This repository contains the code release for the SIGGRAPH 2020 paper "One Shot 3D Photography"
This repository contains code for our publication "Occupancy Anticipation for Efficient Exploration and Navigation" in ECCV 2020.
Code accompanying EGO-TOPO: Environment Affordances from Egocentric Video (CVPR 2020)
Project for the paper "A Scalable Approach to Control Diverse Behaviors for Physically Simulated Characters"
Learning latent representations of registered meshes is useful for many 3D tasks. Techniques have recently shifted to neural mesh autoencoders. Although they demonstrate higher precision than traditional methods, they remain unable to capture fine-grained deformations. Furthermore, these methods can only be applied to a template-specific surface mesh, and is not applicable to more general meshes, like tetrahedrons and non-manifold meshes. While more general graph convolution methods can be employed, they lack performance in reconstruction precision and require higher memory usage. In this paper, we propose a non-template-specific fully convolutional mesh autoencoder for arbitrary registered mesh data. It is enabled by our novel convolution and (un)pooling operators learned with globally shared weights and locally varying coefficients which can efficiently capture the spatially varying contents presented by irregular mesh connections. Our model outperforms state-of-the-art methods on reconstruction accuracy. In addition, the latent codes of our network are fully localized thanks to the fully convolutional structure, and thus have much higher interpolation capability than many traditional 3D mesh generation models.
Official PyTorch implementation of "DeepHandMesh: A Weakly-Supervised Deep Encoder-Decoder Framework for High-Fidelity Hand Mesh Modeling," ECCV 2020
Official PyTorch implementation of "InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image", ECCV 2020
A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator
Code to support the paper "Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets"
Dachshund is a graph mining library written in Rust. It provides high performance data structures for multiple kinds of graphs, from simple undirected graphs to typed hypergraphs. Dachshund also provides algorithms for common tasks for graph mining and analysis, ranging from shortest paths to graph spectral analysis.
Code for "Learning Affordance Landscapes for Interaction Exploration in 3D Environments" (NeurIPS 20)
The paper studies the problem of learning to recognize a new class of objects from a very small number of labeled images. This is called few-shot learning. Previous work in the literature focused on designing new algorithms that allow to learn to generalize to new unseen classes.In this work, we consider the impact of the dataset that we train on, and experiment with some dataset manipulations to see which trade-offs are important in the design of a dataset aimed at few-shot learning.
Code for "Joint Policy Search for Collaborative Multi-agent Incomplete Information Games"
The release codes of LA-MCTS with its application to Neural Architecture Search.
A code implementation for our arXiv paper "Multi-agent Adhoc Team Play using Decompositional Q function"
Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild
A first-of-its-kind acoustic simulation platform for audio-visual embodied AI research. It supports training and evaluating multiple tasks and applications.
