# 3R-GS: Best Practice in Optimizing Camera Poses Along with 3DGS

arXiv: https://arxiv.org/abs/2504.04294 · HTML: https://mlsanity.com/paper/2504.04294/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 61 references that are in the map.
- First posted on arXiv 5 Apr 2025.

## Builds on (most cited first, 30 of 51)

- [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)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [Gaussian Splatting SLAM](https://mlsanity.com/paper/2312.06741/) (2023)
- [INeRF: Inverting Neural Radiance Fields for Pose Estimation](https://mlsanity.com/paper/2012.05877/) (2020)
- [Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass](https://mlsanity.com/paper/2501.13928/) (2025)
- [DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes](https://mlsanity.com/paper/2312.07920/) (2023)
- [GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting](https://mlsanity.com/paper/2404.19702/) (2024)
- [DISK: Learning local features with policy gradient](https://mlsanity.com/paper/2006.13566/) (2020)
- [GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation](https://mlsanity.com/paper/2403.14621/) (2024)
- [gsplat: An Open-Source Library for Gaussian Splatting](https://mlsanity.com/paper/2409.06765/) (2024)
- [3D Reconstruction with Spatial Memory](https://mlsanity.com/paper/2408.16061/) (2024)
- [GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces](https://mlsanity.com/paper/2311.17977/) (2023)
- [NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior](https://mlsanity.com/paper/2212.07388/) (2022)
- [Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes](https://mlsanity.com/paper/2404.10772/) (2024)
- [Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians](https://mlsanity.com/paper/2403.17898/) (2024)
- [Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting](https://mlsanity.com/paper/2401.01339/) (2024)
- [Global Structure-from-Motion Revisited](https://mlsanity.com/paper/2407.20219/) (2024)
- [A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets](https://mlsanity.com/paper/2406.12080/) (2024)
- [Self-Calibrating Neural Radiance Fields](https://mlsanity.com/paper/2108.13826/) (2021)
- [SPARF: Neural Radiance Fields from Sparse and Noisy Poses](https://mlsanity.com/paper/2211.11738/) (2022)

## Built on by (most cited first, 11 of 11)

- [VGGT-X: When VGGT Meets Dense Novel View Synthesis](https://mlsanity.com/paper/2509.25191/) (2025)
- [World Reconstruction From Inconsistent Views](https://mlsanity.com/paper/2603.16736/) (2026)
- [OmniRaindrop: A Comprehensive Benchmark for Dual-Focused Raindrop Removal under Day and Night Scenes](https://mlsanity.com/paper/2510.17719/) (2025)
- [AnimateScene: Camera-controllable Animation in Any Scene](https://mlsanity.com/paper/2508.05982/) (2025)
- [OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects](https://mlsanity.com/paper/2510.20605/) (2025)
- [SatSplat: Geometrically-Accurate Gaussian Splatting for Satellite Imagery](https://mlsanity.com/paper/2606.28581/) (2026)
- [Swimm3R: Splatting with Medium-aware SfM for Underwater 3D Reconstruction](https://mlsanity.com/paper/2608.00950/) (2026)
- [GloSplat: Joint Pose-Appearance Optimization for Faster and More Accurate 3D Reconstruction](https://mlsanity.com/paper/2603.04847/) (2026)
- [Pose-Free Omnidirectional Gaussian Splatting for 360-Degree Videos with Consistent Depth Priors](https://mlsanity.com/paper/2603.23324/) (2026)
- [Fast 3D Foundation Model Initialized Gaussian Splatting](https://mlsanity.com/paper/2607.03209/) (2026)
- [Reliability-Regulated Trajectory Optimization for Progressive COLMAP-Free 3D Gaussian Splatting](https://mlsanity.com/paper/2609.30865/) (2026)

## Abstract (arXiv)

3D Gaussian Splatting (3DGS) has revolutionized neural rendering with its efficiency and quality, but like many novel view synthesis methods, it heavily depends on accurate camera poses from Structure-from-Motion (SfM) systems. Although recent SfM pipelines have made impressive progress, questions remain about how to further improve both their robust performance in challenging conditions (e.g., textureless scenes) and the precision of camera parameter estimation simultaneously. We present 3R-GS, a 3D Gaussian Splatting framework that bridges this gap by jointly optimizing 3D Gaussians and camera parameters from large reconstruction priors MASt3R-SfM. We note that naively performing joint 3D Gaussian and camera optimization faces two challenges: the sensitivity to the quality of SfM initialization, and its limited capacity for global optimization, leading to suboptimal reconstruction results. Our 3R-GS, overcomes these issues by incorporating optimized practices, enabling robust scene reconstruction even with imperfect camera registration. Extensive experiments demonstrate that 3R-GS delivers high-quality novel view synthesis and precise camera pose estimation while remaining computationally efficient. Project page: https://zsh523.github.io/3R-GS/