PLEDGE: Progressive Lossy Error-Bounded Compression of 3D Gaussian Splatting

Mingze Xia; Yuxiao Li; Baixi Sun; Wenbo Li; Pu Jiao; Sheng Di; Franck Cappello; Hanqi Guo

cs.CVOct 13, 2026

PLEDGE: Progressive Lossy Error-Bounded Compression of 3D Gaussian Splatting

Authors: Mingze Xia, Yuxiao Li, Baixi Sun, Wenbo Li, Pu Jiao, Sheng Di, Franck Cappello, Hanqi Guo,

Organizations: Oregon State University · The Ohio State University · Argonne National Laboratory · The University of Texas Rio Grande Valley

Abstract

Existing 3D Gaussian Splatting (3DGS) codecs report reconstruction quality after compression, and give users little control over the distortion of individual primitives. We present PLEDGE, a training-free, progressive, error-bounded codec that translates four user-declared tolerances into per-primitive quantization bounds: screen-space position, footprint deformation due to rotation and scale, view-dependent color, and opacity. The bounds apply throughout a declared camera domain, including previously unseen viewpoints. Position and opacity are bounded directly; footprint deformation is bounded under the rasterizer's affine projection model, and color is bounded over all viewing directions. PLEDGE organizes quantized residuals into a progressive bitstream with explicit error bounds for every valid prefix. Experiments across thirteen scenes verify all declared per-mechanism bounds and demonstrate competitive rate-distortion performance. The four tolerances incur substantially different rate costs, so users can spend rate where their application needs it.

Figures & tables

Panel of Figure 1 — Figure 1: PLEDGE overview. Four user-declared tolerances and a camera domain give per-primitive quantization steps $\Delta=2\varepsilon$ ; by Proposition 1 , everything after quantization affects rate but not the guarantee.

Panel of Figure 2 — Figure 2: (a) Rate–distortion. Solid: $60\%$ keep; dashed: a front over keep fractions $45\%$ down to $12\%$ , whose bounds are relative to smaller models. (b) Progressive decoding at $25/50/75/100\%$ of the byte budget; every valid prefix satisfies Proposition 6 . Test-split PSNR for the full sweep is reported in §5.4.

	$\mu$	$s$	$q$	$\alpha$	$C$
fraction of bound	1.000	1.000	0.996	1.000	0.906

Table 2: (a) Worst error over thirteen scenes at nine

(\tau_{\mathrm{px}},\tau_{\mathrm{sh}},\tau_{C})

settings, each entry divided by its own bound. Upper block by attribute; lower block by declared

\tau

in image space, against

\tau_{\mathrm{px}}

2\tau_{\mathrm{sh}}

and

\sqrt{2}\tau_{\mathrm{px}}{+}2\tau_{\mathrm{sh}}

— the bound ( 2 ) with the loose

\delta_{J}

term dropped. Footprint rows are Hausdorff distances between the rasterizer’s

\Sigma^{\prime}

for the reference and the decoded model, computed independently of the bounds in §3.3. (b) Thirteen-scene mean at three PLEDGE operating points,

\tau_{C}=0.8

0.2

and

0.1

for (A), (B) and (C), all at

(\tau_{\mathrm{px}},\tau_{\mathrm{sh}},\tau_{\alpha})=(8,16,0.005)

; (C) matches SOG in size.

Figure 3: Representative held-out views, each codec at its own operating point.

Quantization

See all 49 papers

CodecSplat: Ultra-Compact Latent Coding for Feed-Forward 3D Gaussian Splatting
May 25, 2026Pengpeng Yu, Runqing Jiang, Qi Zhang +33DGS Compression 3D Gaussian Splatting
1Sun Yat-sen University, China · 3Pengcheng Laboratory, China · 2Peking University, China
ProGS: Towards Progressive Coding for 3D Gaussian Splatting
Mar 10, 2026Zhiye Tang, Lingzhuo Liu, Shengjie Jiao +43DGS Compression 3D Gaussian Splatting
College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China · Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong SAR, China · School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, 430074, China
MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching
Apr 29, 2026Shuzhao Xie, Junchen Ge, Weixiang Zhang +103DGS Compression 3D Gaussian Splatting
Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · The Hong Kong University of Science and Technology, Hong Kong SAR, China · Harbin Institute of Technology, Shenzhen, China +6

May 25, 2026J/K move · Enter open · S save

CodecSplat: Ultra-Compact Latent Coding for Feed-Forward 3D Gaussian Splatting

Pengpeng Yu, Runqing Jiang, Qi Zhang, Dingquan Li+2

1Sun Yat-sen University, China · 3Pengcheng Laboratory, China · 2Peking University, China

3DGS Compression 3D Gaussian Splatting Representation Learning Feed-Forward 3D Reconstruction Gaussian Splatting Compression

Open paper AskPDF arXiv

While feed-forward 3D Gaussian splatting reconstructs renderable Gaussian primitives from sparse context views without per-scene optimization, existing pipelines do not provide a compact scene representation for storage or transmission. A natural solution is to apply existing 3DGS compression methods to the generated Gaussian primitives. However, this approach operates on the final irregular 3D representation and is decoupled from the internal feature-to-Gaussian generation process, which limits compression efficiency. To address this, we introduce CodecSplat, an ultra-compact latent coding framework for feed-forward 3D Gaussian splatting. CodecSplat first encodes an intermediate 2D Gaussian-generation feature into an entropy-coded scene bitstream. At the decoder, the latent feature is reconstructed and used to predict depth and Gaussian parameters, which are then mapped to 3D Gaussian primitives. By integrating compression into the feed-forward Gaussian generation pipeline, CodecSplat avoids inefficient compression over irregular 3D Gaussian primitives and allows the codec to exploit the structured intermediate feature representation. We instantiate CodecSplat on a feed-forward Gaussian splatting backbone with depth-guided multi-view feature refinement and a hierarchical learned feature codec. On DL3DV and RealEstate10K datasets, CodecSplat achieves 23.56-26.36 dB and 24.76-27.05 dB PSNR with only 20.00-107.77 KiB and 3.37-12.51 KiB per scene, respectively. This is roughly one order of magnitude smaller than compressing feed-forward generated Gaussian primitives, while preserving controllable rate-distortion behavior. Code is available at https://github.com/pengpeng-yu/CodecSplat.

Abstract

Quantization

Explore similar work

CodecSplat: Ultra-Compact Latent Coding for Feed-Forward 3D Gaussian Splatting

ProGS: Towards Progressive Coding for 3D Gaussian Splatting

MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching