nileshkulkarni / Csm

Code release for "Canonical Surface Mapping via Geometric Cycle Consistency"

Projects that are alternatives of or similar to Csm

Go Tsne
t-Distributed Stochastic Neighbor Embedding (t-SNE) in Go
Stars: ✭ 153 (-1.92%)
Mutual labels:  3d, unsupervised-learning
Unsup3d
(CVPR'20 Oral) Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild
Stars: ✭ 905 (+480.13%)
Mutual labels:  3d, unsupervised-learning
Spherical Text Embedding
[NeurIPS 2019] Spherical Text Embedding
Stars: ✭ 143 (-8.33%)
Mutual labels:  unsupervised-learning
Xbimgeometry
XbimGeometry contains the CLR interop libraries and the c++ engine used to compute the 3D geometry of models.
Stars: ✭ 152 (-2.56%)
Mutual labels:  3d
Awesome Sentence Embedding
A curated list of pretrained sentence and word embedding models
Stars: ✭ 1,973 (+1164.74%)
Mutual labels:  unsupervised-learning
3d Force Graph
3D force-directed graph component using ThreeJS/WebGL
Stars: ✭ 2,386 (+1429.49%)
Mutual labels:  3d
Wechart
Create all the [ch]arts by cax or three.js - Cax 和 three.js 创造一切图[表]
Stars: ✭ 152 (-2.56%)
Mutual labels:  3d
Synthesize3dviadepthorsil
[CVPR 2017] Generation and reconstruction of 3D shapes via modeling multi-view depth maps or silhouettes
Stars: ✭ 141 (-9.62%)
Mutual labels:  3d
Cosmonium
3D astronomy and space exploration program.
Stars: ✭ 153 (-1.92%)
Mutual labels:  3d
Stylisticpoetry
Codes for Stylistic Chinese Poetry Generation via Unsupervised Style Disentanglement (EMNLP 2018)
Stars: ✭ 148 (-5.13%)
Mutual labels:  unsupervised-learning
Py3dtiles
⚠️ Project migrated to : https://gitlab.com/Oslandia/py3dtiles ⚠️
Stars: ✭ 152 (-2.56%)
Mutual labels:  3d
Jeelizfacefilter
Javascript/WebGL lightweight face tracking library designed for augmented reality webcam filters. Features : multiple faces detection, rotation, mouth opening. Various integration examples are provided (Three.js, Babylon.js, FaceSwap, Canvas2D, CSS3D...).
Stars: ✭ 2,042 (+1208.97%)
Mutual labels:  3d
Andromeda
This is a WebGL recreation of the popular music video Gorillaz - Andromeda.
Stars: ✭ 145 (-7.05%)
Mutual labels:  3d
Graphwavemachine
A scalable implementation of "Learning Structural Node Embeddings Via Diffusion Wavelets (KDD 2018)".
Stars: ✭ 151 (-3.21%)
Mutual labels:  unsupervised-learning
D3feat
[TensorFlow] Implementation of CVPR'20 oral paper - D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features https://arxiv.org/abs/2003.03164
Stars: ✭ 143 (-8.33%)
Mutual labels:  3d
Flame pytorch
This is a implementation of the 3D FLAME model in PyTorch
Stars: ✭ 153 (-1.92%)
Mutual labels:  3d
Spatiotemporalsegmentation
4D Spatio-Temporal Semantic Segmentation on a 3D video (a sequence of 3D scans)
Stars: ✭ 141 (-9.62%)
Mutual labels:  3d
Voxel Core
Voxel plugin for the Godot game engine!
Stars: ✭ 148 (-5.13%)
Mutual labels:  3d
Lr Gan.pytorch
Pytorch code for our ICLR 2017 paper "Layered-Recursive GAN for image generation"
Stars: ✭ 145 (-7.05%)
Mutual labels:  unsupervised-learning
Shapegan
Generative Adversarial Networks and Autoencoders for 3D Shapes
Stars: ✭ 151 (-3.21%)
Mutual labels:  3d

Canonical Surface Mapping via Geometric Cycle Consistency

Nilesh Kulkarni, Abhinav Gupta*, Shubham Tulsiani*

Project Page

teaser

Requirements

  • Python 2.7
  • PyTorch 0.4

Follow-up work on Articulation-aware Canonical Surface Mapping

Please checkout the follow-up work here. We show results on over 10 categories.

Installation

Following instructions here

Training

Please see csm/docs/training.md

Testing

Please see csm/docs/testing.md

Ablation Analysis

Please see csm/docs/ablation.md

Citation

If you use this code for your research, please consider citing:

@article{kulkarni2019csm,
  title={Canonical Surface Mapping via Geometric Cycle Consistency},
  author={Kulkarni, Nilesh
  and Gupta, Abhinav
  and Tulsiani, Shubham},
  journal={International Conference on Computer Vision (ICCV)}
  year={2019}
}

Acknowledgements

Parts of this code were borrowed from CMR.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].