Articulation-Aware Canonical Surface Mapping

Nilesh Kulkarni, Abhinav Gupta, David F. Fouhey, Shubham Tulsiani

Paper Project Page

Requirements

Python 2.7
PyTorch tested with 1.2.0 and works with 1.3.0 too.
cuda 9.2

For setup and installation refer to docs/install.md instructions.

Setup Evlaution and Training

For ease of acess we provide python scripts that can generate slurm scripts that can be used to generate the results in the paper.

Downloading pre-trained model and annotations. Follow setup instructions here
Training from scratch. Follow setup instructions here

Citation

If you find the code useful for your research, please consider citing:-

@inproceedings{kulkarni2020articulation,
  title={Articulation-aware Canonical Surface Mapping},
  author={Kulkarni, Nilesh and Gupta, Abhinav and Fouhey, David F and Tulsiani, Shubham},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={452--461},
  year={2020}
}

Future Release

Python 3.6
PyTorch 1.5
PyTorch3D

Official implementation of "Articulation Aware Canonical Surface Mapping"

Related tags

Overview

Articulation-Aware Canonical Surface Mapping

Requirements

Setup Evlaution and Training

Citation

Future Release

Owner

Nilesh Kulkarni

This code implements constituency parse tree aggregation

PyTorch Implementation of our paper Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation

Code for the ECCV2020 paper "A Differentiable Recurrent Surface for Asynchronous Event-Based Data"

PGPortfolio: Policy Gradient Portfolio, the source code of "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem"(https://arxiv.org/pdf/1706.10059.pdf).

Implementation of the paper All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training

This is the repo for Uncertainty Quantification 360 Toolkit.

A project for developing transformer-based models for clinical relation extraction

A Partition Filter Network for Joint Entity and Relation Extraction EMNLP 2021

Code Release for Learning to Adapt to Evolving Domains

Research - dataset and code for 2016 paper Learning a Driving Simulator

RoboDesk A Multi-Task Reinforcement Learning Benchmark

A graph neural network (GNN) model to predict protein-protein interactions (PPI) with no sample features

LEAP: Learning Articulated Occupancy of People

An implementation for `Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction`

Code for the ICCV'21 paper "Context-aware Scene Graph Generation with Seq2Seq Transformers"

Implementation of EMNLP 2017 Paper "Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog" using PyTorch and ParlAI

Pre-training of Graph Augmented Transformers for Medication Recommendation

Chainer Implementation of Semantic Segmentation using Adversarial Networks

Code for BMVC2021 "MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation"

Analysis of rationale selection in neural rationale models