Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226022580> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4226022580 abstract "We introduce a new method that generates photo-realistic humans under novel views and poses given a monocular video as input. Despite the significant progress recently on this topic, with several methods exploring shared canonical neural radiance fields in dynamic scene scenarios, learning a user-controlled model for unseen poses remains a challenging task. To tackle this problem, we introduce an effective method to a) integrate observations across several frames and b) encode the appearance at each individual frame. We accomplish this by utilizing both the human pose that models the body shape as well as point clouds that partially cover the human as input. Our approach simultaneously learns a shared set of latent codes anchored to the human pose among several frames, and an appearance-dependent code anchored to incomplete point clouds generated by each frame and its predicted depth. The former human pose-based code models the shape of the performer whereas the latter point cloud-based code predicts fine-level details and reasons about missing structures at the unseen poses. To further recover non-visible regions in query frames, we employ a temporal transformer to integrate features of points in query frames and tracked body points from automatically-selected key frames. Experiments on various sequences of dynamic humans from different datasets including ZJU-MoCap show that our method significantly outperforms existing approaches under unseen poses and novel views given monocular videos as input." @default.
- W4226022580 created "2022-05-05" @default.
- W4226022580 creator A5037346006 @default.
- W4226022580 creator A5051145236 @default.
- W4226022580 creator A5063179713 @default.
- W4226022580 creator A5065379006 @default.
- W4226022580 date "2022-04-03" @default.
- W4226022580 modified "2023-09-25" @default.
- W4226022580 title "Neural Rendering of Humans in Novel View and Pose from Monocular Video" @default.
- W4226022580 doi "https://doi.org/10.48550/arxiv.2204.01218" @default.
- W4226022580 hasPublicationYear "2022" @default.
- W4226022580 type Work @default.
- W4226022580 citedByCount "0" @default.
- W4226022580 crossrefType "posted-content" @default.
- W4226022580 hasAuthorship W4226022580A5037346006 @default.
- W4226022580 hasAuthorship W4226022580A5051145236 @default.
- W4226022580 hasAuthorship W4226022580A5063179713 @default.
- W4226022580 hasAuthorship W4226022580A5065379006 @default.
- W4226022580 hasBestOaLocation W42260225801 @default.
- W4226022580 hasConcept C104317684 @default.
- W4226022580 hasConcept C126042441 @default.
- W4226022580 hasConcept C131979681 @default.
- W4226022580 hasConcept C154945302 @default.
- W4226022580 hasConcept C177264268 @default.
- W4226022580 hasConcept C185592680 @default.
- W4226022580 hasConcept C199360897 @default.
- W4226022580 hasConcept C205711294 @default.
- W4226022580 hasConcept C2776760102 @default.
- W4226022580 hasConcept C2780139006 @default.
- W4226022580 hasConcept C31972630 @default.
- W4226022580 hasConcept C41008148 @default.
- W4226022580 hasConcept C55493867 @default.
- W4226022580 hasConcept C65909025 @default.
- W4226022580 hasConcept C66746571 @default.
- W4226022580 hasConcept C76155785 @default.
- W4226022580 hasConceptScore W4226022580C104317684 @default.
- W4226022580 hasConceptScore W4226022580C126042441 @default.
- W4226022580 hasConceptScore W4226022580C131979681 @default.
- W4226022580 hasConceptScore W4226022580C154945302 @default.
- W4226022580 hasConceptScore W4226022580C177264268 @default.
- W4226022580 hasConceptScore W4226022580C185592680 @default.
- W4226022580 hasConceptScore W4226022580C199360897 @default.
- W4226022580 hasConceptScore W4226022580C205711294 @default.
- W4226022580 hasConceptScore W4226022580C2776760102 @default.
- W4226022580 hasConceptScore W4226022580C2780139006 @default.
- W4226022580 hasConceptScore W4226022580C31972630 @default.
- W4226022580 hasConceptScore W4226022580C41008148 @default.
- W4226022580 hasConceptScore W4226022580C55493867 @default.
- W4226022580 hasConceptScore W4226022580C65909025 @default.
- W4226022580 hasConceptScore W4226022580C66746571 @default.
- W4226022580 hasConceptScore W4226022580C76155785 @default.
- W4226022580 hasLocation W42260225801 @default.
- W4226022580 hasOpenAccess W4226022580 @default.
- W4226022580 hasPrimaryLocation W42260225801 @default.
- W4226022580 hasRelatedWork W2571916269 @default.
- W4226022580 hasRelatedWork W2588505718 @default.
- W4226022580 hasRelatedWork W2740010476 @default.
- W4226022580 hasRelatedWork W2972393937 @default.
- W4226022580 hasRelatedWork W2980953096 @default.
- W4226022580 hasRelatedWork W3023157462 @default.
- W4226022580 hasRelatedWork W3109244347 @default.
- W4226022580 hasRelatedWork W3145385008 @default.
- W4226022580 hasRelatedWork W3151946617 @default.
- W4226022580 hasRelatedWork W4313175219 @default.
- W4226022580 isParatext "false" @default.
- W4226022580 isRetracted "false" @default.
- W4226022580 workType "article" @default.