Pop-Out Motion: 3D-Aware Image Deformation via Learning the Shape Laplacian (CVPR 2022) Jihyun Lee*, Minhyuk Sung*, Hyunjin Kim, Tae-Kyun (T-K) Kim (*: equal contributions) [Paper] [Video] We present a framework that can deform an object in a 2D image as it exists in 3D space. While our method leverages 2D-to-3D reconstruction, we argue that reconstruction is not sufficient for realistic deformations due to the vulnerability to topological errors. Thus, we propose to take a supervised learning-based approach to predict the […]

Code repository for the paper “Tracking People by Predicting 3D Appearance, Location & Pose”. Jathushan Rajasegaran, Georgios Pavlakos, Angjoo Kanazawa, Jitendra Malik. This code repository provides a code implementation for our paper PHALP, with installation, preparing datasets, and evaluating on datasets, and a demo code to run on any youtube videos. Abstract : In this paper, we present an approach for tracking people in monocular videos, by predicting their future 3D representations. To achieve this, we first lift people to […]

Turning pixels into virtual points for multimodal 3D object detection. Multimodal Virtual Point 3D Detection,Tianwei Yin, Xingyi Zhou, Philipp Krähenbühl,arXiv technical report (arXiv 2111.06881 ) @article{yin2021multimodal, title={Multimodal Virtual Point 3D Detection}, author={Yin, Tianwei and Zhou, Xingyi and Kr{“a}henb{“u}hl, Philipp}, journal={NeurIPS}, year={2021}, } Contact Any questions or suggestions are welcome! Tianwei Yin [email protected]Xingyi Zhou [email protected] Abstract Lidar-based sensing drives current autonomous vehicles. Despite rapid progress,    

Python 3D finite element code This python code allows for solving 3D structural problems using the finite element method. New features will be added over time. This code has NOT been validated on reference cases yet. Requirements and dependencies Current features: Meshes Tetrahedral mesh generation from a set of points using scipy.spatial.Delaunay 4-node tetrahedral (Tet4), 6-node prism (Prism6), 8-node brick (Brick8) elements support Support for meshes containing different types of elements, possibly of different orders Materials Linear isotropic elastic materials […]

Shape Matching of Real 3D Object Data to Synthetic 3D CADs (3DV project @ ETHZ) Group Member: Yue Pan, Yuanwen Yue, Bingxin Ke, Yujie He Supervisor: Dr. Iro Armeni, Shengyu Huang report | presentation | demo Data preparation and preprocessing TBA How to use Train the model, monitor it via wandb cd ./src # configure the path and parameters in train_scannet.sh bash train_scannet.sh Evaluate the model on ScanNet or 2D3DS dataset # configure the    

Python solver for a rubik’s cube This program makes a 3D representation of a rubiks cube and solves it step by step. Usage To use this program you need to execute the following commands For 3D visualizations: python visualizer.py For statistics: python stats.py Requirements To use this program you need to install python 3.8.10 or later (although it will probably work on python 3.7) You will also need a recent version of numpy and vpython 7 or later, those can […]

WobblyStitcher A scalable implementation of WobblyStitcher Dependencies $ python -m pip install numpy scipy scikit-image Visualization ImageJ Getting started Generate four files with fake input $ (cd tool && make) $ ./tool/gen -n 200 200 200 -o 10 10 $ ls -1 *.raw 200x200x200le.00.00.raw 200x200x200le.00.01.raw 200x200x200le.01.00.raw 200x200x200le.01.01.raw stitch $ python3 main.py main.py: processes = 4 47% 390x390x200le.raw Open 390x390x200le.raw in ImageJ. References Kirst, C., Skriabine, S., Vieites-Prado, A., Topilko, T., Bertin,P., Gerschenfeld, G., … & Renier, N. (2020). Mapping the […]

3D_adapt_auto_driving This paper has been accpeted by Conference on Computer Vision and Pattern Recognition (CVPR) 2020. Train in Germany, Test in The USA: Making 3D Object Detectors Generalize by Yan Wang*, Xiangyu Chen*, Yurong You, Li Erran, Bharath Hariharan, Mark Campbell, Kilian Q. Weinberger, Wei-Lun Chao* Dependencies Usage Prepare Datasets (Jupyter notebook) We develop our method on these datasets: Configure dataset_path in config_path.py. Raw datasets will be organized as the following structure: dataset_path/ | kitti/ # KITTI object detection 3D […]

groomed_nms GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection CVPR 2021 Abhinav Kumar, Garrick Brazil, Xiaoming Liu project, supp, 5min_talk, slides, demo, poster, arxiv This code is based on Kinematic-3D, such that the setup/organization is very similar. A few of the implementations, such as classical NMS, are based on Caffe. References Please cite the following paper if you find this repository useful: @inproceedings{kumar2021groomed, title={{GrooMeD-NMS}: Grouped Mathematically Differentiable NMS for Monocular {$3$D} Object Detection}, author={Kumar, Abhinav and Brazil, Garrick […]