AnyPcc: Compressing Any Point Cloud with a Single Universal Model

TL;DR

AnyPcc introduces a universal point cloud compression framework that employs a robust context model and instance-specific fine-tuning to achieve state-of-the-art results across diverse real-world datasets.

Contribution

The paper presents a novel universal context model and an instance-adaptive fine-tuning strategy for robust, efficient point cloud compression across varying data densities and out-of-distribution scenarios.

Findings

Sets new state-of-the-art performance on 15 diverse datasets.

Maintains low complexity while improving compression quality.

Effective adaptation to out-of-distribution data with minimal bitrate overhead.

Abstract

Generalization remains a critical challenge in deep learning-based point cloud geometry compression. While existing methods perform well on standard benchmarks, their performance collapses in real-world scenarios due to two fundamental limitations: the lack of context models that are robust across diverse data densities, and the inability to efficiently adapt to out-of-distribution (OOD) data. To overcome both challenges, we introduce AnyPcc, a universal point cloud compression framework. AnyPcc first employs a Universal Context Model that leverages coarse-grained spatial priors with fine-grained channel priors to ensure robust context modeling across the entire density spectrum. Second, our novel Instance-Adaptive Fine-Tuning (IAFT) strategy tackles OOD data by synergizing explicit and implicit compression paradigms. For each instance, it fine-tunes a small subset of network weights and transmits them within the bitstream. The minimal bitrate overhead from these weights is significantly outweighed by the resulting gains in geometry compression. Extensive experiments on a benchmark of 15 diverse datasets confirm that AnyPcc sets a new state-of-the-art in point cloud compression while maintaining low complexity. Our code and datasets have been released to encourage reproducible research.