SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2001.03343 · 2020

RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 16 functions out of this paper's own repositories and ran 11 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
Banconxuan/RTM3D canonical 3 of 3
maudzung/RTM3D pwc_unofficial 8 of 13
FunctionStatusWhere it lives
compute_bin_loss Ran maudzung/RTM3D/src/losses/losses.py
code served (permissive licence) · get_code("65d7a40d70c53ed9")
compute_box_3d Ran maudzung/RTM3D/src/data_process/kitti_data_utils.py
code served (permissive licence) · get_code("480409d49471d790")
compute_res_loss Ran maudzung/RTM3D/src/losses/losses.py
code served (permissive licence) · get_code("7df13fb9e54d592b")
conv3x3 Ran maudzung/RTM3D/src/models/fpn_resnet.py
code served (permissive licence) · get_code("fac5364e2f53c6db")
get_alpha Ran maudzung/RTM3D/src/utils/evaluation_utils.py
code served (permissive licence) · get_code("f1dbc18e2080c03e")
get_num_parameters Ran maudzung/RTM3D/src/models/model_utils.py
code served (permissive licence) · get_code("7bf982cd2568c239")
get_pred_depth Ran maudzung/RTM3D/src/utils/evaluation_utils.py
code served (permissive licence) · get_code("80a8f885a0f16ba6")
read_clib Ran Banconxuan/RTM3D/src/tools/kitti.py
code served (permissive licence) · get_code("de329cc98c9f786d")
read_clib0 Ran Banconxuan/RTM3D/src/tools/kitti.py
code served (permissive licence) · get_code("9daaaaf61eccf5c9")
read_clib3 Ran Banconxuan/RTM3D/src/tools/kitti.py
code served (permissive licence) · get_code("3252b60b8cec216a")
roty Ran maudzung/RTM3D/src/data_process/kitti_data_utils.py
code served (permissive licence) · get_code("f83dc76e5a02776d")
compute_rot_loss Not yet run maudzung/RTM3D/src/losses/losses.py
code served (permissive licence) · get_code("9d749234d255406c")
get_pose_net Not yet run maudzung/RTM3D/src/models/fpn_resnet.py
code served (permissive licence) · get_code("53da3f0e2c240363")
get_pose_net Not yet run maudzung/RTM3D/src/models/resnet.py
code served (permissive licence) · get_code("da3cdf1c124aa18f")
make_data_parallel Not yet run maudzung/RTM3D/src/models/model_utils.py
code served (permissive licence) · get_code("cbb1e79cf3f516f7")
rtm3d_decode Not yet run maudzung/RTM3D/src/utils/evaluation_utils.py
code served (permissive licence) · get_code("296d581d9aac4538")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this work, we propose an efficient and accurate monocular 3D detection framework in single shot. Most successful 3D detectors take the projection constraint from the 3D bounding box to the 2D box as an important component. Four edges of a 2D box provide only four constraints and the performance deteriorates dramatically with the small error of the 2D detector. Different from these approaches, our method predicts the nine perspective keypoints of a 3D bounding box in image space, and then utilize the geometric relationship of 3D and 2D perspectives to recover the dimension, location, and orientation in 3D space. In this method, the properties of the object can be predicted stably even when the estimation of keypoints is very noisy, which enables us to obtain fast detection speed with a small architecture. Training our method only uses the 3D properties of the object without the need for external networks or supervision data. Our method is the first real-time system for monocular image 3D detection while achieves state-of-the-art performance on the KITTI benchmark. Code will be released at https://github.com/Banconxuan/RTM3D.

For agents

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

get_harvested_code_for_paper("2001.03343")
get_code_for_paper("2001.03343")
have("2001.03343")

Connect an agent — have() is free.