Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research
Explore this paper's citation graph
Summary
Kaolin provides efficient implementations of differentiable 3D modules for use in deep learning systems and curates a comprehensive model zoo comprising many state-of-the-art 3D deep learning architectures to serve as a starting point for future research endeavours.
- Type
- preprint
- Published
- 2019-11-12
- Cited by
- 155
- References
- 45
- Access
- Open access
- OpenAlex
- https://openalex.org/W2985388077
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:207863434
Keywords
Deep learning, Computer science, Artificial intelligence, Mathematics education, Psychology
References
- Robobarista: Object Part Based Transfer of Manipulation Trajectories from Crowd-Sourcing in 3D Pointclouds
- A vision-based robotic grasping system using deep learning for 3D object recognition and pose estimation
- Gradient-based learning applied to document recognition
- Natural terrain classification using three‐dimensional ladar data for ground robot mobility
- ShapeNet: An Information-Rich 3D Model Repository
- Real-time 3D scene layout from a single image using Convolutional Neural Networks
- Monocular 3D Object Detection for Autonomous Driving
- 3D Bounding Box Estimation Using Deep Learning and Geometry
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
- A Point Set Generation Network for 3D Object Reconstruction from a Single Image
- Real-Time High Resolution 3D Data on the HoloLens
- Joint 2D-3D-Semantic Data for Indoor Scene Understanding
- ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes
- Applying Deep Learning in Augmented Reality Tracking
- Convolutional neural networks on surfaces via seamless toric covers
- Neural 3D Mesh Renderer
- Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images
- MeshCNN: a network with an edge
- Visual SLAM for Automated Driving: Exploring the Applications of Deep Learning
- Automatic differentiation in PyTorch
Cited by
- Extending Maps with Semantic and Contextual Object Information for Robot Navigation: a Learning-Based Framework Using Visual and Depth Cues
- Extending DeepSDF for automatic 3D shape retrieval and similarity transform estimation.
- Neural subdivision
- Learning Neural Light Transport
- Differentiable Rendering: A Survey
- Pose2RGBD. Generating Depth and RGB images from absolute positions
- Accelerating 3D deep learning with PyTorch3D
- Self-Sampling for Neural Point Cloud Consolidation
- DronePose: Photorealistic UAV-Assistant Dataset Synthesis for 3D Pose Estimation via a Smooth Silhouette Loss
- Interactive Annotation of 3D Object Geometry using 2D Scribbles
- MonoClothCap: Towards Temporally Coherent Clothing Capture from Monocular RGB Video
- Multi-View Consistency Loss for Improved Single-Image 3D Reconstruction of Clothed People
- Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering
- Learning Deformable Tetrahedral Meshes for 3D Reconstruction
- 3D Shape Reconstruction from Vision and Touch
- Cycle-Consistent Generative Rendering for 2D-3D Modality Translation
- Fast geometric learning with symbolic matrices
- RobustPointSet: A Dataset for Benchmarking Robustness of Point Cloud Classifiers
- Object Rearrangement Using Learned Implicit Collision Functions
- Torch-Points3D: A Modular Multi-Task Framework for Reproducible Deep Learning on 3D Point Clouds
Related papers
- Overview of deep learning in medical imaging
- Survey of Machine Learning Applications of Convolutional Neural Networks to Medical Image Analysis
- Exploring Deep Learning for View-Based 3D Model Retrieval
- Deep learning ensemble 2D CNN approach towards the detection of lung cancer
- A Comprehensive Analysis of Machine Learning Techniques in Biomedical Image Processing Using Convolutional Neural Network
- Deep learning model for deep fake face recognition and detection
- Image recognition based on deep learning
- Autokeras Approach: A Robust Automated Deep Learning Network for Diagnosis Disease Cases in Medical Images