Indirect Point Cloud Registration: Aligning Distance Fields Using a Pseudo Third Point Set
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Robotics and Automation Letters"
DOI: 10.1109/lra.2022.3181356
Abstract: In recent years, implicit functions have drawn attention in the field of 3D reconstruction and have successfully been applied with Deep Learning. However, for incremental reconstruction, implicit function-based registrations have been rarely explored. Inspired by… read more here.
Keywords: indirect point; registration; distance fields; deep learning ... See more keywords
AiSDF: Structure-Aware Neural Signed Distance Fields in Indoor Scenes
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Robotics and Automation Letters"
DOI: 10.1109/lra.2024.3375117
Abstract: Indoor scenes we are living in are visually homogenous or textureless, while they inherently have structural forms and provide enough structural priors for 3D scene reconstruction. Motivated by this fact, we propose a structure-aware online… read more here.
Keywords: distance fields; structure; reconstruction; indoor scenes ... See more keywords
G2-SDF: Geometry-Guided Neural Signed Distance Fields for Scalable and Detailed Reconstruction
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Robotics and Automation Letters"
DOI: 10.1109/lra.2025.3585381
Abstract: Efficient reconstruction methods, particularly capable of providing detailed information on obstacle distances across diverse environments, are crucial for effective robot motion planning. In this context, neural Signed Distance Fields (SDFs) offer a powerful solution by… read more here.
Keywords: distance fields; neural signed; reconstruction; signed distance ... See more keywords
DCUDF2: Improving Efficiency and Accuracy in Extracting Zero Level Sets From Unsigned Distance Fields
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Visualization and Computer Graphics"
DOI: 10.1109/tvcg.2025.3588659
Abstract: Unsigned distance fields (UDFs) provide a flexible representation for models with complex topologies, but accurately extracting their zero level sets remains challenging, particularly in preserving topological correctness and fine geometric details. We present DCUDF2, an… read more here.
Keywords: distance fields; level sets; unsigned distance; extracting zero ... See more keywords