# Transform-Aligned Learned Features for Lossy Point Cloud Attribute Compression

arXiv: https://arxiv.org/abs/2609.34834 · HTML: https://mlsanity.com/paper/2609.34834/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 41 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 20 of 20)

- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Nonlinear Transform Coding](https://mlsanity.com/paper/2007.03034/) (2020)
- [Sparse Tensor-based Point Cloud Attribute Compression](https://mlsanity.com/paper/2204.01023/) (2022)
- [Lossless Point Cloud Geometry and Attribute Compression Using a Learned Conditional Probability Model](https://mlsanity.com/paper/2303.06519/) (2023)
- [Graph Signal Processing for Geometric Data and Beyond: Theory and Applications](https://mlsanity.com/paper/2008.01918/) (2020)
- [3DAC: Learning Attribute Compression for Point Clouds](https://mlsanity.com/paper/2203.09931/) (2022)
- [LVAC: Learned Volumetric Attribute Compression for Point Clouds using Coordinate Based Networks](https://mlsanity.com/paper/2111.08988/) (2021)
- [Attribute Compression of 3D Point Clouds Using Laplacian Sparsity Optimized Graph Transform](https://mlsanity.com/paper/1710.03532/) (2017)
- [TSC-PCAC: Voxel Transformer and Sparse Convolution Based Point Cloud Attribute Compression for 3D Broadcasting](https://mlsanity.com/paper/2407.04284/) (2024)
- [Predictive Generalized Graph Fourier Transform for Attribute Compression of Dynamic Point Clouds](https://mlsanity.com/paper/1908.01970/) (2019)
- [Lossless Point Cloud Attribute Compression Using Cross-scale, Cross-group, and Cross-color Prediction](https://mlsanity.com/paper/2303.12917/) (2023)
- [Region adaptive graph fourier transform for 3d point clouds](https://mlsanity.com/paper/2003.01866/) (2020)
- [Point Cloud Attribute Compression via Successive Subspace Graph Transform](https://mlsanity.com/paper/2010.15302/) (2020)
- [Learned Nonlinear Predictor for Critically Sampled 3D Point Cloud Attribute Compression](https://mlsanity.com/paper/2311.13539/) (2023)
- [Efficient and Generic Point Model for Lossless Point Cloud Attribute Compression](https://mlsanity.com/paper/2404.06936/) (2024)
- [DeepRAHT: Learning Predictive RAHT for Point Cloud Attribute Compression](https://mlsanity.com/paper/2601.12255/) (2026)
- [Hierarchical Attention Networks for Lossless Point Cloud Attribute Compression](https://mlsanity.com/paper/2504.00481/) (2025)
- [Generalized Gaussian Entropy Model for Point Cloud Attribute Compression with Dynamic Likelihood Intervals](https://mlsanity.com/paper/2506.09510/) (2025)

## Abstract (arXiv)

Transform-based methods provide an effective framework for point cloud attribute compression by representing attributes as transform coefficients. Introducing learned spatial context into this framework requires mapping spatial representations to the transform domain, but this known basis change is often left for the network to learn implicitly. We propose Transform-Aligned Learned Features (TALF) by applying the attribute transform to learned spatial representations, explicitly aligning them with the coding targets. Our analysis shows that the resulting features exactly represent the first-order prediction term of a smooth nonlinear model, with a bounded Taylor remainder. We integrate TALF into a transform-based attribute codec with explicit coefficient prediction and conditional residual entropy modeling under a unified coefficient-domain rate--distortion objective, while retaining explicit quantization-step control. Extensive experiments across three benchmark datasets and multiple transform bases demonstrate that TALF improves rate--distortion performance over conventional and learned baselines.