SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1903.01864 · 2019

Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 16 functions out of this paper's own repositories and ran 15 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
zhixinwang/frustum-convnet canonical 15 of 16
FunctionStatusWhere it lives
in_hull Ran zhixinwang/frustum-convnet/datasets/data_utils.py
code served (permissive licence) · get_code("aab935d4b7b55c2c")
Conv1d Ran zhixinwang/frustum-convnet/models/common.py
code served (permissive licence) · get_code("df9e498714c411f2")
Conv2d Ran zhixinwang/frustum-convnet/models/common.py
code served (permissive licence) · get_code("ce58b42def83bfb4")
Conv3d Ran zhixinwang/frustum-convnet/models/common.py
code served (permissive licence) · get_code("e0f1f2d3ccac5f2e")
adjust_coord_for_view Ran zhixinwang/frustum-convnet/datasets/check_utils.py
code served (permissive licence) · get_code("3b86dc1730e8d1c1")
center_decode Ran zhixinwang/frustum-convnet/models/box_transform.py
code served (permissive licence) · get_code("f47e771020b20fef")
collate_fn Ran zhixinwang/frustum-convnet/datasets/provider_sample.py
code served (permissive licence) · get_code("0c5c08f1db6108da")
compute_alpha Ran zhixinwang/frustum-convnet/datasets/provider_sample.py
code served (permissive licence) · get_code("8d0c2b6ba5dcbf2d")
extract_pc_in_box3d Ran zhixinwang/frustum-convnet/datasets/data_utils.py
code served (permissive licence) · get_code("4b69faf22a81a1e4")
get_box3d_corners_helper Ran zhixinwang/frustum-convnet/models/model_util.py
code served (permissive licence) · get_code("281f3748f309afc2")
huber_loss Ran zhixinwang/frustum-convnet/models/model_util.py
code served (permissive licence) · get_code("f6eae958a22ae877")
rotate_pc_along_y Ran zhixinwang/frustum-convnet/datasets/data_utils.py
code served (permissive licence) · get_code("fda77318c74af228")
size_decode Ran zhixinwang/frustum-convnet/models/box_transform.py
code served (permissive licence) · get_code("9989d7e45fda73c4")
size_encode Ran zhixinwang/frustum-convnet/models/box_transform.py
code served (permissive licence) · get_code("53a9950814898b9c")
smooth_l1_loss Ran zhixinwang/frustum-convnet/models/model_util.py
code served (permissive licence) · get_code("ce156beb68c9daa3")
load_cfg Not yet run zhixinwang/frustum-convnet/configs/config.py
code served (permissive licence) · get_code("a124059a5c42fe93")

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 a novel method termed \emph{Frustum ConvNet (F-ConvNet)} for amodal 3D object detection from point clouds. Given 2D region proposals in an RGB image, our method first generates a sequence of frustums for each region proposal, and uses the obtained frustums to group local points. F-ConvNet aggregates point-wise features as frustum-level feature vectors, and arrays these feature vectors as a feature map for use of its subsequent component of fully convolutional network (FCN), which spatially fuses frustum-level features and supports an end-to-end and continuous estimation of oriented boxes in the 3D space. We also propose component variants of F-ConvNet, including an FCN variant that extracts multi-resolution frustum features, and a refined use of F-ConvNet over a reduced 3D space. Careful ablation studies verify the efficacy of these component variants. F-ConvNet assumes no prior knowledge of the working 3D environment and is thus dataset-agnostic. We present experiments on both the indoor SUN-RGBD and outdoor KITTI datasets. F-ConvNet outperforms all existing methods on SUN-RGBD, and at the time of submission it outperforms all published works on the KITTI benchmark. Code has been made available at: {\url{https://github.com/zhixinwang/frustum-convnet}.}

For agents

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

get_harvested_code_for_paper("1903.01864")
get_code_for_paper("1903.01864")
have("1903.01864")

Connect an agent — have() is free.