{"id":149,"date":"2022-04-29T18:26:11","date_gmt":"2022-04-29T18:26:11","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/?page_id=149"},"modified":"2022-04-29T19:58:02","modified_gmt":"2022-04-29T19:58:02","slug":"experimental-results","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/experimental-results\/","title":{"rendered":"Experimental Results"},"content":{"rendered":"\n<h2 class=\"wp-block-heading\">Benchmark Results<\/h2>\n\n\n\n<p>We compared our method to published state-of-the-art methods on standard benchmarks for 3D and 4D lidar panoptic segmentation on <em>Panoptic nuScenes<\/em> and <em>SemanticKITTI<\/em>. <\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"290\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-4-1024x290.png\" alt=\"\" class=\"wp-image-179\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-4-1024x290.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-4-300x85.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-4-768x218.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-4-1536x436.png 1536w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-4.png 1664w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><figcaption>Table 1: Lidar panoptic segmentation performance on nuScenes validation and test sets. We <strong>obtain overall top results by a significant margin across all metrics<\/strong>. Best results are <strong>bolded<\/strong>, while second best are <span style=\"text-decoration: underline\">underlined<\/span>.<\/figcaption><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"359\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-5-1024x359.png\" alt=\"\" class=\"wp-image-182\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-5-1024x359.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-5-300x105.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-5-768x270.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-5-1536x539.png 1536w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-5.png 1664w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><figcaption>Table 2: Lidar panoptic segmentation performance on SemanticKITTI validation and test sets. Our method is second-best across all metrics without any changes to the model. We note that the top-performing method on SemanticKITTI (GP-S3Net) drops down to rank 4 on nuScenes, while<strong> we perform best or second-best across both datasets<\/strong>. This suggests our framework may be more general. Our method builds on the same encoder-decoder backbone as DS-Net, however, significantly improves the results in terms of PQ and mIoU, thanks to our modal recognition branch and instance segmentation network. Best results are <strong>bolded<\/strong>, while second best are <span style=\"text-decoration: underline\">underlined<\/span>.<\/figcaption><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"339\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-11-1024x339.png\" alt=\"\" class=\"wp-image-193\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-11-1024x339.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-11-300x99.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-11-768x254.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-11.png 1124w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><figcaption>Table 3: 4D lidar panoptic segmentation on panoptic nuScenes test and validation sets. Our method is consistently overall top-performer across all metrics by a significant margin. Best results are <strong>bolded<\/strong>, while second best are <span style=\"text-decoration: underline\">underlined<\/span>.<\/figcaption><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">Ablation Studies<\/h2>\n\n\n\n<p><strong>Modal recognition or center-offset regression?<\/strong><\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"141\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-12-1024x141.png\" alt=\"\" class=\"wp-image-212\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-12-1024x141.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-12-300x41.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-12-768x106.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-12-1536x212.png 1536w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-12-2048x282.png 2048w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><figcaption>Table 4: Bottom-up center-offset regression (DS-Net) vs. Top-down modal approach<\/figcaption><\/figure>\n\n\n\n<p>All methods are sharing <strong>same<\/strong> semantic segmentation network. The first two entries used <strong>center offsets followed by clustering<\/strong> to obtain instances, while the third entry would use our <strong>modal detector followed by PointSegMLP<\/strong> to obtain instances.  As the semantic segmentation networks are identical, <strong>this experiment highlights the effectiveness of our modal detection branch.<\/strong><\/p>\n\n\n\n<p><strong>Separate models or a unified model?<\/strong><\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"152\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-13-1024x152.png\" alt=\"\" class=\"wp-image-217\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-13-1024x152.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-13-300x45.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-13-768x114.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-13-1536x228.png 1536w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-13-2048x304.png 2048w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><figcaption>Table 5: MOST w\/o weight sharing vs. MOST w\/ weight sharing<\/figcaption><\/figure>\n\n\n\n<p>First entry has <strong>two separate models<\/strong> for semantic segmentation &amp; modal instance recognition. we train a single network for semantic segmentation and modal instance recognition and segmentation (i.e. our full model), this yields overall best results with a PQ score of 73.1. This indicates co-learning helps <strong>communication<\/strong> between two tasks and benefit the final performance.<\/p>\n\n\n\n<p><strong>Can our model benefit from amodal labels?<\/strong><\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"197\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-14-1024x197.png\" alt=\"\" class=\"wp-image-218\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-14-1024x197.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-14-300x58.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-14-768x148.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-14-1536x295.png 1536w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-14-2048x394.png 2048w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><figcaption>Table 6: using modal labels vs. using amodal labels<\/figcaption><\/figure>\n\n\n\n<p>In this experiment, we evaluate the impact of modal training on our detection component. While our network trained with modal labels is already state-of-the-art, this experiment c<strong>onfirms we can further benefit from amodal recognition whenever such labels are available<\/strong>. <strong>Extra information (e.g. orientation, full extent)<\/strong> is available in amodal labels, which may help.<\/p>\n\n\n\n<p><strong>PointSegMLP?<\/strong><\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"886\" height=\"240\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-15.png\" alt=\"\" class=\"wp-image-220\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-15.png 886w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-15-300x81.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-15-768x208.png 768w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><figcaption>Table 7: The effectiveness of our PointSegMLP <\/figcaption><\/figure>\n\n\n\n<p>we compare our <em>PointSegMLP<\/em> with a simple, yet surprisingly effective nearest neighbor heuristic (<em>NN-baseline<\/em>). As can be seen, our learning-based <em>PointSegMLP<\/em> based on 3D positions and semantic predictions already significantly outperforms the heuristic. While instance (BEV) features in isolation do not benefit our model, they further improve the performance when combined with per-point semantic features.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Qualitative Results<\/h2>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-16-749x1024.png\" alt=\"\" class=\"wp-image-222\" width=\"675\" height=\"922\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-16-749x1024.png 749w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-16-219x300.png 219w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-16-768x1050.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-16.png 784w\" sizes=\"auto, (max-width: 675px) 100vw, 675px\" \/><figcaption><br>Figure 1. Qualitative comparison of DS-Net, our NN-Baseline and MOST<\/figcaption><\/figure>\n\n\n\n<p><\/p>\n\n\n\n<figure class=\"wp-block-image\"><img decoding=\"async\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/69d75a8d-5b91-42d4-9732-481cd4f05c6a\" alt=\"\" \/><\/figure>\n\n\n\n<p><\/p>\n\n\n\n<p>More qualitative results can be accessed from <a href=\"https:\/\/drive.google.com\/file\/d\/1oz_VCQwb8tyShuUiwSuAvRklVOGEQ0Mq\/view?usp=sharing\">here<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Benchmark Results We compared our method to published state-of-the-art methods on standard benchmarks for 3D and 4D lidar panoptic segmentation on Panoptic nuScenes and SemanticKITTI. Ablation Studies Modal recognition or center-offset regression? All methods are sharing same semantic segmentation network. The first two entries used center offsets followed by clustering to obtain instances, while the &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/experimental-results\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Experimental Results&#8221;<\/span><\/a><\/p>\n","protected":false},"author":107,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-149","page","type-page","status-publish","hentry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.1 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Experimental Results - Panoptic Lidar Segmentation for Autonomous Driving<\/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\/2021teame\/experimental-results\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Experimental Results - Panoptic Lidar Segmentation for Autonomous Driving\" \/>\n<meta property=\"og:description\" content=\"Benchmark Results We compared our method to published state-of-the-art methods on standard benchmarks for 3D and 4D lidar panoptic segmentation on Panoptic nuScenes and SemanticKITTI. Ablation Studies Modal recognition or center-offset regression? All methods are sharing same semantic segmentation network. The first two entries used center offsets followed by clustering to obtain instances, while the &hellip; Continue reading &quot;Experimental Results&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/experimental-results\/\" \/>\n<meta property=\"og:site_name\" content=\"Panoptic Lidar Segmentation for Autonomous Driving\" \/>\n<meta property=\"article:modified_time\" content=\"2022-04-29T19:58:02+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-4-1024x290.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=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2021teame\\\/experimental-results\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2021teame\\\/experimental-results\\\/\",\"name\":\"Experimental Results - Panoptic Lidar Segmentation for Autonomous Driving\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2021teame\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2021teame\\\/experimental-results\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2021teame\\\/experimental-results\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2021teame\\\/wp-content\\\/uploads\\\/sites\\\/50\\\/2022\\\/04\\\/image-4-1024x290.png\",\"datePublished\":\"2022-04-29T18:26:11+00:00\",\"dateModified\":\"2022-04-29T19:58:02+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2021teame\\\/experimental-results\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2021teame\\\/experimental-results\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2021teame\\\/experimental-results\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2021teame\\\/wp-content\\\/uploads\\\/sites\\\/50\\\/2022\\\/04\\\/image-4.png\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2021teame\\\/wp-content\\\/uploads\\\/sites\\\/50\\\/2022\\\/04\\\/image-4.png\",\"width\":1664,\"height\":472},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2021teame\\\/experimental-results\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2021teame\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Experimental Results\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2021teame\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2021teame\\\/\",\"name\":\"Panoptic Lidar Segmentation for Autonomous Driving\",\"description\":\"Students: Abhinav Agarwalla, Xuhua Huang | Advisor: Aljosa Osep, James Hays, Deva Ramanan | Sponsor: Argo AI\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2021teame\\\/?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":"Experimental Results - Panoptic Lidar Segmentation for Autonomous Driving","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\/2021teame\/experimental-results\/","og_locale":"en_US","og_type":"article","og_title":"Experimental Results - Panoptic Lidar Segmentation for Autonomous Driving","og_description":"Benchmark Results We compared our method to published state-of-the-art methods on standard benchmarks for 3D and 4D lidar panoptic segmentation on Panoptic nuScenes and SemanticKITTI. Ablation Studies Modal recognition or center-offset regression? All methods are sharing same semantic segmentation network. The first two entries used center offsets followed by clustering to obtain instances, while the &hellip; Continue reading \"Experimental Results\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/experimental-results\/","og_site_name":"Panoptic Lidar Segmentation for Autonomous Driving","article_modified_time":"2022-04-29T19:58:02+00:00","og_image":[{"url":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-4-1024x290.png","type":"","width":"","height":""}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/experimental-results\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/experimental-results\/","name":"Experimental Results - Panoptic Lidar Segmentation for Autonomous Driving","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/experimental-results\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/experimental-results\/#primaryimage"},"thumbnailUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-4-1024x290.png","datePublished":"2022-04-29T18:26:11+00:00","dateModified":"2022-04-29T19:58:02+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/experimental-results\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/experimental-results\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/experimental-results\/#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-4.png","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-content\/uploads\/sites\/50\/2022\/04\/image-4.png","width":1664,"height":472},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/experimental-results\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/"},{"@type":"ListItem","position":2,"name":"Experimental Results"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/","name":"Panoptic Lidar Segmentation for Autonomous Driving","description":"Students: Abhinav Agarwalla, Xuhua Huang | Advisor: Aljosa Osep, James Hays, Deva Ramanan | Sponsor: Argo AI","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/?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\/2021teame\/wp-json\/wp\/v2\/pages\/149","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-json\/wp\/v2\/users\/107"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-json\/wp\/v2\/comments?post=149"}],"version-history":[{"count":13,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-json\/wp\/v2\/pages\/149\/revisions"}],"predecessor-version":[{"id":231,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-json\/wp\/v2\/pages\/149\/revisions\/231"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2021teame\/wp-json\/wp\/v2\/media?parent=149"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}