CC-4DGS introduces a storage‑efficient framework for dynamic 4D Gaussian splatting by replacing large multi‑resolution hash tables with a deterministic dense hash encoding and compact neural decoders, reducing deformation storage to 1–3 MB per scene. It also compresses canonical point‑cloud attributes through conditional autoencoding, selective quantization, and residual codebooks, achieving 3–5× reduction in point‑cloud size with negligible quality loss. The combined approach maintains real‑time rendering performance while lowering total storage to 20–30 MB, matching state‑of‑the‑art reconstruction accuracy on N3DV and Technicolor Light Field datasets.
By Kyungdae Park, Chae Eun Rhee
The paper presents an explicit compression method for structured and unstructured volume data using 3D Gaussian primitives. By treating collections of Gaussians as an explicit scalar field representation, the authors develop CUDA‑accelerated sampling pipelines and loss functions that ensure accurate domain coverage, eliminating the need for mesh storage in unstructured volumes. The approach achieves faster training, higher reconstruction quality, and significantly higher compression ratios compared to existing implicit neural representations.
By Landon Dyken, Sharmistha Chakrabarti, Nathan Debardeleben, Steve Petruzza, Qi Wu, Will Usher, Sidharth Kumar
The paper introduces a non‑uniform quantisation scheme designed for 3D Gaussian Splatting (3DGS) models, addressing their high bitrate demands. By applying importance‑weighted quantisation and merging, the method adapts to the data distribution and removes post‑voxelisation redundancy. Experiments on benchmark datasets show state‑of‑the‑art compression performance, and the scheme is compatible with any point‑cloud representation, positioning it as a candidate for future MPEG 3DGS standardisation.
By Bert Van hauwermeiren, Patrice Rondao Alface, Adrian Munteanu
arXiv:2607. 01164v1 Announce Type: new Abstract: Recent work has shown that implicit neural representations (INRs) can be trained to effectively compress structured and unstructured volume data, allowing for direct data querying with a reduced memory footprint.
By Landon Dyken, Sharmistha Chakrabarti, Nathan Debardeleben, Steve Petruzza, Qi Wu, Will Usher, Sidharth Kumar
arXiv:2607.13808v2 Announce Type: replace
Abstract: Neural radiance representations in Gaussian Splatting (GS) deliver high-fidelity color detail but impose substantial rendering overhead from networ...
By Neel Kelkar, Simon Niedermayr, Kaloian Petkov, Klaus Engel, R\"udiger Westermann
KISS-GS is a modular compression pipeline for 3D Gaussian Splatting (3DGS) scenes that separates compression from training. It first compacts a vanilla 3DGS scene by 15.7× using state‑of‑the‑art pruning, then encodes the result into the SOG‑XT image‑based format, achieving an additional 6.6× reduction. Optional encoding‑aware fine‑tuning can further cut the size by 2.2×, yielding total reductions of 85× to 319× on standard benchmarks while enabling web‑native decoding.
By Wieland Morgenstern, Friedrich Elias Branschke, Florian Fleischmann, Adrian Szatmari, Paul Schlack, Florian Barthel, Peter Eisert, Anna Hilsmann
arXiv:2605.26616v2 Announce Type: replace
Abstract: While 3D Gaussian Splatting has achieved remarkable success in photorealistic novel view synthesis, its pursuit of fast and high-fidelity 3D recons...
By Zhenhua Du, Zhen Tan, Haoyu Zhang, Dewen Hu, Shuaifeng Zhi, Peidong Liu
DirectUV is an image-conditioned UV texture diffusion framework that generates high-quality textures directly in UV space using a pretrained image VAE and a Diffusion Transformer. It introduces Surface-Aware Positional Encoding (SAPE), which replaces standard 2D-grid positional encoding with encodings derived from 3D surface coordinates, enabling attention to operate based on surface proximity rather than UV-grid distance. A multi-level extension assigns different attention heads to progressively finer subdivisions of the UV patch, allowing the model to reason about surface structure at multiple granularities, resulting in sharper and more globally consistent textures, especially in occluded and view-unseen regions.
By Jiantao Lin, Yingjie Xu, Mingzhi Sheng, Yangkai Wei, Hao Chen, Ying-Cong Chen
arXiv:2605.25563v2 Announce Type: replace
Abstract: While feed-forward 3D Gaussian splatting reconstructs renderable Gaussian primitives from sparse context views without per-scene optimization, exis...
By Pengpeng Yu, Runqing Jiang, Qi Zhang, Dingquan Li, Jing Wang, Yulan Guo
The paper introduces SVRecon, a generalizable neural surface reconstruction framework that uses sparse volumetric representations to achieve high-resolution 3D reconstruction. It employs a two-stage architecture: first predicting occupied voxels with an occupancy network, then rendering only within those regions using specialized sparse algorithms. This approach allows reconstruction at resolutions up to 512³ on 32 GB hardware, producing smoother and more precise surfaces, especially in sparse-view scenarios.
By Aoxiang Fan, Corentin Dumery, Nicolas Talabot, Ming Xu, Hieu Le, Pascal Fua
Thread‑Efficient Decoding for Neural Texture Compression proposes a shared decoder MLP architecture trained with a gradual decoder freezing schedule and texture clustering to reduce GPU thread divergence by 25‑52%. The method preserves rendering quality while achieving up to 8.48× speedup on a Radeon RX 9070 XT compared to non‑shared baselines. Experiments on over 500 textures and multiple real rendering scenes validate the performance gains and provide comprehensive ablation studies.
By Janarbek Matai, Sho Ikeda, Lukasz Lipski, Takahiro Harada
arXiv:2501.13558v4 Announce Type: replace
Abstract: Splat-based radiance fields have rapidly diversified in primitive type, kernel support, and appearance parameterization. This diversity makes compr...
By Francesco Di Sario, Riccardo Renzulli, Marco Grangetto, Akihiro Sugimoto, Enzo Tartaglione