TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Escape from Cells: Deep Kd-Networks for the Recognition of...

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

Roman Klokov, Victor Lempitsky

2017-04-04ICCV 2017 10General ClassificationRetrieval3D Part Segmentation3D Point Cloud Classification
PaperPDFCodeCode

Abstract

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.

Results

TaskDatasetMetricValueModel
Semantic SegmentationShapeNet-PartClass Average IoU77.4Kd-net
Semantic SegmentationShapeNet-PartInstance Average IoU82.3Kd-net
Shape Representation Of 3D Point CloudsModelNet40Overall Accuracy91.8Kd-Net
Shape Representation Of 3D Point CloudsModelNet40Overall Accuracy90.6Kd-net
3D Point Cloud ClassificationModelNet40Overall Accuracy91.8Kd-Net
3D Point Cloud ClassificationModelNet40Overall Accuracy90.6Kd-net
10-shot image generationShapeNet-PartClass Average IoU77.4Kd-net
10-shot image generationShapeNet-PartInstance Average IoU82.3Kd-net
3D Point Cloud ReconstructionModelNet40Overall Accuracy91.8Kd-Net
3D Point Cloud ReconstructionModelNet40Overall Accuracy90.6Kd-net

Related Papers

From Roots to Rewards: Dynamic Tree Reasoning with RL2025-07-17HapticCap: A Multimodal Dataset and Task for Understanding User Experience of Vibration Haptic Signals2025-07-17A Survey of Context Engineering for Large Language Models2025-07-17MCoT-RE: Multi-Faceted Chain-of-Thought and Re-Ranking for Training-Free Zero-Shot Composed Image Retrieval2025-07-17Developing Visual Augmented Q&A System using Scalable Vision Embedding Retrieval & Late Interaction Re-ranker2025-07-16Language-Guided Contrastive Audio-Visual Masked Autoencoder with Automatically Generated Audio-Visual-Text Triplets from Videos2025-07-16Context-Aware Search and Retrieval Over Erasure Channels2025-07-16Seq vs Seq: An Open Suite of Paired Encoders and Decoders2025-07-15