SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.11225 · ICCV · 2021

Pri3D: Can 3D Priors Help 2D Representation Learning?

Saining Xie, Benjamin Graham, Matthias Nießner, Angela Dai, Ji Hou

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: Pri3D leverages 3D priors for downstream 2D image understanding tasks: during pre-training, we incorporate view-invariant and geometric priors from color-geometry information given by RGB-D datasets, imbuing geometric priors into learned features. We show that these 3D-imbued learned features can effectively transfer to improved performance on 2D tasks such as semantic segmentation, object detection, and instance segmentation.

For agents

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

get_harvested_code_for_paper("2104.11225")
get_code_for_paper("2104.11225")
have("2104.11225")

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

curl https://syntology.ai/api/ran/2104.11225.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.11225.svg)](https://syntology.ai/paper/2104.11225)

Connect an agent — have() is free.