SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1503.03167 · 2015

Deep Convolutional Inverse Graphics Network

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

This paper presents the Deep Convolution Inverse Graphics Network (DC-IGN), a model that learns an interpretable representation of images. This representation is disentangled with respect to transformations such as out-of-plane rotations and lighting variations. The DC-IGN model is composed of multiple layers of convolution and de-convolution operators and is trained using the Stochastic Gradient Variational Bayes (SGVB) algorithm. We propose a training procedure to encourage neurons in the graphics code layer to represent a specific transformation (e.g. pose or light). Given a single input image, our model can generate new images of the same object with variations in pose and lighting. We present qualitative and quantitative results of the model's efficacy at learning a 3D rendering engine.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1503.03167")
get_code_for_paper("1503.03167")
have("1503.03167")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1503.03167.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1503.03167.svg)](https://syntology.ai/paper/1503.03167)

Connect an agent — have() is free.