Papers › Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models

Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models

4 Apr 2017ICCV 2017 10arXiv:1704.01222archive 2025-07-28

Roman Klokov, Victor Lempitsky

We present a new deep learning architecture (called Kd-network) that is designed for 3D model recognition tasks and works with unstructured point clouds. The new architecture performs multiplicative transformations and share parameters of these transformations according to the subdivisions of the point clouds imposed onto them by Kd-trees. Unlike the currently dominant convolutional architectures that usually require rasterization on uniform two-dimensional or three-dimensional grids, Kd-networks do not rely on such grids in any way and therefore avoid poor scaling behaviour. In a series of experiments with popular shape recognition benchmarks, Kd-networks demonstrate competitive performance in a number of shape recognition tasks such as shape classification, shape retrieval and shape part segmentation.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

fxia22/kdnet.pytorch mentioned on GitHubpytorch report
qq456cvb/KdNet-Tensorflow mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Part Segmentation3D Point Cloud ClassificationGeneral ClassificationRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Part Segmentation ShapeNet-Part Kd-net Class Average IoU 77.4 #64 of 67 Archive leaderboard report
3D Part Segmentation ShapeNet-Part Kd-net Instance Average IoU 82.3 #64 of 67 Archive leaderboard report
3D Point Cloud Classification ModelNet40 Kd-Net Overall Accuracy 91.8 #96 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 Kd-net Overall Accuracy 90.6 #102 of 111 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections