Pith. sign in

REVIEW 7 cited by

HAC++: Towards 100X Compression of 3D Gaussian Splatting

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2501.12255 v4 pith:N7ZODER4 submitted 2025-01-21 cs.CV

Yihang Chen , Qianyi Wu , Weiyao Lin , Mehrtash Harandi , Jianfei Cai This is my paper
classification cs.CV
keywords compressionanchorsfidelitygaussiangaussianssizeadaptiveattributes
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity. However, the substantial Gaussians and their associated attributes necessitate effective compression techniques. Nevertheless, the sparse and unorganized nature of the point cloud of Gaussians (or anchors in our paper) presents challenges for compression. To achieve a compact size, we propose HAC++, which leverages the relationships between unorganized anchors and a structured hash grid, utilizing their mutual information for context modeling. Additionally, HAC++ captures intra-anchor contextual relationships to further enhance compression performance. To facilitate entropy coding, we utilize Gaussian distributions to precisely estimate the probability of each quantized attribute, where an adaptive quantization module is proposed to enable high-precision quantization of these attributes for improved fidelity restoration. Moreover, we incorporate an adaptive masking strategy to eliminate invalid Gaussians and anchors. Overall, HAC++ achieves a remarkable size reduction of over 100X compared to vanilla 3DGS when averaged on all datasets, while simultaneously improving fidelity. It also delivers more than 20X size reduction compared to Scaffold-GS. Our code is available at https://github.com/YihangChen-ee/HAC-plus.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction

    cs.GR 2025-09 reject novelty 7.0 of 10

    ContraGS trains 3D Gaussian Splatting directly on codebook-compressed representations, cutting peak model memory ~3.5x with small quality loss.

  2. TinySplat: Feedforward Approach for Generating Compact 3D Scene Representation

    cs.CV 2025-06 conditional novelty 7.0 of 10

    TinySplat compresses feedforward 3D Gaussian scenes by 105-199x on two-view benchmarks (about 50x on DL3DV) while keeping rendered quality close to the uncompressed model.

  3. NanoGS: Training-Free Gaussian Splat Simplification

    cs.CV 2026-03 conditional novelty 6.0 of 10

    A training-free, CPU-based graph-merging method reduces 3D Gaussian Splat primitive counts by orders of magnitude while maintaining higher rendering fidelity than prior compaction methods.

  4. Smol-GS: Compact Representations for Abstract 3D Gaussian Splatting

    cs.CV 2025-11 conditional novelty 6.0 of 10

    A 3D Gaussian Splatting compression method that stores coordinates in an occupancy octree and represents appearance with 8-d learned features, reaching ~4.7-6.4 MB per scene at near-SOTA quality.

  5. CF3: Compact and Fast 3D Feature Fields

    cs.CV 2025-08 conditional novelty 6.0 of 10

    CF3 builds a compact 3D feature field from a pre-trained 3DGS by feature lifting, per-Gaussian autoencoding, and adaptive sparsification, matching baseline segmentation quality with roughly 5% of the Gaussians.

  6. A Novel Benchmark and Dataset for Efficient 3D Gaussian Splatting with Gaussian Point Cloud Compression

    cs.GR 2025-05 conditional novelty 6.0 of 10

    GausPcgc adapts learned point cloud compression to Gaussian Splatting anchor positions, and the new GausPcc-1K dataset improves position bitrate by 8.2% over G-PCC v23 in the paper's benchmark.

  7. Perceive-Sample-Compress: Towards Real-Time 3D Gaussian Splatting

    cs.GR 2025-08 conditional novelty 4.0 of 10

    A three-stage perceive-sample-compress framework for 3D Gaussian Splatting improves rendering fidelity and storage efficiency across small and large scenes.

Pith tools