Search

Point cloud upsampling aims to generate dense and uniformly distributed point sets from a sparse point cloud, which plays a critical role in 3D computer vision. Previous methods typically split a sparse point cloud into several local patches, upsample patch points, and merge all upsampled patches. However, these methods often produce holes, outliers or nonuniformity due to the splitting and merging process which does not maintain consistency among local patches. To address these issues, we propose a novel approach that learns an unsigned distance field guided by local priors for point cloud upsampling. Specifically, we train a local distance indicator (LDI) that predicts the unsigned distance from a query point to a local implicit surface. Utilizing the learned LDI, we learn an unsigned distance field to represent the sparse point cloud with patch consistency. At inference time, we randomly sample queries around the sparse point cloud, and project these query points onto the zero-level set of the learned implicit field to generate a dense point cloud. We justify that the implicit field is naturally continuous, which inherently enables the application of arbitrary-scale upsampling without necessarily retraining for various scales. We conduct comprehensive experiments on both synthetic data and real scans, and report state-of-the-art results under widely used benchmarks., Comment: Accepted by AAAI 2024. Project page: https://lisj575.github.io/APU-LDI

Latest methods represent shapes with open surfaces using unsigned distance functions (UDFs). They train neural networks to learn UDFs and reconstruct surfaces with the gradients around the zero level set of the UDF. However, the differential networks struggle from learning the zero level set where the UDF is not differentiable, which leads to large errors on unsigned distances and gradients around the zero level set, resulting in highly fragmented and discontinuous surfaces. To resolve this problem, we propose to learn a more continuous zero level set in UDFs with level set projections. Our insight is to guide the learning of zero level set using the rest non-zero level sets via a projection procedure. Our idea is inspired from the observations that the non-zero level sets are much smoother and more continuous than the zero level set. We pull the non-zero level sets onto the zero level set with gradient constraints which align gradients over different level sets and correct unsigned distance errors on the zero level set, leading to a smoother and more continuous unsigned distance field. We conduct comprehensive experiments in surface reconstruction for point clouds, real scans or depth maps, and further explore the performance in unsupervised point cloud upsampling and unsupervised point normal estimation with the learned UDF, which demonstrate our non-trivial improvements over the state-of-the-art methods. Code is available at https://github.com/junshengzhou/LevelSetUDF ., Comment: To appear at ICCV2023. Code is available at https://github.com/junshengzhou/LevelSetUDF

Normal estimation for unstructured point clouds is an important task in 3D computer vision. Current methods achieve encouraging results by mapping local patches to normal vectors or learning local surface fitting using neural networks. However, these methods are not generalized well to unseen scenarios and are sensitive to parameter settings. To resolve these issues, we propose an implicit function to learn an angle field around the normal of each point in the spherical coordinate system, which is dubbed as Neural Angle Fields (NeAF). Instead of directly predicting the normal of an input point, we predict the angle offset between the ground truth normal and a randomly sampled query normal. This strategy pushes the network to observe more diverse samples, which leads to higher prediction accuracy in a more robust manner. To predict normals from the learned angle fields at inference time, we randomly sample query vectors in a unit spherical space and take the vectors with minimal angle values as the predicted normals. To further leverage the prior learned by NeAF, we propose to refine the predicted normal vectors by minimizing the angle offsets. The experimental results with synthetic data and real scans show significant improvements over the state-of-the-art under widely used benchmarks., Comment: Accepted by AAAI 2023. Project page: https://lisj575.github.io/NeAF/ Code:https://github.com/lisj575/NeAF

Surface reconstruction for point clouds is an important task in 3D computer vision. Most of the latest methods resolve this problem by learning signed distance functions from point clouds, which are limited to reconstructing closed surfaces. Some other methods tried to represent open surfaces using unsigned distance functions (UDF) which are learned from ground truth distances. However, the learned UDF is hard to provide smooth distance fields due to the discontinuous character of point clouds. In this paper, we propose CAP-UDF, a novel method to learn consistency-aware UDF from raw point clouds. We achieve this by learning to move queries onto the surface with a field consistency constraint, where we also enable to progressively estimate a more accurate surface. Specifically, we train a neural network to gradually infer the relationship between queries and the approximated surface by searching for the moving target of queries in a dynamic way. Meanwhile, we introduce a polygonization algorithm to extract surfaces using the gradients of the learned UDF. We conduct comprehensive experiments in surface reconstruction for point clouds, real scans or depth maps, and further explore our performance in unsupervised point normal estimation, which demonstrate non-trivial improvements of CAP-UDF over the state-of-the-art methods., Comment: Accepted by TPAMI 2024 (extension) and NeurIPS 2022. Project page:https://junshengzhou.github.io/CAP-UDF. Code:https://github.com/junshengzhou/CAP-UDF

Hydrogen bond patterns, proton ordering, and phase transitions of monolayer ice in two-dimensional hydrophobic confinement are fundamentally different from those found for bulk ice. To investigate the behavior of quasi-2D ice, we perform molecular dynamics simulations of water confined between fixed graphene plates at a distance of 0.65 nm. While experimental results are still limited and theoretical investigations are often based on a single force field model, this work presents a systematic study using different water force fields, i.e. SPCE, TIP3P, TIP4P, TIP4P/ICE, TIP5P. The water occupancy of the graphene capillary at a pressure of 1000 MPa is determined to be between 13.5 and 13.9 water molecules per square nanometer, depending on the choice of the water force field. To ensure complete sampling of the configurational space and to overcome barriers separating metastable structures, these simulations are based on the replica exchange molecular dynamics technique. We report different tetragonal hydrogen bond patterns which are classified as nearly square or as rhombic. While many of these arrangements are flat, in some cases puckered arrangements are found, too. Also the proton ordering of the quasi-2D water structures is considered, allowing to identify them as ferroelectric, ferrielectric or antiferroelectric. For temperatures between 200 K and 400 K we find several second-order phase transitions from one ice structure to another, changing in many cases both the arrangements of the oxygen atoms and the proton ordering. For temperatures between 400 K and 600 K there are melting-like transitions from a monolayer of ice to a monolayer of liquid water. These first-order phase transitions have a latent heat between 3.4 and 4.0 kJ/mol., Comment: 40 pages, 9 figures