SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.13087 · 2021

DCL: Differential Contrastive Learning for Geometry-Aware Depth Synthesis

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

We describe a method for unpaired realistic depth synthesis that learns diverse variations from the real-world depth scans and ensures geometric consistency between the synthetic and synthesized depth. The synthesized realistic depth can then be used to train task-specific networks facilitating label transfer from the synthetic domain. Unlike existing image synthesis pipelines, where geometries are mostly ignored, we treat geometries carried by the depth scans based on their own existence. We propose differential contrastive learning that explicitly enforces the underlying geometric properties to be invariant regarding the real variations been learned. The resulting depth synthesis method is task-agnostic, and we demonstrate the effectiveness of the proposed synthesis method by extensive evaluations on real-world geometric reasoning tasks. The networks trained with the depth synthesized by our method consistently achieve better performance across a wide range of tasks than state of the art, and can even surpass the networks supervised with full real-world annotations when slightly fine-tuned, showing good transferability.

For agents

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

get_harvested_code_for_paper("2107.13087")
get_code_for_paper("2107.13087")
have("2107.13087")

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

curl https://syntology.ai/api/ran/2107.13087.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.13087.svg)](https://syntology.ai/paper/2107.13087)

Connect an agent — have() is free.