SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.03676 · 2022

IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertainty

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

Single image surface normal estimation and depth estimation are closely related problems as the former can be calculated from the latter. However, the surface normals computed from the output of depth estimation methods are significantly less accurate than the surface normals directly estimated by networks. To reduce such discrepancy, we introduce a novel framework that uses surface normal and its uncertainty to recurrently refine the predicted depth-map. The depth of each pixel can be propagated to a query pixel, using the predicted surface normal as guidance. We thus formulate depth refinement as a classification of choosing the neighboring pixel to propagate from. Then, by propagating to sub-pixel points, we upsample the refined, low-resolution output. The proposed method shows state-of-the-art performance on NYUv2 and iBims-1 - both in terms of depth and normal. Our refinement module can also be attached to the existing depth estimation methods to improve their accuracy. We also show that our framework, only trained for depth estimation, can also be used for depth completion. The code is available at https://github.com/baegwangbin/IronDepth.

For agents

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

get_harvested_code_for_paper("2210.03676")
get_code_for_paper("2210.03676")
have("2210.03676")

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

curl https://syntology.ai/api/ran/2210.03676.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.03676.svg)](https://syntology.ai/paper/2210.03676)

Connect an agent — have() is free.