. Available: http:\/\/www.blender.org<\/p>\n

[42] Yang L, Kang B, Huang Z, Zhao Z, Xu X, Feng J, Zhao H. Depth Anything V2. arXiv preprint arXiv:2406.09414. 2024 Jun 13.<\/p>\n

[43] Agrawal, Aviral, et al. “Clear-Splatting: Learning Residual Gaussian Splats for Transparent Object Manipulation.” RoboNerF: 1st Workshop On Neural Fields In Robotics at ICRA 2024<\/i>.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n

\n
\u00a0<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>","protected":false},"excerpt":{"rendered":"

Conclusion and Future Work In this work, we study the performance of using Gaussian Splatting [10] (3DGS) for transparent object depth perception. We propose Clear-Splatting, a method to leverage a strong scene prior to improving depth perception of transparent objects using 3DGS. Clear-Splatting begins by learning background Splats of the entire scene without transparent objects. … <\/p>\n

Continue reading “Conclusion”<\/span><\/a><\/p>\n","protected":false},"author":210,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-228","page","type-page","status-publish","hentry"],"yoast_head":"\nConclusion - MS Computer Vision Capstone | Team 10<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/conclusion-aviral-agrawal\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Conclusion - MS Computer Vision Capstone | Team 10\" \/>\n<meta property=\"og:description\" content=\"Conclusion and Future Work In this work, we study the performance of using Gaussian Splatting [10] (3DGS) for transparent object depth perception. We propose Clear-Splatting, a method to leverage a strong scene prior to improving depth perception of transparent objects using 3DGS. Clear-Splatting begins by learning background Splats of the entire scene without transparent objects. … Continue reading "Conclusion"\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/conclusion-aviral-agrawal\/\" \/>\n<meta property=\"og:site_name\" content=\"MS Computer Vision Capstone | Team 10\" \/>\n<meta property=\"article:modified_time\" content=\"2024-12-14T04:49:16+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/wp-content\/uploads\/sites\/108\/2024\/04\/image1_genai.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1174\" \/>\n\t<meta property=\"og:image:height\" content=\"696\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"7 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team10\\\/conclusion-aviral-agrawal\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team10\\\/conclusion-aviral-agrawal\\\/\",\"name\":\"Conclusion - MS Computer Vision Capstone | Team 10\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team10\\\/#website\"},\"datePublished\":\"2024-05-12T23:30:43+00:00\",\"dateModified\":\"2024-12-14T04:49:16+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team10\\\/conclusion-aviral-agrawal\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team10\\\/conclusion-aviral-agrawal\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team10\\\/conclusion-aviral-agrawal\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team10\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Conclusion\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team10\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team10\\\/\",\"name\":\"Interpretability using Diffusion\",\"description\":\"\",\"alternateName\":\"iud\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team10\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Conclusion - MS Computer Vision Capstone | Team 10","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/conclusion-aviral-agrawal\/","og_locale":"en_US","og_type":"article","og_title":"Conclusion - MS Computer Vision Capstone | Team 10","og_description":"Conclusion and Future Work In this work, we study the performance of using Gaussian Splatting [10] (3DGS) for transparent object depth perception. We propose Clear-Splatting, a method to leverage a strong scene prior to improving depth perception of transparent objects using 3DGS. Clear-Splatting begins by learning background Splats of the entire scene without transparent objects. … Continue reading \"Conclusion\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/conclusion-aviral-agrawal\/","og_site_name":"MS Computer Vision Capstone | Team 10","article_modified_time":"2024-12-14T04:49:16+00:00","og_image":[{"width":1174,"height":696,"url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/wp-content\/uploads\/sites\/108\/2024\/04\/image1_genai.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"7 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/conclusion-aviral-agrawal\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/conclusion-aviral-agrawal\/","name":"Conclusion - MS Computer Vision Capstone | Team 10","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/#website"},"datePublished":"2024-05-12T23:30:43+00:00","dateModified":"2024-12-14T04:49:16+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/conclusion-aviral-agrawal\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/conclusion-aviral-agrawal\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/conclusion-aviral-agrawal\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/"},{"@type":"ListItem","position":2,"name":"Conclusion"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/","name":"Interpretability using Diffusion","description":"","alternateName":"iud","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/wp-json\/wp\/v2\/pages\/228","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/wp-json\/wp\/v2\/users\/210"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/wp-json\/wp\/v2\/comments?post=228"}],"version-history":[{"count":4,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/wp-json\/wp\/v2\/pages\/228\/revisions"}],"predecessor-version":[{"id":342,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/wp-json\/wp\/v2\/pages\/228\/revisions\/342"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team10\/wp-json\/wp\/v2\/media?parent=228"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}