Tri-Perspective View Decomposition for Geometry Aware Depth Completion and Super-Resolution

Tri-Perspective View Decomposition for Geometry Aware Depth Completion and Super-Resolution

Depth completion and super-resolution are crucial tasks for comprehensive RGB-D scene understanding, as they involve reconstructing the precise 3D geometry of a scene from sparse or low-resolution depth measurements. However, most existing methods either rely solely on 2D depth representations or di...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on pattern analysis and machine intelligence. - 1979. - PP(2025) vom: 06. Aug.
Auteur principal: Yan, Zhiqiang (Auteur)
Autres auteurs: Wang, Kun, Li, Xiang, Gao, Guangwei, Li, Jun, Yang, Jian
Format: Article en ligne
Langue:English
Publié: 2025
Accès à la collection:IEEE transactions on pattern analysis and machine intelligence
Sujets:Journal Article
LEADER 01000naa a22002652c 4500
001 NLM390739324
003 DE-627
005 20250807232433.0
007 cr uuu---uuuuu
008 250807s2025 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2025.3596391  |2 doi 
028 5 2 |a pubmed25n1523.xml 
035 |a (DE-627)NLM390739324 
035 |a (NLM)40768454 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Yan, Zhiqiang  |e verfasserin  |4 aut 
245 1 0 |a Tri-Perspective View Decomposition for Geometry Aware Depth Completion and Super-Resolution 
264 1 |c 2025 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 06.08.2025 
500 |a published: Print-Electronic 
500 |a Citation Status Publisher 
520 |a Depth completion and super-resolution are crucial tasks for comprehensive RGB-D scene understanding, as they involve reconstructing the precise 3D geometry of a scene from sparse or low-resolution depth measurements. However, most existing methods either rely solely on 2D depth representations or directly incorporate raw 3D point clouds for compensation, which are still insufficient to capture the fine-grained 3D geometry of the scene. In this paper, we introduce Tri-Perspective View Decomposition (TPVD) frameworks that can explicitly model 3D geometry. To this end, (1) TPVD ingeniously decomposes the original 3D point cloud into three 2D views, one of which corresponds to the sparse or low-resolution depth input. (2) For sufficient geometric interaction, TPV Fusion is designed to update the 2D TPV features through recurrent 2D-3D-2D aggregation. (3) By adaptively searching for TPV affinitive neighbors, two additional refinement heads are developed for these two tasks to further improve the geometric consistency. Meanwhile, we build novel datasets named TOFDC for depth completion and TOFDSR for depth super-resolution. Both datasets are acquired using time-of-flight (TOF) sensors and color cameras on smartphones. Extensive experiments on TOFDC, KITTI, NYUv2, SUN RGBD, VKITTI, TOFDSR, RGB-D-D, Lu, and Middlebury datasets indicate that our TPVD outperforms previous depth completion and super-resolution methods, reaching the state of the art 
650 4 |a Journal Article 
700 1 |a Wang, Kun  |e verfasserin  |4 aut 
700 1 |a Li, Xiang  |e verfasserin  |4 aut 
700 1 |a Gao, Guangwei  |e verfasserin  |4 aut 
700 1 |a Li, Jun  |e verfasserin  |4 aut 
700 1 |a Yang, Jian  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g PP(2025) vom: 06. Aug.  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnas 
773 1 8 |g volume:PP  |g year:2025  |g day:06  |g month:08 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2025.3596391  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d PP  |j 2025  |b 06  |c 08