Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386076432> ?p ?o ?g. }
- W4386076432 abstract "We present a method for inferring dense depth from a camera image and a sparse noisy radar point cloud. We first describe the mechanics behind mmWave radar point cloud formation and the challenges that it poses, i.e. ambiguous elevation and noisy depth and azimuth components that yields incorrect positions when projected onto the image, and how existing works have overlooked these nuances in camera-radar fusion. Our approach is motivated by these mechanics, leading to the design of a network that maps each radar point to the possible surfaces that it may project onto in the image plane. Unlike existing works, we do not process the raw radar point cloud as an erroneous depth map, but query each raw point independently to associate it with likely pixels in the image – yielding a semi-dense radar depth map. To fuse radar depth with an image, we propose a gated fusion scheme that accounts for the confidence scores of the correspondence so that we selectively combine radar and camera embeddings to yield a dense depth map. We test our method on the NuScenes benchmark and show a 10.3% improvement in mean absolute error and a 9.1% improvement in root-mean-square error over the best method. Code: https://github.com/nesl/radar-camera-fusion-depth." @default.
- W4386076432 created "2023-08-23" @default.
- W4386076432 creator A5014648131 @default.
- W4386076432 creator A5022681108 @default.
- W4386076432 creator A5038126065 @default.
- W4386076432 creator A5038328783 @default.
- W4386076432 creator A5039720020 @default.
- W4386076432 creator A5060564722 @default.
- W4386076432 creator A5069083901 @default.
- W4386076432 creator A5074563122 @default.
- W4386076432 date "2023-06-01" @default.
- W4386076432 modified "2023-09-27" @default.
- W4386076432 title "Depth Estimation from Camera Image and mmWave Radar Point Cloud" @default.
- W4386076432 cites W2017161545 @default.
- W4386076432 cites W2060613652 @default.
- W4386076432 cites W2194775991 @default.
- W4386076432 cites W2200911156 @default.
- W4386076432 cites W2416799949 @default.
- W4386076432 cites W2642464438 @default.
- W4386076432 cites W2794739174 @default.
- W4386076432 cites W2883362496 @default.
- W4386076432 cites W2886851716 @default.
- W4386076432 cites W2961926014 @default.
- W4386076432 cites W2963045776 @default.
- W4386076432 cites W2963150697 @default.
- W4386076432 cites W2963316641 @default.
- W4386076432 cites W2964326562 @default.
- W4386076432 cites W2969088625 @default.
- W4386076432 cites W2969202876 @default.
- W4386076432 cites W2986701260 @default.
- W4386076432 cites W2990926822 @default.
- W4386076432 cites W2992464978 @default.
- W4386076432 cites W2998031326 @default.
- W4386076432 cites W2998293366 @default.
- W4386076432 cites W3003796433 @default.
- W4386076432 cites W3009783082 @default.
- W4386076432 cites W3021999445 @default.
- W4386076432 cites W3034041704 @default.
- W4386076432 cites W3035574168 @default.
- W4386076432 cites W3108796451 @default.
- W4386076432 cites W3109128945 @default.
- W4386076432 cites W3118132944 @default.
- W4386076432 cites W3127062510 @default.
- W4386076432 cites W3129529899 @default.
- W4386076432 cites W3129773144 @default.
- W4386076432 cites W3134336057 @default.
- W4386076432 cites W3152805691 @default.
- W4386076432 cites W3168472259 @default.
- W4386076432 cites W3173187288 @default.
- W4386076432 cites W3194042845 @default.
- W4386076432 cites W3196148789 @default.
- W4386076432 cites W3200820186 @default.
- W4386076432 cites W3206335707 @default.
- W4386076432 cites W3210566209 @default.
- W4386076432 cites W4214561781 @default.
- W4386076432 cites W4225807319 @default.
- W4386076432 cites W4287026788 @default.
- W4386076432 cites W4312525448 @default.
- W4386076432 cites W4313151263 @default.
- W4386076432 cites W647288058 @default.
- W4386076432 doi "https://doi.org/10.1109/cvpr52729.2023.00895" @default.
- W4386076432 hasPublicationYear "2023" @default.
- W4386076432 type Work @default.
- W4386076432 citedByCount "0" @default.
- W4386076432 crossrefType "proceedings-article" @default.
- W4386076432 hasAuthorship W4386076432A5014648131 @default.
- W4386076432 hasAuthorship W4386076432A5022681108 @default.
- W4386076432 hasAuthorship W4386076432A5038126065 @default.
- W4386076432 hasAuthorship W4386076432A5038328783 @default.
- W4386076432 hasAuthorship W4386076432A5039720020 @default.
- W4386076432 hasAuthorship W4386076432A5060564722 @default.
- W4386076432 hasAuthorship W4386076432A5069083901 @default.
- W4386076432 hasAuthorship W4386076432A5074563122 @default.
- W4386076432 hasConcept C10929652 @default.
- W4386076432 hasConcept C121332964 @default.
- W4386076432 hasConcept C127313418 @default.
- W4386076432 hasConcept C131979681 @default.
- W4386076432 hasConcept C134406370 @default.
- W4386076432 hasConcept C141353440 @default.
- W4386076432 hasConcept C154945302 @default.
- W4386076432 hasConcept C160633673 @default.
- W4386076432 hasConcept C31972630 @default.
- W4386076432 hasConcept C41008148 @default.
- W4386076432 hasConcept C51399673 @default.
- W4386076432 hasConcept C554190296 @default.
- W4386076432 hasConcept C62520636 @default.
- W4386076432 hasConcept C62649853 @default.
- W4386076432 hasConcept C76155785 @default.
- W4386076432 hasConceptScore W4386076432C10929652 @default.
- W4386076432 hasConceptScore W4386076432C121332964 @default.
- W4386076432 hasConceptScore W4386076432C127313418 @default.
- W4386076432 hasConceptScore W4386076432C131979681 @default.
- W4386076432 hasConceptScore W4386076432C134406370 @default.
- W4386076432 hasConceptScore W4386076432C141353440 @default.
- W4386076432 hasConceptScore W4386076432C154945302 @default.
- W4386076432 hasConceptScore W4386076432C160633673 @default.
- W4386076432 hasConceptScore W4386076432C31972630 @default.
- W4386076432 hasConceptScore W4386076432C41008148 @default.
- W4386076432 hasConceptScore W4386076432C51399673 @default.
- W4386076432 hasConceptScore W4386076432C554190296 @default.