Improved Block Merging for 3D Point Cloud Instance Segmentation

• URL: http://arxiv.org/abs/2407.06991v1
• Date: Tue, 9 Jul 2024 16:06:34 GMT
• Title: Improved Block Merging for 3D Point Cloud Instance Segmentation
• Authors: Leon Denis, Remco Royen, Adrian Munteanu,
• Abstract summary: The proposed work improves over the state-of-the-art by allowing wrongly labelled points of already processed blocks to be corrected through label propagation. Our experiments show that the proposed block merging algorithm significantly and consistently improves the obtained accuracy for all evaluation metrics employed in literature.
• Score: 6.632158868486343
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper proposes a novel block merging algorithm suitable for any block-based 3D instance segmentation technique. The proposed work improves over the state-of-the-art by allowing wrongly labelled points of already processed blocks to be corrected through label propagation. By doing so, instance overlap between blocks is not anymore necessary to produce the desirable results, which is the main limitation of the current art. Our experiments show that the proposed block merging algorithm significantly and consistently improves the obtained accuracy for all evaluation metrics employed in literature, regardless of the underlying network architecture.

Related papers

• Towards Universal Dense Blocking for Entity Resolution [49.06313308481536]
  We propose UniBlocker, a dense blocker that is pre-trained on a domain-independent, easily-obtainable corpus. By conducting domain-independent pre-training, UniBlocker can be adapted to various downstream blocking scenarios without requiring domain-specific fine-tuning. Our experiments show that the proposed UniBlocker, without any domain-specific learning, significantly outperforms previous self- and unsupervised dense blocking methods.
  arXiv  Detail & Related papers  (2024-04-23T08:39:29Z)
• Theoretically Achieving Continuous Representation of Oriented Bounding Boxes [64.15627958879053]
  This paper endeavors to completely solve the issue of discontinuity in Oriented Bounding Box representation. We propose a novel representation method called Continuous OBB (COBB) which can be readily integrated into existing detectors. For fairness and transparency of experiments, we have developed a modularized benchmark based on the open-source deep learning framework Jittor's detection toolbox JDet for OOD evaluation.
  arXiv  Detail & Related papers  (2024-02-29T09:27:40Z)
• Block Sparse Bayesian Learning: A Diversified Scheme [16.61484758008309]
  We introduce a novel prior called Diversified Block Sparse Prior to characterize the widespread block sparsity phenomenon in real-world data. By allowing diversification on intra-block variance and inter-block correlation matrices, we effectively address the sensitivity issue of existing block sparse learning methods to pre-defined block information.
  arXiv  Detail & Related papers  (2024-02-07T08:18:06Z)
• Multi-modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation [47.81638388980828]
  We propose a simple yet effective scene-level weakly supervised point cloud segmentation method with a newly introduced multi-modality point affinity inference module. Our method outperforms the state-of-the-art by 4% to 6% mIoU on the ScanNet and S3DIS benchmarks.
  arXiv  Detail & Related papers  (2023-12-27T14:01:35Z)
• ShallowBlocker: Improving Set Similarity Joins for Blocking [1.8492669447784602]
  We propose a hands-off blocking method based on classical string similarity measures: ShallowBlocker. It uses a novel hybrid set similarity join combining absolute similarity, relative similarity, and local cardinality conditions with a new effective pre-candidate filter replacing size filter. We show that the method achieves state-of-the-art pair effectiveness on both unsupervised and supervised blocking in a scalable way.
  arXiv  Detail & Related papers  (2023-12-26T00:31:43Z)
• BASS: Block-wise Adaptation for Speech Summarization [47.518484305407185]
  We develop a method that allows one to train summarization models on very long sequences in an incremental manner. Speech summarization is realized as a streaming process, where hypothesis summaries are updated every block. Experiments on the How2 dataset demonstrate that the proposed block-wise training method improves by 3 points absolute on ROUGE-L over a truncated input baseline.
  arXiv  Detail & Related papers  (2023-07-17T03:31:36Z)
• The Cascaded Forward Algorithm for Neural Network Training [61.06444586991505]
  We propose a new learning framework for neural networks, namely Cascaded Forward (CaFo) algorithm, which does not rely on BP optimization as that in FF. Unlike FF, our framework directly outputs label distributions at each cascaded block, which does not require generation of additional negative samples. In our framework each block can be trained independently, so it can be easily deployed into parallel acceleration systems.
  arXiv  Detail & Related papers  (2023-03-17T02:01:11Z)
• Collaborative Propagation on Multiple Instance Graphs for 3D Instance Segmentation with Single-point Supervision [63.429704654271475]
  We propose a novel weakly supervised method RWSeg that only requires labeling one object with one point. With these sparse weak labels, we introduce a unified framework with two branches to propagate semantic and instance information. Specifically, we propose a Cross-graph Competing Random Walks (CRW) algorithm that encourages competition among different instance graphs.
  arXiv  Detail & Related papers  (2022-08-10T02:14:39Z)
• Copy-Move Image Forgery Detection Based on Evolving Circular Domains Coverage [5.716030416222748]
  The proposed scheme integrates both block-based and keypoint-based forgery detection methods. The experimental results indicate that the proposed CMFD scheme can achieve better detection performance under various attacks.
  arXiv  Detail & Related papers  (2021-09-09T16:08:03Z)
• Structural block driven - enhanced convolutional neural representation for relation extraction [11.617819771034927]
  We propose a novel lightweight relation extraction approach of structural block driven - convolutional neural learning. We detect the essential sequential tokens associated with entities through dependency analysis, named as a structural block. We only encode the block on a block-wise and an inter-block-wise representation, utilizing multi-scale CNNs.
  arXiv  Detail & Related papers  (2021-03-21T10:23:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.