# Efficient Learning on Point Clouds with Basis Point Sets

arXiv: https://arxiv.org/abs/1908.09186 · HTML: https://mlsanity.com/paper/1908.09186/

## Key facts

- Cited by 103 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Aug 2019.

## Built on by (most cited first, 30 of 103)

- [Object Motion Guided Human Motion Synthesis](https://mlsanity.com/paper/2309.16237/) (2023)
- [GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping](https://mlsanity.com/paper/2112.11454/) (2021)
- [OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction](https://mlsanity.com/paper/2203.15709/) (2022)
- [Controllable Human-Object Interaction Synthesis](https://mlsanity.com/paper/2312.03913/) (2023)
- [SAGA: Stochastic Whole-Body Grasping with Contact](https://mlsanity.com/paper/2112.10103/) (2021)
- [Generating Human Interaction Motions in Scenes with Text Control](https://mlsanity.com/paper/2404.10685/) (2024)
- [CIRCLE: Capture In Rich Contextual Environments](https://mlsanity.com/paper/2303.17912/) (2023)
- [ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning](https://mlsanity.com/paper/2503.21860/) (2025)
- [Human-Object Interaction from Human-Level Instructions](https://mlsanity.com/paper/2406.17840/) (2024)
- [BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information](https://mlsanity.com/paper/2203.15536/) (2022)
- [A Skeleton-Driven Neural Occupancy Representation for Articulated Hands](https://mlsanity.com/paper/2109.11399/) (2021)
- [DexDiffuser: Generating Dexterous Grasps with Diffusion Models](https://mlsanity.com/paper/2402.02989/) (2024)
- [FLEX: Full-Body Grasping Without Full-Body Grasps](https://mlsanity.com/paper/2211.11903/) (2022)
- [Task-Oriented Human-Object Interactions Generation with Implicit Neural Representations](https://mlsanity.com/paper/2303.13129/) (2023)
- [HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances](https://mlsanity.com/paper/2403.01693/) (2024)
- [Diffusion Models for Robotic Manipulation: A Survey](https://mlsanity.com/paper/2504.08438/) (2025)
- [GenZI: Zero-Shot 3D Human-Scene Interaction Generation](https://mlsanity.com/paper/2311.17737/) (2023)
- [HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Data](https://mlsanity.com/paper/2403.12011/) (2024)
- [HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects](https://mlsanity.com/paper/2407.12371/) (2024)
- [InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation](https://mlsanity.com/paper/2509.09555/) (2025)
- [Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronization](https://mlsanity.com/paper/2111.12878/) (2021)
- [BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects](https://mlsanity.com/paper/2412.05066/) (2024)
- [Contact-aware Human Motion Forecasting](https://mlsanity.com/paper/2210.03954/) (2022)
- [Revisit Human-Scene Interaction via Space Occupancy](https://mlsanity.com/paper/2312.02700/) (2023)
- [A Survey on Human Interaction Motion Generation](https://mlsanity.com/paper/2503.12763/) (2025)
- [ROAM: Robust and Object-Aware Motion Generation Using Neural Pose Descriptors](https://mlsanity.com/paper/2308.12969/) (2023)
- [ManiDext: Hand-Object Manipulation Synthesis via Continuous Correspondence Embeddings and Residual-Guided Diffusion](https://mlsanity.com/paper/2409.09300/) (2024)
- [SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance](https://mlsanity.com/paper/2503.01291/) (2025)
- [Generalizing Neural Human Fitting to Unseen Poses With Articulated SE(3) Equivariance](https://mlsanity.com/paper/2304.10528/) (2023)
- [SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesis](https://mlsanity.com/paper/2412.20104/) (2024)

## Abstract (arXiv)

With the increased availability of 3D scanning technology, point clouds are moving into the focus of computer vision as a rich representation of everyday scenes. However, they are hard to handle for machine learning algorithms due to their unordered structure. One common approach is to apply occupancy grid mapping, which dramatically increases the amount of data stored and at the same time loses details through discretization. Recently, deep learning models were proposed to handle point clouds directly and achieve input permutation invariance. However, these architectures often use an increased number of parameters and are computationally inefficient. In this work, we propose basis point sets (BPS) as a highly efficient and fully general way to process point clouds with machine learning algorithms. The basis point set representation is a residual representation that can be computed efficiently and can be used with standard neural network architectures and other machine learning algorithms. Using the proposed representation as the input to a simple fully connected network allows us to match the performance of PointNet on a shape classification task while using three orders of magnitude less floating-point operations. In a second experiment, we show how the proposed representation can be used for registering high-resolution meshes to noisy 3D scans. Here, we present the first method for single-pass high-resolution mesh registration, avoiding time-consuming per-scan optimization and allowing real-time execution.