Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386076107> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4386076107 abstract "Recovery of an underlying scene geometry from multi-view images stands as a long-time challenge in computer vision research. The recent promise leverages neural implicit surface learning and differentiable volume rendering, and achieves both the recovery of scene geometry and synthesis of novel views, where deep priors of neural models are used as an inductive smoothness bias. While promising for object-level surfaces, these methods suffer when coping with complex scene surfaces. In the meanwhile, traditional multi-view stereo can recover the geometry of scenes with rich textures, by globally optimizing the local, pixel-wise correspondences across multiple views. We are thus motivated to make use of the complementary benefits from the two strategies, and propose a method termed Helix-shaped neural implicit Surface learning or HelixSurf; HelixSurf uses the intermediate prediction from one strategy as the guidance to regularize the learning of the other one, and conducts such intertwined regularization iteratively during the learning process. We also propose an efficient scheme for differentiable volume rendering in HelixSurf Experiments on surface reconstruction of indoor scenes show that our method compares favorably with existing methods and is orders of magnitude faster, even when some of existing methods are assisted with auxiliary training data. The source code is available at hups://guhub.com/Gorilla-Lab-SCUT/HelixSurf." @default.
- W4386076107 created "2023-08-23" @default.
- W4386076107 creator A5017524281 @default.
- W4386076107 creator A5036326490 @default.
- W4386076107 creator A5038748720 @default.
- W4386076107 creator A5065964089 @default.
- W4386076107 date "2023-06-01" @default.
- W4386076107 modified "2023-09-27" @default.
- W4386076107 title "HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes with Iterative Intertwined Regularization" @default.
- W4386076107 cites W1964057156 @default.
- W4386076107 cites W1992642990 @default.
- W4386076107 cites W1993120651 @default.
- W4386076107 cites W1999478155 @default.
- W4386076107 cites W2074378519 @default.
- W4386076107 cites W2112174119 @default.
- W4386076107 cites W2118246710 @default.
- W4386076107 cites W2122572959 @default.
- W4386076107 cites W2142792228 @default.
- W4386076107 cites W2205172244 @default.
- W4386076107 cites W2345333930 @default.
- W4386076107 cites W2471962767 @default.
- W4386076107 cites W2594519801 @default.
- W4386076107 cites W2738551266 @default.
- W4386076107 cites W2926429807 @default.
- W4386076107 cites W2963926543 @default.
- W4386076107 cites W2967693513 @default.
- W4386076107 cites W2997914516 @default.
- W4386076107 cites W3034259269 @default.
- W4386076107 cites W3034968345 @default.
- W4386076107 cites W3170262190 @default.
- W4386076107 cites W3202037070 @default.
- W4386076107 cites W4206760982 @default.
- W4386076107 cites W4221151978 @default.
- W4386076107 cites W4233857083 @default.
- W4386076107 cites W4247250903 @default.
- W4386076107 cites W4312598811 @default.
- W4386076107 cites W4313186498 @default.
- W4386076107 doi "https://doi.org/10.1109/cvpr52729.2023.01265" @default.
- W4386076107 hasPublicationYear "2023" @default.
- W4386076107 type Work @default.
- W4386076107 citedByCount "0" @default.
- W4386076107 crossrefType "proceedings-article" @default.
- W4386076107 hasAuthorship W4386076107A5017524281 @default.
- W4386076107 hasAuthorship W4386076107A5036326490 @default.
- W4386076107 hasAuthorship W4386076107A5038748720 @default.
- W4386076107 hasAuthorship W4386076107A5065964089 @default.
- W4386076107 hasConcept C108583219 @default.
- W4386076107 hasConcept C134306372 @default.
- W4386076107 hasConcept C154945302 @default.
- W4386076107 hasConcept C160633673 @default.
- W4386076107 hasConcept C202615002 @default.
- W4386076107 hasConcept C205711294 @default.
- W4386076107 hasConcept C2776135515 @default.
- W4386076107 hasConcept C2984842247 @default.
- W4386076107 hasConcept C31972630 @default.
- W4386076107 hasConcept C33923547 @default.
- W4386076107 hasConcept C41008148 @default.
- W4386076107 hasConcept C50644808 @default.
- W4386076107 hasConceptScore W4386076107C108583219 @default.
- W4386076107 hasConceptScore W4386076107C134306372 @default.
- W4386076107 hasConceptScore W4386076107C154945302 @default.
- W4386076107 hasConceptScore W4386076107C160633673 @default.
- W4386076107 hasConceptScore W4386076107C202615002 @default.
- W4386076107 hasConceptScore W4386076107C205711294 @default.
- W4386076107 hasConceptScore W4386076107C2776135515 @default.
- W4386076107 hasConceptScore W4386076107C2984842247 @default.
- W4386076107 hasConceptScore W4386076107C31972630 @default.
- W4386076107 hasConceptScore W4386076107C33923547 @default.
- W4386076107 hasConceptScore W4386076107C41008148 @default.
- W4386076107 hasConceptScore W4386076107C50644808 @default.
- W4386076107 hasLocation W43860761071 @default.
- W4386076107 hasOpenAccess W4386076107 @default.
- W4386076107 hasPrimaryLocation W43860761071 @default.
- W4386076107 hasRelatedWork W121273120 @default.
- W4386076107 hasRelatedWork W1863533157 @default.
- W4386076107 hasRelatedWork W2002009170 @default.
- W4386076107 hasRelatedWork W2034462085 @default.
- W4386076107 hasRelatedWork W2048402902 @default.
- W4386076107 hasRelatedWork W2337415362 @default.
- W4386076107 hasRelatedWork W2740820121 @default.
- W4386076107 hasRelatedWork W317572212 @default.
- W4386076107 hasRelatedWork W4312857205 @default.
- W4386076107 hasRelatedWork W3182299699 @default.
- W4386076107 isParatext "false" @default.
- W4386076107 isRetracted "false" @default.
- W4386076107 workType "article" @default.