SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.08557 · ICCV · 2021

DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoders

Nicola Conci, Nicola Garau, Niccolò Bisagno, Piotr Bródka

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

Figure 1: [Better seen in color]. Overview of the proposed solution. Two different views of the same subject are shown for each image: (a) 2D/3D Human Pose Estimation (HPE) and (b) 3D Human Mesh Recovery (HMR) methods achieve good accuracy on the front-view (second row). Changing the viewpoint turns into performance degradation (first row). Our method (c) promotes viewpoint equivariance, showing good results in both the RGB and depth domains.

For agents

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

get_harvested_code_for_paper("2108.08557")
get_code_for_paper("2108.08557")
have("2108.08557")

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

curl https://syntology.ai/api/ran/2108.08557.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.08557.svg)](https://syntology.ai/paper/2108.08557)

Connect an agent — have() is free.