SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1904.01690 · 2019

Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 2 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
copy not recorded — 2 of 3
FunctionStatusWhere it lives
create_corners Ran this paper's copy was not recorded; identical code first harvested from ZhixinLai/3D-detection-with-monocular-RGB-image
pointer only · get_code("ddd1724d77acef32")
rotation_matrix Ran this paper's copy was not recorded; identical code first harvested from ZhixinLai/3D-detection-with-monocular-RGB-image
pointer only · get_code("502bf1a47f6d2dbe")
calc_location Not yet run this paper's copy was not recorded; identical code first harvested from ZhixinLai/3D-detection-with-monocular-RGB-image
pointer only · get_code("e309a2bcb8e15116")

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 present MonoPSR, a monocular 3D object detection method that leverages proposals and shape reconstruction. First, using the fundamental relations of a pinhole camera model, detections from a mature 2D object detector are used to generate a 3D proposal per object in a scene. The 3D location of these proposals prove to be quite accurate, which greatly reduces the difficulty of regressing the final 3D bounding box detection. Simultaneously, a point cloud is predicted in an object centered coordinate system to learn local scale and shape information. However, the key challenge is how to exploit shape information to guide 3D localization. As such, we devise aggregate losses, including a novel projection alignment loss, to jointly optimize these tasks in the neural network to improve 3D localization accuracy. We validate our method on the KITTI benchmark where we set new state-of-the-art results among published monocular methods, including the harder pedestrian and cyclist classes, while maintaining efficient run-time.

For agents

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

get_harvested_code_for_paper("1904.01690")
get_code_for_paper("1904.01690")
have("1904.01690")

Connect an agent — have() is free.