ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Deep Implicit Surface Point Prediction Networks

Venkatesh, R and Karmali, T and Sharma, S and Ghosh, A and Babu, RV and Jeni, LA and Singh, M (2021) Deep Implicit Surface Point Prediction Networks. In: Proceedings of the IEEE International Conference on Computer Vision, 10 - 17 October 2021, Montreal, QC, Canada, pp. 12633-12642.

ICCV_2021.pdf - Published Version

Download (5MB) | Preview
Official URL: https://doi.org/10.1109/ICCV48922.2021.01242


Deep neural representations of 3D shapes as implicit functions have been shown to produce high fidelity models surpassing the resolution-memory trade-off faced by the explicit representations using meshes and point clouds. However, most such approaches focus on representing closed shapes. Unsigned distance function (UDF) based approaches have been proposed recently as a promising alternative to represent both open and closed shapes. However, since the gradients of UDFs vanish on the surface, it is challenging to estimate local (differential) geometric properties like the normals and tangent planes which are needed for many downstream applications in vision and graphics. There are additional challenges in computing these properties efficiently with a low-memory footprint. This paper presents a novel approach that models such surfaces using a new class of implicit representations called the closest surface-point (CSP) representation. We show that CSP allows us to represent complex surfaces of any topology (open or closed) with high fidelity. It also allows for accurate and efficient computation of local geometric properties. We further demonstrate that it leads to efficient implementation of downstream algorithms like sphere-tracing for rendering the 3D surface as well as to create explicit mesh-based representations. Extensive experimental evaluation on the ShapeNet dataset validate the above contributions with results surpassing the state-of-the-art.

Item Type: Conference Paper
Publication: Proceedings of the IEEE International Conference on Computer Vision
Publisher: Institute of Electrical and Electronics Engineers Inc.
Additional Information: The copyright for this article belongs to the Authors
Keywords: Computer vision; Deep neural networks; Three dimensional computer graphics, 3-D shape; Explicit representation; Geometric properties; High-fidelity modeling; Implicit function; Implicit surfaces; Neural representations; Point-clouds; Surface points; Trade off, Economic and social effects
Department/Centre: Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited: 01 Jun 2023 09:35
Last Modified: 01 Jun 2023 09:35
URI: https://eprints.iisc.ac.in/id/eprint/81727

Actions (login required)

View Item View Item