# SplatSuRe: Selective Super-Resolution for Multi-view Consistent 3D Gaussian Splatting

arXiv: https://arxiv.org/abs/2512.02172 · HTML: https://mlsanity.com/paper/2512.02172/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 1 Dec 2025.

## Builds on (most cited first, 27 of 27)

- [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)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Mip-Splatting: Alias-free 3D Gaussian Splatting](https://mlsanity.com/paper/2311.16493/) (2023)
- [Exploiting Diffusion Prior for Real-World Image Super-Resolution](https://mlsanity.com/paper/2305.07015/) (2023)
- [Rethinking FID: Towards a Better Evaluation Metric for Image Generation](https://mlsanity.com/paper/2401.09603/) (2023)
- [PU-Net: Point Cloud Upsampling Network](https://mlsanity.com/paper/1801.06761/) (2018)
- [Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models](https://mlsanity.com/paper/2503.01774/) (2025)
- [3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors](https://mlsanity.com/paper/2410.16266/) (2024)
- [NeRF-SR: High-Quality Neural Radiance Fields using Supersampling](https://mlsanity.com/paper/2112.01759/) (2021)
- [DiffGS: Functional Gaussian Splatting Diffusion](https://mlsanity.com/paper/2410.19657/) (2024)
- [DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation](https://mlsanity.com/paper/2501.16764/) (2025)
- [GANeRF: Leveraging Discriminators to Optimize Neural Radiance Fields](https://mlsanity.com/paper/2306.06044/) (2023)
- [SRGS: Super-Resolution 3D Gaussian Splatting](https://mlsanity.com/paper/2404.10318/) (2024)
- [S2Gaussian: Sparse-View Super-Resolution 3D Gaussian Splatting](https://mlsanity.com/paper/2503.04314/) (2025)
- [SuperGaussian: Repurposing Video Models for 3D Super Resolution](https://mlsanity.com/paper/2406.00609/) (2024)
- [GaussianSR: 3D Gaussian Super-Resolution with 2D Diffusion Priors](https://mlsanity.com/paper/2406.10111/) (2024)
- [GSFix3D: Diffusion-Guided Repair of Novel Views in Gaussian Splatting](https://mlsanity.com/paper/2508.14717/) (2025)
- [3D Point Cloud Super-Resolution via Graph Total Variation on Surface Normals](https://mlsanity.com/paper/1908.06261/) (2019)
- [Bridging Diffusion Models and 3D Representations: A 3D Consistent Super-Resolution Framework](https://mlsanity.com/paper/2508.04090/) (2025)
- [ZS-SRT: An Efficient Zero-Shot Super-Resolution Training Method for Neural Radiance Fields](https://mlsanity.com/paper/2312.12122/) (2023)
- [ASSR-NeRF: Arbitrary-Scale Super-Resolution on Voxel Grid for High-Quality Radiance Fields Reconstruction](https://mlsanity.com/paper/2406.20066/) (2024)
- [Advancing Super-Resolution in Neural Radiance Fields via Variational Diffusion Strategies](https://mlsanity.com/paper/2410.18137/) (2024)
- [SuperNeRF-GAN: A Universal 3D-Consistent Super-Resolution Framework for Efficient and Enhanced 3D-Aware Image Synthesis](https://mlsanity.com/paper/2501.06770/) (2025)
- [EGP3D: Edge-guided Geometric Preserving 3D Point Cloud Super-resolution for RGB-D camera](https://mlsanity.com/paper/2412.11680/) (2024)

## Built on by (most cited first, 2 of 2)

- [ConFi-GS Confidence-Guided High-Frequency Injection for 3D Gaussian Splatting Super-Resolution](https://mlsanity.com/paper/2605.24964/) (2026)
- [MACRO: Training-free Multi-plane Attention for Closeup Render Optimization](https://mlsanity.com/paper/2607.03875/) (2026)

## Abstract (arXiv)

3D Gaussian Splatting (3DGS) enables high-quality novel view synthesis, motivating interest in generating higher-resolution renders than those available during training. A natural strategy is to apply super-resolution (SR) to low-resolution (LR) input views, but independently enhancing each image introduces multi-view inconsistencies, leading to blurry renders. Prior methods attempt to mitigate these inconsistencies through learned neural components, temporally consistent video priors, or joint optimization on LR and SR views, but all uniformly apply SR across every image. In contrast, our key insight is that close-up LR views may contain high-frequency information for regions also captured in more distant views and that we can use the camera pose relative to scene geometry to inform where to add SR content. Building on this insight, we propose SplatSuRe, a method that selectively applies SR content only in undersampled regions lacking high-frequency supervision, yielding sharper and more consistent results. Across Tanks & Temples, Deep Blending, and Mip-NeRF 360, our approach surpasses baselines in both fidelity and perceptual quality. Notably, our gains are most significant in localized foreground regions where higher detail is desired.