JHUVisionLab / multi-modal-regression
Models and Loss functions for our Mixed Classification-Regression framework for 3D Pose Estimation
☆31Updated 6 years ago
Alternatives and similar repositories for multi-modal-regression:
Users that are interested in multi-modal-regression are comparing it to the libraries listed below
- A model-free 6D object pose tracking baseline with ICP and TSDF fusion.☆26Updated 5 years ago
- ☆12Updated 6 years ago
- Code for our work on pose-estimation using template 3D models.☆33Updated 5 years ago
- Deep Directional Statistics: Pose Estimation with Uncertainty Quantification☆22Updated 5 years ago
- Public repository for paper "Finding Your (3D) Center: 3D object detection using a learned loss"☆17Updated 2 years ago
- The code is implemented to show focal loss improvement based on 3D-FCN and VoxelNet for “Focal Loss in 3D Object Detection”.☆75Updated 6 years ago
- Official PyTorch Implementation for "Sequential Forecasting of 100,000 Points", In Submission☆25Updated 5 years ago
- PyTorch implementation to train MortonNet and use it to compute point features. MortonNet is trained in a self-supervised fashion, and th…☆21Updated 5 years ago
- ☆38Updated 5 years ago
- Data-Driven 3D Voxel Patterns for Object Category Recognition☆38Updated 8 years ago
- Inference code and trained networks for Deep Model-Based 6D Pose Refinement in RGB☆51Updated 6 years ago
- Code visualize and evaluate the dataset from "A Framework for Evaluating 6-DOF Object Trackers".☆36Updated 4 years ago
- Discrete Rotation Equivariance for Point Cloud Recognition. ICRA 2019☆23Updated 6 years ago
- Code for "PackNet-SfM: 3D Packing for Self-Supervised Monocular Depth Estimation"☆60Updated 5 years ago
- ☆21Updated 5 years ago
- Learning about RANSAC.☆20Updated 5 years ago
- Code to accompany "Does computer vision matter for action?"☆43Updated 7 months ago
- Monocular depth estimation from a single image☆21Updated 4 years ago
- A novel dense correspondence network☆16Updated 3 years ago
- Unsupervised Training of DepthNet☆60Updated 4 years ago
- Deep 6 DOF Tracking☆35Updated 6 years ago
- An extremely fast RGB-D segmentation network☆26Updated 6 years ago
- Unsupervised Generation of a Viewpoint Annotated Car Dataset from Videos☆19Updated last year
- 3d object detection papers☆23Updated 5 years ago
- ☆15Updated 5 years ago
- Code release for the ICRA 2017 paper "Reconstructing vehicles from a single image: shape priors for road scene understanding"☆39Updated 6 years ago
- Code and data for "Learning Compact Geometric Features"☆41Updated 5 years ago
- Main reference:Handa, A., Whelan, T., Mcdonald, J., & Davison, A. J. (2014). A Benchmark for RGB-D Visual Odometry , 3D Reconstruction an…☆31Updated 8 years ago
- Multi-view Self-supervised 6D Object Pose Prediction☆10Updated 6 years ago
- Implementation of our ECCV 2018 paper "Efficient Semantic Scene Completion Network with Spatial Group Convolution"☆44Updated 5 years ago