Matterport makes a 3D camera that allows users to easily capture physical spaces. That has resulted in the world’s largest dataset of aligned RGB-D images--200 million images from 300,000 different locations, and we want you to help us work with it. We have a broad research agenda focusing on 3D reconstruction and deep learning that includes semantic labeling and segmentation, 3D object classification and pose estimation, depth from RGB, estimation of unseen 3D surfaces, texture/depth in-filling, photogrammetry, SLAM, keypoint matching, and passive stereo.
Matterport makes a 3D camera that allows users to easily capture physical spaces. That has resulted in the world’s largest dataset of aligned RGB-D images--200 million images from 300,000 different locations, and we want you to help us work with it. We have a broad research agenda focusing on 3D reconstruction and deep learning that includes semantic labeling and segmentation, 3D object classification and pose estimation, depth from RGB, estimation of unseen 3D surfaces, texture/depth in-filling, photogrammetry, SLAM, keypoint matching, and passive stereo.
Matterport makes a 3D camera that allows users to easily capture physical spaces. That has resulted in the world’s largest dataset of aligned RGB-D images--400 million images from 450,000 different locations, and we want you to help us work with it. We have a broad research agenda focusing on 3D reconstruction and deep learning that includes semantic labeling and segmentation, 3D object classification and pose estimation, depth from RGB, estimation of unseen 3D surfaces, texture/depth in-filling, photogrammetry, SLAM, keypoint matching, and passive stereo.
Matterport makes a 3D camera that allows users to easily capture physical spaces. That has resulted in the world’s largest dataset of aligned RGB-D images--200 million images from 300,000 different locations, and we want you to help us work with it. We have a broad research agenda focusing on 3D reconstruction and deep learning that includes semantic labeling and segmentation, 3D object classification and pose estimation, depth from RGB, estimation of unseen 3D surfaces, texture/depth in-filling, photogrammetry, SLAM, keypoint matching, and passive stereo.
Check out the gallery here: matterport.com/gallery
Matterport makes a 3D camera that allows users to easily capture physical spaces. That has resulted in the world’s largest dataset of aligned RGB-D images--200 million images from 300,000 different locations, and we want you to help us work with it. We have a broad research agenda focusing on 3D reconstruction and deep learning that includes semantic labeling and segmentation, 3D object classification and pose estimation, depth from RGB, estimation of unseen 3D surfaces, texture/depth in-filling, photogrammetry, SLAM, keypoint matching, and passive stereo.
Check out the gallery here: matterport.com/gallery
Matterport makes a 3D camera that allows users to easily capture physical spaces. That has resulted in the world’s largest dataset of aligned RGB-D images--200 million images from 300,000 different locations, and we want you to help us work with it. We have a broad research agenda focusing on 3D reconstruction and deep learning that includes semantic labeling and segmentation, 3D object classification and pose estimation, depth from RGB, estimation of unseen 3D surfaces, texture/depth in-filling, photogrammetry, SLAM, keypoint matching, and passive stereo.
Check out the gallery here: matterport.com/gallery
Our team has developed an end-to-end hardware and software solution that allows anyone to create, edit, and share 3D models of real-world spaces. Our tools are already used by thousands of professionals in a variety of industries, including real estate, hospitality, entertainment, media, and location-scouting. Our dedicated users create over 20,000 models per month, and these models have been viewed over 70 million times.
Our team has developed an end-to-end hardware and software solution that allows anyone to create, edit, and share 3D models of real-world spaces. Our tools are already used by thousands of professionals in a variety of industries, including real estate, hospitality, entertainment, media, and location-scouting. Our dedicated users create over 20,000 models per month, and these models have been viewed over 70 million times.
Our team has developed an end-to-end hardware and software solution that allows anyone to create, edit, and share 3D models of real-world spaces. Our tools are already used by thousands of professionals in a variety of industries, including real estate, hospitality, entertainment, media, and location-scouting. Our dedicated users create over 20,000 models per month, and these models have been viewed over 70 million times.
Matterport | Sunnyvale, CA | ONSITE | Full-Time |
Matterport develops an end-to-end platform that allows anyone to capture, edit, and share virtual 3D models of real-world spaces.
Matterport makes a 3D camera that allows users to easily capture physical spaces. That has resulted in the world’s largest dataset of aligned RGB-D images--200 million images from 300,000 different locations, and we want you to help us work with it. We have a broad research agenda focusing on 3D reconstruction and deep learning that includes semantic labeling and segmentation, 3D object classification and pose estimation, depth from RGB, estimation of unseen 3D surfaces, texture/depth in-filling, photogrammetry, SLAM, keypoint matching, and passive stereo.
Check out the gallery here: https://matterport.com/gallery
Roles: Computer Vision Engineer / Computer Vis. Researcher / Deep Learning Engineer/ Back-End Developer / Javascript Engineer (3D Team) / Data Platform Architect
Apply: https://matterport.com/careers/positions/
Process: Resume > Technical Phone screen > Onsite
Contact: vbui(at) matterport(dot)com