LPMNet: Latent Part Modification and Generation for 3D Point Clouds

Date

2021-03-01

Author

Öngün, Cihan
Temizel, Alptekin

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

229
views

0
downloads

In this paper, we focus on latent modification and generation of 3D point cloud object models with respect to their semantic parts. Different to the existing methods which use separate networks for part generation and assembly, we propose a single end-to-end Autoencoder model that can handle generation and modification of both semantic parts, and global shapes. The proposed method supports part exchange between 3D point cloud models and composition by different parts to form new models by directly editing latent representations. This holistic approach does not need part-based training to learn part representations and does not introduce any extra loss besides the standard reconstruction loss. The experiments demonstrate the robustness of the proposed method with different object categories and varying number of points. The method can generate new models by integration of generative models such as GANs and VAEs and can work with unannotated point clouds by integration of a segmentation module

URI

https://www.sciencedirect.com/science/article/pii/S0097849321000285?
https://hdl.handle.net/11511/89140

Journal

Computers & Graphics-Uk

DOI

https://doi.org/10.1016/j.cag.2021.02.006

Collections

Graduate School of Informatics, Article

Suggestions

OpenMETU
Core

E3D-D2D: EMBEDDING IN 3D, DETECTION IN 2D THROUGH PROJECTIVE INVARIANTS Yasaroglu, Yagiz; Alatan, Abdullah Aydın (2014-10-30) A novel watermarking method is presented in which the data embedded into a 3D model is extracted from an arbitrary 2D view by using a perspective projective invariant. The data is embedded into 3D positions of selected interest points on a 3D mesh. Determining the interest point modification vectors for ensuring watermark detection constitutes an important part of the proposed method. Different watermark embedding schemes based on optimization of the watermark function are implemented and evaluated. Another...
turboTDDFT - A code for the simulation of molecular spectra using the Liouville-Lanczos approach to time-dependent density-functional perturbation theory Malcıoğlu, Osman Barış; Rocca, Dario; Baroni, Stefano (Elsevier BV, 2011-08-01) We introduce turboTDDFT, an implementation of the Liouville-Lanczos approach to linearized time-dependent density-functional theory, designed to simulate the optical spectra of molecular systems made of up to several hundred atoms. turboTDDFT is open-source software distributed under the terms of the GPL as a component of QUANTUM ESPRESSO. As with other components, turboTDDFT is optimized to run on a variety of different platforms, from laptops to massively parallel architectures, using native mathematical ...
VSC BASED D-STATCOM WITH SELECTIVE HARMONIC ELIMINATION Cetin, A.; Ermiş, Muammer (2007-09-27) This paper describes the design, implementation and performance of a medium-size distribution type static synchronous compensator (D-STATCOM) with the simplest 2-level, 3-leg VSC topology. Reactive power control is achieved by phase-shift-angle control, and voltage source converter (VSC) harmonics arc eliminated by selective harmonic elimination method (SHEM) technique. VSC has been designed at the highest low-voltage level of 1 kV, and connected to medium-voltage (MV) bus through a low-pass input filter an...
DeepDistance: A multi-task deep regression model for cell detection in inverted microscopy images Koyuncu, Can Fahrettin; Gunesli, Gozde Nur; Atalay, Rengül; GÜNDÜZ DEMİR, Çiğdem (Elsevier BV, 2020-07-01) This paper presents a new deep regression model, which we call DeepDistance, for cell detection in images acquired with inverted microscopy. This model considers cell detection as a task of finding most probable locations that suggest cell centers in an image. It represents this main task with a regression task of learning an inner distance metric. However, different than the previously reported regression based methods, the DeepDistance model proposes to approach its learning as a multi-task regression pro...
3D shape recovery and tracking from multi-camera video sequences via surface deformation Çok kamerali video görüntülerinden yüzey deformasyonu ile 3B şekil geric̈atma ve i̇zleme Sahillioğlu, Yusuf; Yemez, Y.; Skala, V. (2006-12-01) This paper addresses 3D reconstruction and modeling of time-varying real objects using multicamera video. The work consists of two phases. In the first phase, the initial shape of the object is recovered from its silhouettes using a surface deformation model. The same deformation model is also employed in the second phase to track the recovered initial shape through the time-varying silhouette information by surface evolution. The surface deformation/evolution model allows us to construct a spatially and te...

Citation Formats

C. Öngün and A. Temizel, “LPMNet: Latent Part Modification and Generation for 3D Point Clouds,” Computers & Graphics-Uk, pp. 1–20, 2021, Accessed: 00, 2021. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0097849321000285?