We lifted 15 functions out of this paper's own repositories and ran 6 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.
| Repository | Role | Ran |
|---|---|---|
| voidrank/Geo-CNN | pwc_unofficial | 6 of 15 |
| Function | Status | Where it lives |
|---|---|---|
| in_hull | Ran | voidrank/Geo-CNN/kitti/dataset.py code served (permissive licence) · get_code("aab935d4b7b55c2c") |
| extract_pc_in_box3d | Ran | voidrank/Geo-CNN/kitti/dataset.py code served (permissive licence) · get_code("50bdbf961c28b4b2") |
| get_lidar_in_image_fov | Ran | voidrank/Geo-CNN/kitti/kitti_object.py code served (permissive licence) · get_code("47397a2377a470c7") |
| rotx | Ran | voidrank/Geo-CNN/kitti/kitti_util.py code served (permissive licence) · get_code("8843d80ab666c4e9") |
| roty | Ran | voidrank/Geo-CNN/kitti/kitti_util.py code served (permissive licence) · get_code("ae86074e10e1dfd7") |
| rotz | Ran | voidrank/Geo-CNN/kitti/kitti_util.py code served (permissive licence) · get_code("082920adf6e29c94") |
| conv1d | Not yet run | voidrank/Geo-CNN/models/tf_util.py code served (permissive licence) · get_code("18d51d8d06002af3") |
| conv2d | Not yet run | voidrank/Geo-CNN/models/tf_util.py code served (permissive licence) · get_code("dd4ea839e0207aea") |
| extract_pc_in_box2d | Not yet run | voidrank/Geo-CNN/kitti/dataset.py code served (permissive licence) · get_code("c1c81b9614b5c990") |
| get_box3d_corners | Not yet run | voidrank/Geo-CNN/models/model_util.py code served (permissive licence) · get_code("3967747ca77d105b") |
| get_box3d_corners_helper | Not yet run | voidrank/Geo-CNN/models/model_util.py code served (permissive licence) · get_code("a40bf46fcddcbcc1") |
| perceptron | Not yet run | voidrank/Geo-CNN/models/tf_util.py code served (permissive licence) · get_code("2877e6c3454ad533") |
| sample_and_group_all | Not yet run | voidrank/Geo-CNN/models/geoconv_util.py code served (permissive licence) · get_code("142a56400c483118") |
| show_lidar_on_image | Not yet run | voidrank/Geo-CNN/kitti/kitti_object.py code served (permissive licence) · get_code("12502f21d75c671f") |
| tf_gather_object_pc | Not yet run | voidrank/Geo-CNN/models/model_util.py code served (permissive licence) · get_code("c2360b0773935ea1") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Recent advances in deep convolutional neural networks (CNNs) have motivated researchers to adapt CNNs to directly model points in 3D point clouds. Modeling local structure has been proven to be important for the success of convolutional architectures, and researchers exploited the modeling of local point sets in the feature extraction hierarchy. However, limited attention has been paid to explicitly model the geometric structure amongst points in a local region. To address this problem, we propose Geo-CNN, which applies a generic convolution-like operation dubbed as GeoConv to each point and its local neighborhood. Local geometric relationships among points are captured when extracting edge features between the center and its neighboring points. We first decompose the edge feature extraction process onto three orthogonal bases, and then aggregate the extracted features based on the angles between the edge vector and the bases. This encourages the network to preserve the geometric structure in Euclidean space throughout the feature extraction hierarchy. GeoConv is a generic and efficient operation that can be easily integrated into 3D point cloud analysis pipelines for multiple applications. We evaluate Geo-CNN on ModelNet40 and KITTI and achieve state-of-the-art performance.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1811.07782")
get_code_for_paper("1811.07782")
have("1811.07782")
Connect an agent — have() is free.