Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204320006> ?p ?o ?g. }
- W3204320006 abstract "In this paper we contribute a simple yet effective approach for estimating 3D poses of multiple people from multi-view images. Our proposed coarse-to-fine pipeline first aggregates noisy 2D observations from multiple camera views into 3D space and then associates them into individual instances based on a confidence-aware majority voting technique. The final pose estimates are attained from a novel optimization scheme which links high-confidence multi-view 2D observations and 3D joint candidates. More-over, a statistical parametric body model such as SMPL is leveraged as a regularizing prior for these 3D joint candidates. Specifically, both 3D poses and SMPL parameters are optimized jointly in an alternating fashion. Here the parametric models help in correcting implausible 3D pose estimates and filling in missing joint detections while updated 3D poses in turn guide obtaining better SMPL estimations. By linking 2D and 3D observations, our method is both accurate and generalizes to different data sources because it better decouples the final 3D pose from the interperson constellation and is more robust to noisy 2D detections. We systematically evaluate our method on public datasets and achieve state-of-the-art performance. The code and video will be available on the project page: https://ait.ethz.ch/projects/2021/multi-human-pose/." @default.
- W3204320006 created "2021-10-11" @default.
- W3204320006 creator A5007653479 @default.
- W3204320006 creator A5025000908 @default.
- W3204320006 creator A5042785211 @default.
- W3204320006 creator A5047371218 @default.
- W3204320006 creator A5082294830 @default.
- W3204320006 date "2021-10-01" @default.
- W3204320006 modified "2023-10-18" @default.
- W3204320006 title "Shape-aware Multi-Person Pose Estimation from Multi-View Images" @default.
- W3204320006 cites W1967554269 @default.
- W3204320006 cites W1994508094 @default.
- W3204320006 cites W2073246097 @default.
- W3204320006 cites W2079846689 @default.
- W3204320006 cites W2089384364 @default.
- W3204320006 cites W2095016389 @default.
- W3204320006 cites W2135826343 @default.
- W3204320006 cites W2215643317 @default.
- W3204320006 cites W2345033116 @default.
- W3204320006 cites W2604346130 @default.
- W3204320006 cites W2605947573 @default.
- W3204320006 cites W2611932403 @default.
- W3204320006 cites W2612706635 @default.
- W3204320006 cites W2753067135 @default.
- W3204320006 cites W2771965516 @default.
- W3204320006 cites W2792747672 @default.
- W3204320006 cites W2798411580 @default.
- W3204320006 cites W2962954622 @default.
- W3204320006 cites W2963150697 @default.
- W3204320006 cites W2963355540 @default.
- W3204320006 cites W2963515833 @default.
- W3204320006 cites W2963772981 @default.
- W3204320006 cites W2963781481 @default.
- W3204320006 cites W2963995996 @default.
- W3204320006 cites W2964304707 @default.
- W3204320006 cites W2971476609 @default.
- W3204320006 cites W2971856312 @default.
- W3204320006 cites W2984313141 @default.
- W3204320006 cites W2996498816 @default.
- W3204320006 cites W3009246422 @default.
- W3204320006 cites W3034399482 @default.
- W3204320006 cites W3035068106 @default.
- W3204320006 cites W3035129432 @default.
- W3204320006 cites W3035191304 @default.
- W3204320006 cites W3035278762 @default.
- W3204320006 cites W3035419359 @default.
- W3204320006 cites W3036563849 @default.
- W3204320006 cites W3095001858 @default.
- W3204320006 cites W3115407334 @default.
- W3204320006 cites W3116592456 @default.
- W3204320006 cites W4242146635 @default.
- W3204320006 cites W4248870381 @default.
- W3204320006 doi "https://doi.org/10.1109/iccv48922.2021.01097" @default.
- W3204320006 hasPublicationYear "2021" @default.
- W3204320006 type Work @default.
- W3204320006 sameAs 3204320006 @default.
- W3204320006 citedByCount "17" @default.
- W3204320006 countsByYear W32043200062021 @default.
- W3204320006 countsByYear W32043200062022 @default.
- W3204320006 countsByYear W32043200062023 @default.
- W3204320006 crossrefType "proceedings-article" @default.
- W3204320006 hasAuthorship W3204320006A5007653479 @default.
- W3204320006 hasAuthorship W3204320006A5025000908 @default.
- W3204320006 hasAuthorship W3204320006A5042785211 @default.
- W3204320006 hasAuthorship W3204320006A5047371218 @default.
- W3204320006 hasAuthorship W3204320006A5082294830 @default.
- W3204320006 hasBestOaLocation W32043200062 @default.
- W3204320006 hasConcept C105795698 @default.
- W3204320006 hasConcept C117251300 @default.
- W3204320006 hasConcept C119857082 @default.
- W3204320006 hasConcept C127413603 @default.
- W3204320006 hasConcept C134306372 @default.
- W3204320006 hasConcept C154945302 @default.
- W3204320006 hasConcept C162324750 @default.
- W3204320006 hasConcept C170154142 @default.
- W3204320006 hasConcept C177264268 @default.
- W3204320006 hasConcept C17744445 @default.
- W3204320006 hasConcept C18555067 @default.
- W3204320006 hasConcept C187736073 @default.
- W3204320006 hasConcept C199360897 @default.
- W3204320006 hasConcept C199539241 @default.
- W3204320006 hasConcept C2776760102 @default.
- W3204320006 hasConcept C31972630 @default.
- W3204320006 hasConcept C33923547 @default.
- W3204320006 hasConcept C41008148 @default.
- W3204320006 hasConcept C43521106 @default.
- W3204320006 hasConcept C520049643 @default.
- W3204320006 hasConcept C52102323 @default.
- W3204320006 hasConcept C77618280 @default.
- W3204320006 hasConcept C94625758 @default.
- W3204320006 hasConcept C96250715 @default.
- W3204320006 hasConceptScore W3204320006C105795698 @default.
- W3204320006 hasConceptScore W3204320006C117251300 @default.
- W3204320006 hasConceptScore W3204320006C119857082 @default.
- W3204320006 hasConceptScore W3204320006C127413603 @default.
- W3204320006 hasConceptScore W3204320006C134306372 @default.
- W3204320006 hasConceptScore W3204320006C154945302 @default.
- W3204320006 hasConceptScore W3204320006C162324750 @default.
- W3204320006 hasConceptScore W3204320006C170154142 @default.
- W3204320006 hasConceptScore W3204320006C177264268 @default.