ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction

12/08/2022
by   Zhen Wang, et al.
0

This work introduces alternating latent topologies (ALTO) for high-fidelity reconstruction of implicit 3D surfaces from noisy point clouds. Previous work identifies that the spatial arrangement of latent encodings is important to recover detail. One school of thought is to encode a latent vector for each point (point latents). Another school of thought is to project point latents into a grid (grid latents) which could be a voxel grid or triplane grid. Each school of thought has tradeoffs. Grid latents are coarse and lose high-frequency detail. In contrast, point latents preserve detail. However, point latents are more difficult to decode into a surface, and quality and runtime suffer. In this paper, we propose ALTO to sequentially alternate between geometric representations, before converging to an easy-to-decode latent. We find that this preserves spatial expressiveness and makes decoding lightweight. We validate ALTO on implicit 3D recovery and observe not only a performance improvement over the state-of-the-art, but a runtime improvement of 3-10×. Project website at https://visual.ee.ucla.edu/alto.htm/.

READ FULL TEXT

page 1

page 7

page 8

page 18

page 19

page 20

research
09/22/2020

Implicit reconstructions of thin leaf surfaces from large, noisy point clouds

Thin surfaces, such as the leaves of a plant, pose a significant challen...
research
03/04/2023

NeuDA: Neural Deformable Anchor for High-Fidelity Implicit Surface Reconstruction

This paper studies implicit surface reconstruction leveraging differenti...
research
10/26/2022

Automated Reconstruction of 3D Open Surfaces from Sparse Point Clouds

Real-world 3D data may contain intricate details defined by salient surf...
research
01/05/2022

POCO: Point Convolution for Surface Reconstruction

Implicit neural networks have been successfully used for surface reconst...
research
03/22/2023

Uni-Fusion: Universal Continuous Mapping

We introduce Uni-Fusion, an universal continuous mapping framework for s...
research
10/22/2021

AIR-Nets: An Attention-Based Framework for Locally Conditioned Implicit Representations

This paper introduces Attentive Implicit Representation Networks (AIR-Ne...

Please sign up or login with your details

Forgot password? Click here to reset