Transform-Aligned Learned Features for Lossy Point Cloud Attribute Compression

Yueru Chen; Pengpeng Yu; Dingquan Li; Wei Gao; Wei Zhang; Fei Song

cs.CVSep 28, 2026

Transform-Aligned Learned Features for Lossy Point Cloud Attribute Compression

Authors: Yueru Chen, Pengpeng Yu, Dingquan Li, Wei Gao, Wei Zhang, Fei Song

Organizations: Pengcheng Laboratory, Shenzhen, China · Sun Yat-sen University, Shenzhen, China · Peking University, Shenzhen, China · Xidian University, Xi’an, China

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.

Figures & tables

Dataset	3DAC	Unicorn	TALF
Ford	$+1.81$	$-5.63^{\dagger}$	$\mathbf{-20.93}$
KITTI	$+9.89$	$-4.68^{\dagger}$	$\mathbf{-14.01}$

Table 1: Comparisons of coding performance using average BD-Rate (%) against the baseline methods and runtime (s/frame). G-PCCv33 is the BD-Rate anchor, except for Unicorn † , which uses the reported Unicorn-G-PCC (RAHT21) anchor.

Predictor	Nonlinearity	Parameters	Innovation MSE	Residual energy reduction
Shared linear predictor	None	513	139.2518	30.37
Shared one-hidden-layer MLP	GELU	263,169	135.2843	32.35

Table 2: Analysis of transform alignment on Ford. (a) Residual energy reduction is relative to zero-innovation prediction. (b) Prediction MSE is evaluated on valid AC coefficients before quantization. (c) BD-Rate is relative to G-PCCv33. All reductions, increases, and BD-Rate values are in %.

Prediction variant	BD-Rate vs. G-PCCv33	BD-Rate vs. No $\mu$	BD-Rate vs. Integer $\mu_{n}^{q}$
No $\mu$	-7.68	0.00	–
Integer $\mu_{n}^{q}$	-15.50	-8.46	0.00
Full $\mu$	-20.93	-14.02	-6.00

Table 3: Ablation of explicit coefficient correction on Ford. BD-Rate (%) is reported relative to G-PCCv33, No

\mu

, and Integer

\mu_{n}^{q}

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Configuration	Reflectance	Color
Maximum references per node	32	32
Attention blocks	5	5
Attention width	128	128
Output feature dimension	512	512
Input feature dimension	5	9
Shared MLP dimensions	$512\!\rightarrow\!256$	$512\!\rightarrow\!256$

Appendix

Table 4: Network and training configuration used for the reported models.

QS	$\Pr(\mu_{n}^{q}\neq 0)$	$\mathbb{E}[\|\mu_{n}^{q}\|]$	$\Pr(q_{\mu}\neq q_{n})$
4	50.92	1.460	19.21
8	34.93	0.678	14.93
16	19.76	0.291	11.14
32	8.00	0.101	6.08
64	2.28	0.027	2.48

Appendix

Table 5: Mechanistic analysis of the explicit coefficient correction on Ford. The integer-only and full corrections are compared with the no-correction path using the codec’s actual quantizer. Probabilities, zero-symbol ratios, and relative changes are reported in %.

G-PCCv33			TALF
Point	bpp	PSNR-Refl	QS	bpp	PSNR-Refl
R8	4.4898	50.17	4.00	2.9921	46.28
R7	3.5089	46.24	5.03	2.6260	43.84
R6	2.5609	41.00	6.34	2.3246	42.03
R5	1.6631	35.45	8.00	2.0329	40.16
R4	0.8915	30.23	10.06	1.8060	38.83

Appendix

Table 6: Dataset-average rate–distortion results for Ford.

G-PCCv33			TALF
Point	bpp	PSNR-Refl	QS	bpp	PSNR-Refl
R8	3.6923	50.43	4.00	2.3908	46.44
R7	2.7439	46.44	5.03	2.0212	43.91
R6	1.8133	41.06	6.34	1.7255	42.07
R5	0.8855	35.56	8.00	1.4498	40.30
R4	0.2518	31.28	10.06	1.2438	38.97

Appendix

Table 7: Dataset-average rate–distortion results for KITTI.

G-PCCv33						TALF
Point	bpp	Y	Cb	Cr	YCbCr	QS	Neural bpp	RL bpp	Y	Cb	Cr	YCbCr
R8	7.6590	49.98	49.98	49.73	49.95	4.00	4.2864	4.6183	46.20	46.95	47.27	46.41
R7	4.8095	45.92	46.39	46.62	46.06	5.03	3.7922	4.0720	43.86	46.25	46.74	44.39
R6	2.5896	40.63	42.42	43.99	41.14	6.34	2.9026	3.1165	42.16	44.46	45.32	42.69
R5	1.3095	35.49	39.82	41.97	36.33	8.00	2.3043	2.4613	40.51	43.09	44.35	41.11
R4	0.5993	30.82	38.06	40.03	31.85	10.06	1.9140	2.0176	39.28	42.03	43.65	39.92

Appendix

Table 8: Dataset-average rate–distortion results for ScanNet.

Explore similar work

TAFA-GSGC: Group-wise Scalable Point Cloud Geometry Compression with Progressive Residual Refinement
Apr 30, 2026Xiumei Li, Alexander Kopte, André KaupPoint Clouds
Chair of Multimedia Communications and Signal Processing Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen, Germany
Deep Unrolling of Sparsity-Induced RDO for 3D Point Cloud Attribute Coding
Sep 10, 2025Tam Thuc Do, Philip A. Chou, Gene CheungPoint Clouds Deep Unfolding Networks
department of EECS, York University, 4700 Keele Street, Toronto, M3J 1P3, Canada
Geometry-Based Compression of Plenoptic Point Clouds
Aug 11, 2026Davi R. Freitas, Gustavo L. Sandri, Ricardo L. de QueirozPoint Clouds Volumetric Video
Inria - Rennes Bretagne-Atlantique Rennes, France · Instituto Federal de Bras´ılia Bras´ılia, Brazil · Universidade de Bras´ılia Bras´ılia, Brazil

Apr 30, 2026, cs.CVJ/K move · Enter open · S save

TAFA-GSGC: Group-wise Scalable Point Cloud Geometry Compression with Progressive Residual Refinement

Xiumei Li, Alexander Kopte, André Kaup

Chair of Multimedia Communications and Signal Processing Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen, Germany

Point Clouds

Open paper AskPDF arXiv

Scalable compression is essential for bandwidth-adaptive transmission, yet most learned codecs are optimized for a fixed rate-distortion point, making rate adaptation costly due to re-encoding or maintaining multiple bitstreams. In this work, we propose TAFA-GSGC, a scalable learned point cloud geometry codec that enables multi-quality decoding from a single bitstream and a single trained model. TAFA-GSGC combines layered residual refinement with channel-group entropy coding, and introduces a Target-Aligned Feature Aggregation module to reduce cross-layer redundancy in enhancement residuals. Our framework supports up to 9 decodable quality levels with monotonic quality improvement as more subbitstreams are received, while maintaining strong compression efficiency. Compared with the PCGCv2 baseline, TAFA-GSGC demonstrates improved RD performance, achieving average BD-rate reductions of 4.99% and 5.92% in terms of D1-PSNR and D2-PSNR, respectively.

Abstract

Explore similar work

TAFA-GSGC: Group-wise Scalable Point Cloud Geometry Compression with Progressive Residual Refinement

Deep Unrolling of Sparsity-Induced RDO for 3D Point Cloud Attribute Coding

Geometry-Based Compression of Plenoptic Point Clouds