Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297942337> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4297942337 abstract "Although PIFu-based 3D human reconstruction methods are popular, the quality of recovered details is still unsatisfactory. In a sparse (e.g., 3 RGBD sensors) capture setting, the depth noise is typically amplified in the PIFu representation, resulting in flat facial surfaces and geometry-fallible bodies. In this paper, we propose a novel geometry-aware two-scale PIFu for 3D human reconstruction from sparse, noisy inputs. Our key idea is to exploit the complementary properties of depth denoising and 3D reconstruction, for learning a two-scale PIFu representation to reconstruct high-frequency facial details and consistent bodies separately. To this end, we first formulate depth denoising and 3D reconstruction as a multi-task learning problem. The depth denoising process enriches the local geometry information of the reconstruction features, while the reconstruction process enhances depth denoising with global topology information. We then propose to learn the two-scale PIFu representation using two MLPs based on the denoised depth and geometry-aware features. Extensive experiments demonstrate the effectiveness of our approach in reconstructing facial details and bodies of different poses and its superiority over state-of-the-art methods." @default.
- W4297942337 created "2022-10-01" @default.
- W4297942337 creator A5000336592 @default.
- W4297942337 creator A5006197413 @default.
- W4297942337 creator A5013867024 @default.
- W4297942337 creator A5052582390 @default.
- W4297942337 creator A5059021869 @default.
- W4297942337 creator A5076139079 @default.
- W4297942337 date "2021-12-03" @default.
- W4297942337 modified "2023-10-16" @default.
- W4297942337 title "Geometry-aware Two-scale PIFu Representation for Human Reconstruction" @default.
- W4297942337 doi "https://doi.org/10.48550/arxiv.2112.02082" @default.
- W4297942337 hasPublicationYear "2021" @default.
- W4297942337 type Work @default.
- W4297942337 citedByCount "0" @default.
- W4297942337 crossrefType "posted-content" @default.
- W4297942337 hasAuthorship W4297942337A5000336592 @default.
- W4297942337 hasAuthorship W4297942337A5006197413 @default.
- W4297942337 hasAuthorship W4297942337A5013867024 @default.
- W4297942337 hasAuthorship W4297942337A5052582390 @default.
- W4297942337 hasAuthorship W4297942337A5059021869 @default.
- W4297942337 hasAuthorship W4297942337A5076139079 @default.
- W4297942337 hasBestOaLocation W42979423371 @default.
- W4297942337 hasConcept C109950114 @default.
- W4297942337 hasConcept C111919701 @default.
- W4297942337 hasConcept C115961682 @default.
- W4297942337 hasConcept C124066611 @default.
- W4297942337 hasConcept C141379421 @default.
- W4297942337 hasConcept C144024400 @default.
- W4297942337 hasConcept C153180895 @default.
- W4297942337 hasConcept C154945302 @default.
- W4297942337 hasConcept C163294075 @default.
- W4297942337 hasConcept C165696696 @default.
- W4297942337 hasConcept C17744445 @default.
- W4297942337 hasConcept C199539241 @default.
- W4297942337 hasConcept C205649164 @default.
- W4297942337 hasConcept C2776359362 @default.
- W4297942337 hasConcept C2778755073 @default.
- W4297942337 hasConcept C2779304628 @default.
- W4297942337 hasConcept C31972630 @default.
- W4297942337 hasConcept C36289849 @default.
- W4297942337 hasConcept C38652104 @default.
- W4297942337 hasConcept C41008148 @default.
- W4297942337 hasConcept C58640448 @default.
- W4297942337 hasConcept C94625758 @default.
- W4297942337 hasConcept C98045186 @default.
- W4297942337 hasConcept C99498987 @default.
- W4297942337 hasConceptScore W4297942337C109950114 @default.
- W4297942337 hasConceptScore W4297942337C111919701 @default.
- W4297942337 hasConceptScore W4297942337C115961682 @default.
- W4297942337 hasConceptScore W4297942337C124066611 @default.
- W4297942337 hasConceptScore W4297942337C141379421 @default.
- W4297942337 hasConceptScore W4297942337C144024400 @default.
- W4297942337 hasConceptScore W4297942337C153180895 @default.
- W4297942337 hasConceptScore W4297942337C154945302 @default.
- W4297942337 hasConceptScore W4297942337C163294075 @default.
- W4297942337 hasConceptScore W4297942337C165696696 @default.
- W4297942337 hasConceptScore W4297942337C17744445 @default.
- W4297942337 hasConceptScore W4297942337C199539241 @default.
- W4297942337 hasConceptScore W4297942337C205649164 @default.
- W4297942337 hasConceptScore W4297942337C2776359362 @default.
- W4297942337 hasConceptScore W4297942337C2778755073 @default.
- W4297942337 hasConceptScore W4297942337C2779304628 @default.
- W4297942337 hasConceptScore W4297942337C31972630 @default.
- W4297942337 hasConceptScore W4297942337C36289849 @default.
- W4297942337 hasConceptScore W4297942337C38652104 @default.
- W4297942337 hasConceptScore W4297942337C41008148 @default.
- W4297942337 hasConceptScore W4297942337C58640448 @default.
- W4297942337 hasConceptScore W4297942337C94625758 @default.
- W4297942337 hasConceptScore W4297942337C98045186 @default.
- W4297942337 hasConceptScore W4297942337C99498987 @default.
- W4297942337 hasLocation W42979423371 @default.
- W4297942337 hasOpenAccess W4297942337 @default.
- W4297942337 hasPrimaryLocation W42979423371 @default.
- W4297942337 hasRelatedWork W2007874122 @default.
- W4297942337 hasRelatedWork W2042690015 @default.
- W4297942337 hasRelatedWork W2093747323 @default.
- W4297942337 hasRelatedWork W2119493293 @default.
- W4297942337 hasRelatedWork W2397188463 @default.
- W4297942337 hasRelatedWork W2517246325 @default.
- W4297942337 hasRelatedWork W2790481334 @default.
- W4297942337 hasRelatedWork W2914011423 @default.
- W4297942337 hasRelatedWork W3011087369 @default.
- W4297942337 hasRelatedWork W3109244347 @default.
- W4297942337 isParatext "false" @default.
- W4297942337 isRetracted "false" @default.
- W4297942337 workType "article" @default.