Beyond Farthest Point Sampling in Point-Wise Analysis
- URL: http://arxiv.org/abs/2107.04291v2
- Date: Mon, 12 Jul 2021 03:04:09 GMT
- Title: Beyond Farthest Point Sampling in Point-Wise Analysis
- Authors: Yiqun Lin, Lichang Chen, Haibin Huang, Chongyang Ma, Xiaoguang Han and
Shuguang Cui
- Abstract summary: We propose a novel data-driven sampler learning strategy for point-wise analysis tasks.
We learn sampling and downstream applications jointly.
Our experiments show that jointly learning of the sampler and task brings remarkable improvement over previous baseline methods.
- Score: 52.218037492342546
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Sampling, grouping, and aggregation are three important components in the
multi-scale analysis of point clouds. In this paper, we present a novel
data-driven sampler learning strategy for point-wise analysis tasks. Unlike the
widely used sampling technique, Farthest Point Sampling (FPS), we propose to
learn sampling and downstream applications jointly. Our key insight is that
uniform sampling methods like FPS are not always optimal for different tasks:
sampling more points around boundary areas can make the point-wise
classification easier for segmentation. Towards the end, we propose a novel
sampler learning strategy that learns sampling point displacement supervised by
task-related ground truth information and can be trained jointly with the
underlying tasks. We further demonstrate our methods in various point-wise
analysis architectures, including semantic part segmentation, point cloud
completion, and keypoint detection. Our experiments show that jointly learning
of the sampler and task brings remarkable improvement over previous baseline
methods.
Related papers
- Diffusion Generative Flow Samplers: Improving learning signals through
partial trajectory optimization [87.21285093582446]
Diffusion Generative Flow Samplers (DGFS) is a sampling-based framework where the learning process can be tractably broken down into short partial trajectory segments.
Our method takes inspiration from the theory developed for generative flow networks (GFlowNets)
arXiv Detail & Related papers (2023-10-04T09:39:05Z) - Dimension Independent Mixup for Hard Negative Sample in Collaborative
Filtering [36.26865960551565]
Negative sampling plays a vital role in training CF-based models with implicit feedback.
We propose Dimension Independent Mixup for Hard Negative Sampling (DINS), which is the first Area-wise sampling method for training CF-based models.
Our work contributes a new perspective, introduces Area-wise sampling, and presents DINS as a novel approach for negative sampling.
arXiv Detail & Related papers (2023-06-28T04:03:31Z) - Importance Sampling for Stochastic Gradient Descent in Deep Neural
Networks [0.0]
Importance sampling for training deep neural networks has been widely studied.
This paper reviews the challenges inherent to this research area.
We propose a metric allowing the assessment of the quality of a given sampling scheme.
arXiv Detail & Related papers (2023-03-29T08:35:11Z) - Attention-based Point Cloud Edge Sampling [0.0]
Point cloud sampling is a less explored research topic for this data representation.
This paper proposes a non-generative Attention-based Point cloud Edge Sampling method (APES)
Both qualitative and quantitative experimental results show the superior performance of our sampling method on common benchmark tasks.
arXiv Detail & Related papers (2023-02-28T15:36:17Z) - BIMS-PU: Bi-Directional and Multi-Scale Point Cloud Upsampling [60.257912103351394]
We develop a new point cloud upsampling pipeline called BIMS-PU.
We decompose the up/downsampling procedure into several up/downsampling sub-steps by breaking the target sampling factor into smaller factors.
We show that our method achieves superior results to state-of-the-art approaches.
arXiv Detail & Related papers (2022-06-25T13:13:37Z) - Meta-Sampler: Almost-Universal yet Task-Oriented Sampling for Point
Clouds [46.33828400918886]
We show how we can train an almost-universal meta-sampler across multiple tasks.
This meta-sampler can then be rapidly fine-tuned when applied to different datasets, networks, or even different tasks.
arXiv Detail & Related papers (2022-03-30T02:21:34Z) - SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object
Detection [78.90102636266276]
We propose a novel set abstraction method named Semantics-Augmented Set Abstraction (SASA)
Based on the estimated point-wise foreground scores, we then propose a semantics-guided point sampling algorithm to help retain more important foreground points during down-sampling.
In practice, SASA shows to be effective in identifying valuable points related to foreground objects and improving feature learning for point-based 3D detection.
arXiv Detail & Related papers (2022-01-06T08:54:47Z) - Learning Semantic Segmentation of Large-Scale Point Clouds with Random
Sampling [52.464516118826765]
We introduce RandLA-Net, an efficient and lightweight neural architecture to infer per-point semantics for large-scale point clouds.
The key to our approach is to use random point sampling instead of more complex point selection approaches.
Our RandLA-Net can process 1 million points in a single pass up to 200x faster than existing approaches.
arXiv Detail & Related papers (2021-07-06T05:08:34Z) - Rethinking Sampling in 3D Point Cloud Generative Adversarial Networks [82.72642388129843]
We show that sampling-insensitive discriminators produce shape point clouds with point clustering artifacts while sampling-oversensitive discriminators fail to guide valid shape generation.
We propose the concept of sampling spectrum to depict the different sampling sensitivities of discriminators.
We discover a middle-point sampling-aware baseline discriminator, PointNet-Mix, which improves all existing point cloud generators by a large margin on sampling-related metrics.
arXiv Detail & Related papers (2020-06-12T09:29:24Z)
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.