Reference : TSCom-Net: Coarse-to-Fine 3D Textured Shape Completion Network

	Document type :	Scientific congresses, symposiums and conference proceedings : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	Focus Areas :	Computational Sciences
	To cite this reference:	http://hdl.handle.net/10993/52299

Title :	TSCom-Net: Coarse-to-Fine 3D Textured Shape Completion Network
Language :	English
Author, co-author :	Karadeniz, Ahmet Serdar [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2 >]
	Ali, Sk Aziz [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2 >]
	Kacem, Anis [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2 >]
	Dupont, Elona [University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > CVI2 >]
	Aouada, Djamila [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2 >]
Publication date :	2022
Main document title :	TSCom-Net: Coarse-to-Fine 3D Textured Shape Completion Network
Author, co-author :	Karadeniz, Ahmet Serdar
	Ali, Sk Aziz
	Kacem, Anis
	Dupont, Elona
	Aouada, Djamila
Peer reviewed :	Yes
Event name :	European Conference on Computer Vision Workshops
Event date :	from 23-10-2022 to 27-10-2022
Event place (city) :	Tel-Aviv
Event country :	Israel
Keywords :	[en] 3D Reconstruction ; Shape Completion ; Texture-Inpainting ; Implicit Function ; Signed Distance Function
Abstract :	[en] Reconstructing 3D human body shapes from 3D partial textured scans remains a fundamental task for many computer vision and graphics applications – e.g., body animation, and virtual dressing. We propose a new neural network architecture for 3D body shape and highresolution texture completion – TSCom-Net – that can reconstruct the full geometry from mid-level to high-level partial input scans. We decompose the overall reconstruction task into two stages – first, a joint implicit learning network (SCom-Net and TCom-Net) that takes a voxelized scan and its occupancy grid as input to reconstruct the full body shape and predict vertex textures. Second, a high-resolution texture completion network, that utilizes the predicted coarse vertex textures to inpaint the missing parts of the partial ‘texture atlas’. A Thorough experimental evaluation on 3DBodyTex.V2 dataset shows that our method achieves competitive results with respect to the state-of-the-art while generalizing to different types and levels of partial shapes. The proposed method has also ranked second in the track1 of SHApe Recovery from Partial textured 3D scans (SHARP [37 , 2]) 2022 1 challenge1.
Research centres :	Interdisciplinary Centre for Security, Reliability and Trust (SnT) > Computer Vision Imaging & Machine Intelligence (CVI²)
Funders :	Fonds National de la Recherche - FnR
Name of the research project :	FREE-3D: Feature-based Reverse Engineering Of 3D Scans
Permalink :	http://hdl.handle.net/10993/52299
FnR project :	FnR ; FNR16849599 > Djamila Aouada > FREE-3D > Feature-based Reverse Engineering Of 3d Scans > 01/01/2022 > 31/12/2024 > 2021

	File(s) associated to this reference
	Fulltext file(s): File Commentary Version Size Access Open access 2208.08768v2.pdf Author preprint 10.83 MB View/Open

All documents in ORBi^lu are protected by a user license.

 

University of Luxembourg Library |  Feedback |  Legal notices Site Map