# JSGS: JPEG State-Guided Supervision for 3D Gaussian Splatting from Mixed-Quality Views

arXiv: https://arxiv.org/abs/2608.08659 · HTML: https://mlsanity.com/paper/2608.08659/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 28 references that are in the map.
- First posted on arXiv 9 Aug 2026.

## Builds on (most cited first, 19 of 19)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering](https://mlsanity.com/paper/2312.00109/) (2023)
- [Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians](https://mlsanity.com/paper/2403.14166/) (2024)
- [GaussianPro: 3D Gaussian Splatting with Progressive Propagation](https://mlsanity.com/paper/2402.14650/) (2024)
- [WildGaussians: 3D Gaussian Splatting in the Wild](https://mlsanity.com/paper/2407.08447/) (2024)
- [Compression Artifacts Reduction by a Deep Convolutional Network](https://mlsanity.com/paper/1504.06993/) (2015)
- [Revising Densification in Gaussian Splatting](https://mlsanity.com/paper/2404.06109/) (2024)
- [FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization](https://mlsanity.com/paper/2403.06908/) (2024)
- [Towards Flexible Blind JPEG Artifacts Removal](https://mlsanity.com/paper/2109.14573/) (2021)
- [BAD-Gaussians: Bundle Adjusted Deblur Gaussian Splatting](https://mlsanity.com/paper/2403.11831/) (2024)
- [Quantization Guided JPEG Artifact Correction](https://mlsanity.com/paper/2004.09320/) (2020)
- [Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustment](https://mlsanity.com/paper/2504.01503/) (2025)
- [Implicit Dual-domain Convolutional Network for Robust Color Image Compression Artifact Reduction](https://mlsanity.com/paper/1810.08042/) (2018)
- [Gaussian in the Dark: Real-Time View Synthesis From Inconsistent Dark Images Using Gaussian Splatting](https://mlsanity.com/paper/2408.09130/) (2024)
- [From Chaos to Clarity: 3DGS in the Dark](https://mlsanity.com/paper/2406.08300/) (2024)
- [JDEC: JPEG Decoding via Enhanced Continuous Cosine Coefficients](https://mlsanity.com/paper/2404.05558/) (2024)
- [CompSplat: Compression-aware 3D Gaussian Splatting for Real-world Video](https://mlsanity.com/paper/2602.09816/) (2026)

## Abstract (arXiv)

Standard 3D Gaussian Splatting (3DGS) assumes that every input image faithfully samples scene radiance. However, mixed-quality JPEG images violate this assumption because compression-induced blocking and ringing artifacts can corrupt updates to Gaussians shared across views. To address this problem, we propose JPEG State-Guided Supervision for 3D Gaussian Splatting from Mixed-Quality Views (JSGS). JSGS uses luminance and chrominance quantization tables stored in each JPEG file to construct a view-specific JPEG observation operator. This operator encodes and decodes each rendered view for domain-matched comparison with the corresponding decoded input image. The luminance quantization table supplies continuous weights within a fixed middle frequency band. A loss in the low frequency band anchors coarse structure, while the weighted middle frequency loss redistributes supervision among the selected DCT coordinates. The resulting block disagreement also guides the Gaussian Controller to regularize small primitives with high opacity in disagreement regions. Across seven scenes and three mixed-quality schedules, JSGS achieves the lowest mean LPIPS and the highest mean SSIM under every schedule while rendering at approximately 150 FPS. Code: https://github.com/Jayden-Cui/JSGS.