RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds

@article{Wang2022RangeUDFSS,
  title={RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds},
  author={Bing Wang and Zheng-Sheng Yu and Bo Yang and Jie Qin and T. Breckon and Ling Shao and Niki Trigoni and A. Markham},
  journal={ArXiv},
  year={2022},
  volume={abs/2204.09138}
}
. We present RangeUDF, a new implicit representation based framework to recover the geometry and semantics of continuous 3D scene surfaces from point clouds. Unlike occupancy fields or signed distance fields which can only model closed 3D surfaces, our approach is not restricted to any type of topology. Being different from the existing unsigned distance fields, our framework does not suffer from any surface ambiguity. In addition, our RangeUDF can jointly estimate precise semantics for… 

Learning Consistency-Aware Unsigned Distance Functions Progressively from Raw Point Clouds

A novel method to learn consistency-aware unsigned distance functions directly from raw point clouds is proposed by learning to move 3D queries to reach the surface with a field consistency constraint, where it enables to progressively estimate a more accurate surface.

Self-Supervised Pre-training for 3D Point Clouds via View-Specific Point-to-Image Translation

This paper investigates a translative pre-training paradigm, namely PointVST, driven by a novel self-supervised pretext task of cross-modal translation from an input 3D object point cloud to its diverse forms of 2D rendered images (e.g., silhouette, depth, contour).

DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images

The DM-NeRF method is among the first to simultaneously reconstruct, decompose, manipulate and render complex 3D scenes in a single pipeline, allowing any interested object to be freely manipulated in 3D space such as translation, rotation, size adjustment, and deformation.