Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384405902> ?p ?o ?g. }
- W4384405902 endingPage "15" @default.
- W4384405902 startingPage "1" @default.
- W4384405902 abstract "We present a novel method for reconstructing clothed humans from a sparse set of, e.g., 1–6 RGB images. Despite impressive results from recent works employing deep implicit representation, we revisit the volumetric approach and demonstrate that better performance can be achieved with proper system design. The volumetric representation offers significant advantages in leveraging 3D spatial context through 3D convolutions, and the notorious quantization error is largely negligible with a reasonably large yet affordable volume resolution, e.g., 512. To handle memory and computation costs, we propose a sophisticated coarse-to-fine strategy with voxel culling and subspace sparse convolution. Our method starts with a discretized visual hull to compute a coarse shape and then focuses on a narrow band nearby the coarse shape for refinement. Once the shape is reconstructed, we adopt an image-based rendering approach, which computes the colors of surface points by blending input images with learned weights. Extensive experimental results show that our method significantly reduces the mean point-to-surface (P2S) precision of state-of-the-art methods by more than 50% to achieve approximately 2mm accuracy with a 512 volume resolution. Additionally, images rendered from our textured model achieve a higher peak signal-to-noise ratio (PSNR) compared to state-of-the-art methods." @default.
- W4384405902 created "2023-07-16" @default.
- W4384405902 creator A5003927678 @default.
- W4384405902 creator A5003928684 @default.
- W4384405902 creator A5006988702 @default.
- W4384405902 creator A5007968636 @default.
- W4384405902 creator A5010674973 @default.
- W4384405902 creator A5084953118 @default.
- W4384405902 date "2023-08-21" @default.
- W4384405902 modified "2023-09-25" @default.
- W4384405902 title "High-Resolution Volumetric Reconstruction for Clothed Humans" @default.
- W4384405902 cites W1938204631 @default.
- W4384405902 cites W1967554269 @default.
- W4384405902 cites W1987648924 @default.
- W4384405902 cites W1989191365 @default.
- W4384405902 cites W2040436296 @default.
- W4384405902 cites W2044618760 @default.
- W4384405902 cites W2307770531 @default.
- W4384405902 cites W2461005315 @default.
- W4384405902 cites W2483862638 @default.
- W4384405902 cites W2737305288 @default.
- W4384405902 cites W2771965516 @default.
- W4384405902 cites W2776768244 @default.
- W4384405902 cites W2797515701 @default.
- W4384405902 cites W2798637590 @default.
- W4384405902 cites W2811169695 @default.
- W4384405902 cites W2894865236 @default.
- W4384405902 cites W2961325344 @default.
- W4384405902 cites W2962754033 @default.
- W4384405902 cites W2962849139 @default.
- W4384405902 cites W2963182550 @default.
- W4384405902 cites W2963355540 @default.
- W4384405902 cites W2963515833 @default.
- W4384405902 cites W2963627347 @default.
- W4384405902 cites W2963926543 @default.
- W4384405902 cites W2963995996 @default.
- W4384405902 cites W2965523038 @default.
- W4384405902 cites W2971467054 @default.
- W4384405902 cites W2974180492 @default.
- W4384405902 cites W2978956737 @default.
- W4384405902 cites W2979283733 @default.
- W4384405902 cites W2981637078 @default.
- W4384405902 cites W2981978060 @default.
- W4384405902 cites W2988856441 @default.
- W4384405902 cites W2991621301 @default.
- W4384405902 cites W3004162361 @default.
- W4384405902 cites W3035291735 @default.
- W4384405902 cites W3035492592 @default.
- W4384405902 cites W3035507572 @default.
- W4384405902 cites W3035515538 @default.
- W4384405902 cites W3035551320 @default.
- W4384405902 cites W3041416670 @default.
- W4384405902 cites W309515887 @default.
- W4384405902 cites W3107197814 @default.
- W4384405902 cites W3109585842 @default.
- W4384405902 cites W3117476483 @default.
- W4384405902 cites W3174025609 @default.
- W4384405902 cites W3175408382 @default.
- W4384405902 cites W3176327543 @default.
- W4384405902 cites W3176368002 @default.
- W4384405902 cites W3202432020 @default.
- W4384405902 cites W3209771269 @default.
- W4384405902 cites W4226160668 @default.
- W4384405902 cites W4233857083 @default.
- W4384405902 cites W4312926441 @default.
- W4384405902 cites W4313175219 @default.
- W4384405902 doi "https://doi.org/10.1145/3606032" @default.
- W4384405902 hasPublicationYear "2023" @default.
- W4384405902 type Work @default.
- W4384405902 citedByCount "0" @default.
- W4384405902 crossrefType "journal-article" @default.
- W4384405902 hasAuthorship W4384405902A5003927678 @default.
- W4384405902 hasAuthorship W4384405902A5003928684 @default.
- W4384405902 hasAuthorship W4384405902A5006988702 @default.
- W4384405902 hasAuthorship W4384405902A5007968636 @default.
- W4384405902 hasAuthorship W4384405902A5010674973 @default.
- W4384405902 hasAuthorship W4384405902A5084953118 @default.
- W4384405902 hasBestOaLocation W43844059021 @default.
- W4384405902 hasConcept C11413529 @default.
- W4384405902 hasConcept C141379421 @default.
- W4384405902 hasConcept C154945302 @default.
- W4384405902 hasConcept C205711294 @default.
- W4384405902 hasConcept C2776863239 @default.
- W4384405902 hasConcept C31972630 @default.
- W4384405902 hasConcept C41008148 @default.
- W4384405902 hasConcept C45374587 @default.
- W4384405902 hasConcept C54170458 @default.
- W4384405902 hasConcept C82990744 @default.
- W4384405902 hasConceptScore W4384405902C11413529 @default.
- W4384405902 hasConceptScore W4384405902C141379421 @default.
- W4384405902 hasConceptScore W4384405902C154945302 @default.
- W4384405902 hasConceptScore W4384405902C205711294 @default.
- W4384405902 hasConceptScore W4384405902C2776863239 @default.
- W4384405902 hasConceptScore W4384405902C31972630 @default.
- W4384405902 hasConceptScore W4384405902C41008148 @default.
- W4384405902 hasConceptScore W4384405902C45374587 @default.
- W4384405902 hasConceptScore W4384405902C54170458 @default.
- W4384405902 hasConceptScore W4384405902C82990744 @default.