Search Results for author:
Found 68 papers, 38 papers with code
MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-Step
Recent methods usually train neural networks to overfit on single point clouds to infer signed distance functions (SDFs).
DiffGS: Functional Gaussian Splatting Diffusion
Through the novel disentanglement of 3DGS, we represent the discrete and unstructured 3DGS with continuous Gaussian Splatting functions, where we then train a latent diffusion model with the target of generating these Gaussian Splatting functions both unconditionally and conditionally.
Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priors
To resolve this issue, we propose a method to promote pros of both data-driven based and overfitting-based methods for better generalization, faster inference, and higher accuracy in learning neural SDFs.
Zero-shot Object Navigation with Vision-Language Models Reasoning
Zero-shot object navigation (ZSON) aims to address this challenge, allowing robots to interact with unknown objects without specific training data.
Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis
In this paper, We propose a novel method for synthesizing novel views from sparse views with Gaussian Splatting that does not require external prior as supervision.
Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assembly
Large language and vision models have been leading a revolution in visual computing.
Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set
Although 3DGS provides a promising neural rendering option, it is still hard to infer SDFs for surface reconstruction with 3DGS due to the discreteness, the sparseness, and the off-surface drift of 3D Gaussians.
Learning Local Pattern Modularization for Point Cloud Reconstruction from Unseen Classes
Instead of object-centered coordinate system, current methods generalized global priors learned in seen classes to reconstruct 3D shapes from unseen classes in viewer-centered coordinate system.
Learning Unsigned Distance Functions from Multi-view Images with Volume Rendering Priors
To infer a UDF for an unseen scene from multiple RGB images, we generalize the learned volume rendering priors to map inferred unsigned distances in alpha blending for RGB image rendering.
Implicit Filtering for Learning Neural Signed Distance Functions from 3D Point Clouds
The neural network typically fits the shape with a rough surface and omits fine-grained geometric details such as shape edges and corners.
UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusion
In this work, we present UDiFF, a 3D diffusion model for unsigned distance fields (UDFs) which is capable to generate textured 3D shapes with open surfaces from text conditions or unconditionally.
GridFormer: Point-Grid Transformer for Surface Reconstruction
Our method maximizes the spatial expressiveness of grid features and maintains computational efficiency.
Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling
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.
NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views
To achieve this, we train a neural network to learn a global implicit field from the on-surface points obtained from SfM and then leverage it as a coarse geometric constraint.
Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matching
To address these problems, we propose to learn a structured cross-modality latent space to represent pixel features and 3D features via a differentiable probabilistic PnP solver.
GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation
We justify that the refined 3D geometric priors aid in the 3D-aware capability of 2D diffusion priors, which in turn provides superior guidance for the refinement of 3D geometric priors.
NeuralGF: Unsupervised Point Normal Estimation by Learning Neural Gradient Function
Specifically, we introduce loss functions to facilitate query points to iteratively reach the moving targets and aggregate onto the approximated surface, thereby learning a global surface representation of the data.
Uni3D: Exploring Unified 3D Representation at Scale
Scaling up representations for images or text has been extensively investigated in the past few years and has led to revolutions in learning vision and language.
Ranked #1 on
Zero-shot 3D classification
on Objaverse LVIS
(using extra training data)
Neural Gradient Learning and Optimization for Oriented Point Normal Estimation
We propose Neural Gradient Learning (NGL), a deep learning approach to learn gradient vectors with consistent orientation from 3D point clouds for normal estimation.
GridPull: Towards Scalability in Learning Implicit Representations from 3D Point Clouds
However, these methods suffer from a slow inference due to the slow convergence of neural networks and the extensive calculation of distances to surface points, which limits them to small scale points.
Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projection
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.
Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation
In this way, the categorization of each point is conditioned on its local semantic pattern.
Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping
However, without ground truth signed distances, point normals or clean point clouds, current methods still struggle from learning SDFs from noisy point clouds.
Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignment
Our insight is to propagate the zero level set to everywhere in the field through consistent gradients to eliminate uncertainty in the field that is caused by the discreteness of 3D point clouds or the lack of observations from multi-view images.
Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation
In this work, we introduce signed hyper surfaces (SHS), which are parameterized by multi-layer perceptron (MLP) layers, to learn to estimate oriented normals from point clouds in an end-to-end manner.
D-Net: Learning for Distinctive Point Clouds by Self-Attentive Point Searching and Learnable Feature Fusion
Most of early methods selected the important points on 3D shapes by analyzing the intrinsic geometric properties of every single shape, which fails to capture the importance of points that distinguishes a shape from objects of other classes, i. e., the distinction of points.
Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting
Previous multiview registration methods rely on exhaustive pairwise registration to construct a densely-connected pose graph and apply Iteratively Reweighted Least Square (IRLS) on the pose graph to compute the scan poses.
Unsupervised Inference of Signed Distance Functions from Single Sparse Point Clouds without Learning Priors
To resolve this issue, we present a neural network to directly infer SDFs from single sparse point clouds without using signed distance supervision, learned priors or even normals.
LP-DIF: Learning Local Pattern-Specific Deep Implicit Function for 3D Objects and Scenes
To capture geometry details, current mainstream methods divide 3D shapes into local regions and then learn each one with a local latent code via a decoder, where the decoder shares the geometric similarities among different local regions.
NeAF: Learning Neural Angle Fields for Point Normal Estimation
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).
Ranked #3 on
Surface Normals Estimation
on PCPNet
HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfaces
To address these issues, we introduce hyper surface fitting to implicitly learn hyper surfaces, which are represented by multi-layer perceptron (MLP) layers that take point features as input and output surface patterns in a high dimensional feature space.
Ranked #2 on
Surface Normals Estimation
on PCPNet
CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimization
Some other methods tried to represent open surfaces using unsigned distance functions (UDF) which are learned from ground truth distances.
Fast Learning Radiance Fields by Shooting Much Fewer Rays
Experimental results show that our method achieves comparable accuracy to the state-of-the-art with much faster training.
Latent Partition Implicit with Surface Codes for 3D Representation
Our insight here is that both the part learning and the part blending can be conducted much easier in the latent space than in the spatial space.
Surface Reconstruction from Point Clouds by Learning Predictive Context Priors
To reconstruct a surface at a specific query location at inference time, these methods then match the local reconstruction target by searching for the best match in the local prior space (by optimizing the parameters encoding the local context) at the given query location.
Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors
Our key idea is to infer signed distances by pushing both the query projections to be on the surface and the projection distance to be the minimum.
3D Shape Reconstruction from 2D Images with Disentangled Attribute Flow
Reconstructing 3D shape from a single 2D image is a challenging task, which needs to estimate the detailed 3D structures based on the semantic attributes from 2D image.
3D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point Clouds
To address this problem, we present a novel and efficient self-supervised point cloud representation learning framework, named 3D Occlusion Auto-Encoder (3D-OAE), to facilitate the detailed supervision inherited in local regions and global shapes.
Learning Deep Implicit Functions for 3D Shapes with Dynamic Code Clouds
However, the local codes are constrained at discrete and regular positions like grid points, which makes the code positions difficult to be optimized and limits their representation ability.
Modeling and Validating Temporal Rules with Semantic Petri-Net for Digital Twins
Semantic rule checking on RDFS/OWL data has been widely used in the construction industry.
PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Paths
It moves each point of incomplete input to obtain a complete point cloud, where total distance of point moving paths (PMPs) should be the shortest.
Ranked #1 on
Point Cloud Completion
on Completion3D
Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer
Our insight into the detailed geometry is to introduce a skip-transformer in the SPD to learn the point splitting patterns that can best fit the local regions.
Ranked #5 on
Point Cloud Completion
on ShapeNet
Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Results
Based on the MVP dataset, this paper reports methods and results in the Multi-View Partial Point Cloud Challenge 2021 on Completion and Registration.
KTNet: Knowledge Transfer for Unpaired 3D Shape Completion
The student network takes the incomplete one as input and restores the corresponding complete shape.
SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer
However, previous methods usually suffered from discrete nature of point cloud and unstructured prediction of points in local regions, which makes it hard to reveal fine local geometric details on the complete shape.
Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projection Matching
Our method pushes the neural network to generate a 3D point cloud whose 2D projections match the irregular point supervision from different view angles.
Hierarchical View Predictor: Unsupervised 3D Global Feature Learning through Hierarchical Prediction among Unordered Views
To mine highly discriminative information from unordered views, HVP performs a novel hierarchical view prediction over a view pair, and aggregates the knowledge learned from the predictions in all view pairs into a global feature.
Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding
We provide a comprehensive evaluation in experiments, which shows that our model with the learned bidirectional geometry correspondence outperforms state-of-the-art unpaired completion methods.
Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projections Matching
Our method pushes the neural network to generate a 3D point cloud whose 2D projections match the irregular point supervision from different view angles.
SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine Reconstruction with Self-Projection Optimization
The task of point cloud upsampling aims to acquire dense and uniform point sets from sparse and irregular point sets.
PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths
As a result, the network learns a strict and unique correspondence on point-level, which can capture the detailed topology and structure relationships between the incomplete shape and the complete target, and thus improves the quality of the predicted complete shape.
Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces
Specifically, we train a neural network to pull query 3D locations to their closest points on the surface using the predicted signed distance values and the gradient at the query locations, both of which are computed by the network itself.
DRWR: A Differentiable Renderer without Rendering for Unsupervised 3D Structure Learning from Silhouette Images
To optimize 3D shape parameters, current renderers rely on pixel-wise losses between rendered images of 3D reconstructions and ground truth images from corresponding viewpoints.
Fine-Grained 3D Shape Classification with Hierarchical Part-View Attentions
According to our experiments under this fine-grained dataset, we find that state-of-the-art methods are significantly limited by the small variance among subcategories in the same category.
Point Cloud Completion by Skip-attention Network with Hierarchical Folding
Point cloud completion aims to infer the complete geometries for missing regions of 3D objects from incomplete ones.
LRC-Net: Learning Discriminative Features on Point Clouds by Encoding Local Region Contexts
However, due to the irregularity and sparsity in sampled point clouds, it is hard to encode the fine-grained geometry of local regions and their spatial relationships when only using the fixed-size filters and individual local feature integration, which limit the ability to learn discriminative features.
SeqXY2SeqZ: Structure Learning for 3D Shapes by Sequentially Predicting 1D Occupancy Segments From 2D Coordinates
To avoid dense and irregular sampling in 3D, we propose to represent shapes using 2D functions, where the output of the function at each 2D location is a sequence of line segments inside the shape.
Fast Low-rank Metric Learning for Large-scale and High-dimensional Data
Low-rank metric learning aims to learn better discrimination of data subject to low-rank constraints.
Point2SpatialCapsule: Aggregating Features and Spatial Relationships of Local Regions on Point Clouds using Spatial-aware Capsules
Compared to the previous capsule network based methods, the feature routing on the spatial-aware capsules can learn more discriminative spatial relationships among local regions for point clouds, which establishes a direct mapping between log priors and the spatial locations through feature clusters.
L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attention
Specifically, L2G-AE employs an encoder to encode the geometry information of multiple scales in a local region at the same time.
ShapeCaptioner: Generative Caption Network for 3D Shapes by Learning a Mapping from Parts Detected in Multiple Views to Sentences
Specifically, ShapeCaptioner aggregates the parts detected in multiple colored views using our novel part class specific aggregation to represent a 3D shape, and then, employs a sequence to sequence model to generate the caption.
Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction
To resolve this issue, we propose MAP-VAE to enable the learning of global and local geometry by jointly leveraging global and local self-supervision.
Ranked #16 on
3D Point Cloud Linear Classification
on ModelNet40
3D Point Cloud Linear Classification
Unsupervised 3D Point Cloud Linear Evaluation
Parts4Feature: Learning 3D Global Features from Generally Semantic Parts in Multiple Views
In contrast, we propose a deep neural network, called Parts4Feature, to learn 3D global features from part-level information in multiple views.
3DViewGraph: Learning Global Features for 3D Shapes from A Graph of Unordered Views with Attention
Then, the content and spatial information of each pair of view nodes are encoded by a novel spatial pattern correlation, where the correlation is computed among latent semantic patterns.
Adversarial Cross-Modal Retrieval via Learning and Transferring Single-Modal Similarities
Cross-modal retrieval aims to retrieve relevant data across different modalities (e. g., texts vs. images).
Y^2Seq2Seq: Cross-Modal Representation Learning for 3D Shape and Text by Joint Reconstruction and Prediction of View and Word Sequences
A recent method employs 3D voxels to represent 3D shapes, but this limits the approach to low resolutions due to the computational cost caused by the cubic complexity of 3D voxels.
View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictions
Intuitively, this memory enables the system to aggregate information that is useful to better solve the view inter-prediction tasks for each shape, and to leverage the memory as a view-independent shape representation.
Ranked #14 on
3D Point Cloud Linear Classification
on ModelNet40
3D Point Cloud Linear Classification
Representation Learning
Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network
However, it is hard to capture fine-grained contextual information in hand-crafted or explicit manners, such as the correlation between different areas in a local region, which limits the discriminative ability of learned features.
Ranked #49 on
3D Part Segmentation
on ShapeNet-Part
