SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.06072 · ICCV · 2023

Out-of-Distribution Detection for Monocular Depth Estimation

Vasileios Belagiannis, Adrian Holzbock, Julia Hornauer

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
jhornauer/mde_ood canonical 3 of 6
FunctionStatusWhere it lives
get_metrics_ood Ran jhornauer/mde_ood/monodepth2_ood/evaluate_ood_kitti.py
code served (permissive licence) · get_code("50b44a52da35bada")
h5_loader Ran jhornauer/mde_ood/monodepth2_ood/id_datasets/nyu_dataset.py
code served (permissive licence) · get_code("c76f77ddf75da739")
rgb_loader Ran jhornauer/mde_ood/monodepth2_ood/ood_datasets/india_driving_dataset.py
code served (permissive licence) · get_code("4c52fefa3528c764")
adjust_brightness Not yet run jhornauer/mde_ood/monodepth2_ood/id_datasets/transforms.py
code served (permissive licence) · get_code("89384966174d44ff")
adjust_contrast Not yet run jhornauer/mde_ood/monodepth2_ood/id_datasets/transforms.py
code served (permissive licence) · get_code("8bee1c36802f8893")
adjust_saturation Not yet run jhornauer/mde_ood/monodepth2_ood/id_datasets/transforms.py
code served (permissive licence) · get_code("cff3e6cd63597420")

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: Depth prediction (center) and absolute relative error (right) from a model trained on KITTI for images from KITTI (top, left; in-distribution: ID) and virtual KITTI (bottom, left; out-of-distribution: OOD): The depth prediction for virtual KITTI, which is not represented in the training distribution, is incorrect; therefore, the error is too high.

For agents

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

get_harvested_code_for_paper("2308.06072")
get_code_for_paper("2308.06072")
have("2308.06072")

Connect an agent — have() is free.