Abstract
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.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Chen, Y., Yu, P., Li, D., Gao, W., Zhang, W., & Song, F. (2026). Transform-Aligned Learned Features for Lossy Point Cloud Attribute Compression. https://omanscience.com/en/articles/transform-aligned-learned-features-for-lossy-point-cloud-attribute-compression
MLA 9
Chen, Yueru, et al. "Transform-Aligned Learned Features for Lossy Point Cloud Attribute Compression." https://omanscience.com/en/articles/transform-aligned-learned-features-for-lossy-point-cloud-attribute-compression.
Chicago (author–date)
Chen, Yueru, Pengpeng Yu, Dingquan Li, Wei Gao, Wei Zhang, and Fei Song. 2026. "Transform-Aligned Learned Features for Lossy Point Cloud Attribute Compression." https://omanscience.com/en/articles/transform-aligned-learned-features-for-lossy-point-cloud-attribute-compression.
Harvard
Chen, Y., Yu, P., Li, D., Gao, W., Zhang, W. and Song, F. (2026) 'Transform-Aligned Learned Features for Lossy Point Cloud Attribute Compression', Available at: https://omanscience.com/en/articles/transform-aligned-learned-features-for-lossy-point-cloud-attribute-compression.
Vancouver
Chen Y, Yu P, Li D, Gao W, Zhang W, Song F. Transform-Aligned Learned Features for Lossy Point Cloud Attribute Compression. https://omanscience.com/en/articles/transform-aligned-learned-features-for-lossy-point-cloud-attribute-compression
IEEE
Y. Chen, P. Yu, D. Li, W. Gao, W. Zhang, and F. Song, "Transform-Aligned Learned Features for Lossy Point Cloud Attribute Compression," https://omanscience.com/en/articles/transform-aligned-learned-features-for-lossy-point-cloud-attribute-compression.