- Convolutional Neural Networks on Surfaces via Seamless Toric Covers
- Learning to Infer Graphics Programs from Hand-Drawn Images
- ComplementMe: Weakly-Supervised Component Suggestions for 3D Modeling
- High Fidelity Semantic Shape Completion for Point Clouds using Latent Optimization
- Parsing Geometry Using Structure-Aware Shape Templates
- CompoNet: Learning to Generate the Unseen by Part Synthesis and Composition
- Primitive-based 3D Building Modeling, Sensor Simulation, and Estimation
- AdaCoSeg: Adaptive Shape Co-Segmentation with Group Consistency Loss
- Unpaired Point Cloud Completion on Real Scans using Adversarial Training
- Recovery of Superquadrics from Range Images using Deep Learning: A Preliminary Study
- Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era
- Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds
- PRS-Net: Planar Reflective Symmetry Detection Net for 3D Models
- NASA: Neural Articulated Shape Approximation
- 3D-GMNet: Single-View 3D Shape Recovery as A Gaussian Mixture
- Multimodal Shape Completion via Conditional Generative Adversarial Networks
- DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares
- ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds
- DualSDF: Semantic Shape Manipulation using a Two-Level Representation
- A Simple and Scalable Shape Representation for 3D Reconstruction
- Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learning
- UCLID-Net: Single View Reconstruction in Object Space
- MeshSDF: Differentiable Iso-Surface Extraction
- ShapeFlow: Learnable Deformations Among 3D Shapes
- UCSG-NET - Unsupervised Discovering of Constructive Solid Geometry Tree
- Detail Preserved Point Cloud Completion via Separated Feature Aggregation
- PIE-NET: Parametric Inference of Point Cloud Edges
- Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction
- Neural Sparse Voxel Fields
- KAPLAN: A 3D Point Descriptor for Shape Completion
- Self-Supervised Learning of Point Clouds via Orientation Estimation
- Point Cloud Completion by Learning Shape Priors
- COALESCE: Component Assembly by Learning to Synthesize Connections
- CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations
- LPMNet: Latent Part Modification and Generation for 3D Point Clouds
- DSM-Net: Disentangled Structured Mesh Net for Controllable Generation of Fine Geometry
- SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces from RGB Images
- Learning Gradient Fields for Shape Generation
- Weakly-supervised 3D Shape Completion in the Wild
- CAD-PU: A Curvature-Adaptive Deep Learning Solution for Point Set Upsampling
- Implicit Feature Networks for Texture Completion from Partial 3D Data
- Overfit Neural Networks as a Compact Shape Representation
- TM-NET: Deep Generative Networks for Textured Meshes
- Better Patch Stitching for Parametric Surface Reconstruction
- Skeleton-bridged Point Completion: From Global Inference to Local Adjustment
- Conclave: secure multi-party computation on big data
- Learning Occupancy Function from Point Clouds for Surface Reconstruction
- Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence
- Neural Unsigned Distance Fields for Implicit Function Learning
- Dynamic Plane Convolutional Occupancy Networks
- Learning to Infer Shape Programs Using Latent Execution Self Training
- Deep Implicit Templates for 3D Shape Representation
- Efficient and Flexible Deformation Representation for Data-Driven Surface Modeling
- Quaternion Equivariant Capsule Networks for 3D Point Clouds
- Ladybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetry
- CoReNet: Coherent 3D scene reconstruction from a single RGB image
- Intrinsic Point Cloud Interpolation via Dual Latent Space Navigation
- LIMP: Learning Latent Shape Representations with Metric Preservation Priors
- SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification
- Weakly-supervised 3D Shape Completion in the Wild
- GSIR: Generalizable 3D Shape Interpretation and Reconstruction
- DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction
- Discrete Point Flow Networks for Efficient Point Cloud Generation
- BAE-NET: Branched Autoencoder for Shape Co-Segmentation
- 3D ShapeNets: A Deep Representation for Volumetric Shapes
- Neural Implicit Embedding for Point Cloud Analysis
- Unsupervised Deep Learning for Primitive-Based Shape Abstraction
- Global-to-Local Generative Model for 3D Shapes
- Learning Generative Models of Shape Handles
- Learning Shape Templates with Structured Implicit Functions
- Local Deep Implicit Functions for 3D Shape
- Aligning 3D Models to RGB-D Images of Cluttered Scenes
- Unsupervised Primitive Discovery for Improved 3D Generative Modeling
- Topology-Aware Single-Image 3D Shape Reconstruction
- Learning 3D Mesh Segmentation and Labeling
- Interpolated Convolutional Networks for 3D Point Cloud Understanding
- DiscoNet: Shapes Learning on Disconnected Manifolds for 3D Editing
- SSRNet: Scalable 3D Surface Reconstruction Network
- Geometric deep learning on graphs and manifolds using mixture model CNNs
- Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations
- Convolutional-Recursive Deep Learning for 3D Object Classification
- PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
- InverseCSG: Automatic Conversion of 3D Models to CSG Trees
- PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations
- Constructive Solid Geometry for Polyhedral Objects
- A Benchmark for 3D Mesh Segmentation
- Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images
- A Scalable Active Framework for Region Annotation in 3D Shape Collections
- Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image
- PointWeb: Enhancing Local Neighborhood Features for Point Cloud Processing
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
- FroDO: From Detections to 3D Objects
- PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization
- The shape variational autoencoder: A deep generative model of part-segmented 3D objects
- 3D Shape Segmentation with Projective Convolutional Networks
- PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
- Deep Parametric Shape Predictions using Distance Fields
- Active Co-Analysis of a Set of Shapes
- Structure-Aware Shape Processing
- Multi-view Convolutional Neural Networks for 3D Shape Recognition
- Variational Autoencoders for Deforming 3D Mesh Models
- VoxNet: A 3D Convolutional Neural Network for Real-Time Object Recognition
- Symmetry Hierarchy of Man-Made Objects
- Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation
- Learning to Generate 3D Training Data
- Physical Primitive Decomposition
manjunath5496 / deep-geometry-learning-papers Goto Github PK
View Code? Open in Web Editor NEW"Just as all things speak about God to those that know Him, and reveal Him to those that love Him, they also hide Him from all those that neither seek nor know Him."― Blaise Pascal