SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.15380 · CVPR · 2023

Hi4D: 4D Instance Segmentation of Close Human Interaction

Otmar Hilliges, Jie Song, Chen Guo, Manuel Kaufmann, Juan Zarate, Yifei Yin

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

Meshes with Contact Annotations (C) Instance Segmentation Masks in 2D and 3D (D) Parametric Body Models with Contact Annotations Figure 1. Method and dataset. We propose a method that leverages personalized human avatars to segment merged (A) 4D textured scans of multiple closely interacting humans. Based on the (B) instance meshes (with vertex-level contact annotations) we obtained in 3D space, we further provide (C) instance segmentation masks in 2D and 3D, (D) registered parametric body models with contact annotations.

For agents

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

get_harvested_code_for_paper("2303.15380")
get_code_for_paper("2303.15380")
have("2303.15380")

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

curl https://syntology.ai/api/ran/2303.15380.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.15380.svg)](https://syntology.ai/paper/2303.15380)

Connect an agent — have() is free.