Meta-Sampler: Almost-Universal yet Task-Oriented Sampling for Point Clouds

by   Ta-Ying Cheng, et al.

Sampling is a key operation in point-cloud task and acts to increase computational efficiency and tractability by discarding redundant points. Universal sampling algorithms (e.g., Farthest Point Sampling) work without modification across different tasks, models, and datasets, but by their very nature are agnostic about the downstream task/model. As such, they have no implicit knowledge about which points would be best to keep and which to reject. Recent work has shown how task-specific point cloud sampling (e.g., SampleNet) can be used to outperform traditional sampling approaches by learning which points are more informative. However, these learnable samplers face two inherent issues: i) overfitting to a model rather than a task, and ) requiring training of the sampling network from scratch, in addition to the task network, somewhat countering the original objective of down-sampling to increase efficiency. In this work, we propose an almost-universal sampler, in our quest for a sampler that can learn to preserve the most useful points for a particular task, yet be inexpensive to adapt to different tasks, models, or datasets. We first demonstrate how training over multiple models for the same task (e.g., shape reconstruction) significantly outperforms the vanilla SampleNet in terms of accuracy by not overfitting the sample network to a particular task network. Second, 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, thus amortizing the initial cost of training.


SampleNet: Differentiable Point Cloud Sampling

There is a growing number of tasks that work directly on point clouds. A...

Beyond Farthest Point Sampling in Point-Wise Analysis

Sampling, grouping, and aggregation are three important components in th...

AS-PD: An Arbitrary-Size Downsampling Framework for Point Clouds

Point cloud downsampling is a crucial pre-processing operation to downsa...

APSNet: Attention Based Point Cloud Sampling

Processing large point clouds is a challenging task. Therefore, the data...

Meta-PU: An Arbitrary-Scale Upsampling Network for Point Cloud

Point cloud upsampling is vital for the quality of the mesh in three-dim...

Hierarchical Adaptive Voxel-guided Sampling for Real-time Applications in Large-scale Point Clouds

While point-based neural architectures have demonstrated their efficacy,...

Efficient Topology-Controlled Sampling of Implicit Shapes

Sampling from distributions of implicitly defined shapes enables analysi...

Please sign up or login with your details

Forgot password? Click here to reset