# UPGS: Unified Pose-aware Gaussian Splatting for Dynamic Scene Deblurring

arXiv: https://arxiv.org/abs/2509.00831 · HTML: https://mlsanity.com/paper/2509.00831/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 51 references that are in the map.
- First posted on arXiv 31 Aug 2025.

## Builds on (most cited first, 30 of 36)

- [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)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction](https://mlsanity.com/paper/2309.13101/) (2023)
- [Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis](https://mlsanity.com/paper/2308.09713/) (2023)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [EDVR: Video Restoration with Enhanced Deformable Convolutional Networks](https://mlsanity.com/paper/1905.02716/) (2019)
- [Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting](https://mlsanity.com/paper/2310.10642/) (2023)
- [Gaussian Splatting SLAM](https://mlsanity.com/paper/2312.06741/) (2023)
- [DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks](https://mlsanity.com/paper/1711.07064/) (2017)
- [DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes](https://mlsanity.com/paper/2312.07920/) (2023)
- [Scale-recurrent Network for Deep Image Deblurring](https://mlsanity.com/paper/1802.01770/) (2018)
- [Shape of Motion: 4D Reconstruction from a Single Video](https://mlsanity.com/paper/2407.13764/) (2024)
- [NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior](https://mlsanity.com/paper/2212.07388/) (2022)
- [Deblur-NeRF: Neural Radiance Fields from Blurry Images](https://mlsanity.com/paper/2111.14292/) (2021)
- [VR-GS: A Physical Dynamics-Aware Interactive Gaussian Splatting System in Virtual Reality](https://mlsanity.com/paper/2401.16663/) (2024)
- [Spatio-Temporal Filter Adaptive Network for Video Deblurring](https://mlsanity.com/paper/1904.12257/) (2019)
- [Cascaded Deep Video Deblurring Using Temporal Sharpness Prior](https://mlsanity.com/paper/2004.02501/) (2020)
- [BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fields](https://mlsanity.com/paper/2211.12853/) (2022)
- [DP-NeRF: Deblurred Neural Radiance Field with Physical Scene Priors](https://mlsanity.com/paper/2211.12046/) (2022)
- [Deblurring 3D Gaussian Splatting](https://mlsanity.com/paper/2401.00834/) (2024)
- [BAD-Gaussians: Bundle Adjusted Deblur Gaussian Splatting](https://mlsanity.com/paper/2403.11831/) (2024)
- [ExBluRF: Efficient Radiance Fields for Extreme Motion Blurred Images](https://mlsanity.com/paper/2309.08957/) (2023)
- [DAVANet: Stereo Deblurring with View Aggregation](https://mlsanity.com/paper/1904.05065/) (2019)
- [Deblur4DGS: 4D Gaussian Splatting from Blurry Monocular Video](https://mlsanity.com/paper/2412.06424/) (2024)
- [BARD-GS: Blur-Aware Reconstruction of Dynamic Scenes via Gaussian Splatting](https://mlsanity.com/paper/2503.15835/) (2025)
- [DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video](https://mlsanity.com/paper/2403.10103/) (2024)
- [Sharp-NeRF: Grid-based Fast Deblurring Neural Radiance Fields Using Sharpness Prior](https://mlsanity.com/paper/2401.00825/) (2024)

## Abstract (arXiv)

Reconstructing dynamic 3D scenes from monocular video has broad applications in AR/VR, robotics, and autonomous navigation, but often fails due to severe motion blur caused by camera and object motion. Existing methods commonly follow a two-step pipeline, where camera poses are first estimated and then 3D Gaussians are optimized. Since blurring artifacts usually undermine pose estimation, pose errors could be accumulated to produce inferior reconstruction results. To address this issue, we introduce a unified optimization framework by incorporating camera poses as learnable parameters complementary to 3DGS attributes for end-to-end optimization. Specifically, we recast camera and object motion as per-primitive SE(3) affine transformations on 3D Gaussians and formulate a unified optimization objective. For stable optimization, we introduce a three-stage training schedule that optimizes camera poses and Gaussians alternatively. Particularly, 3D Gaussians are first trained with poses being fixed, and then poses are optimized with 3D Gaussians being untouched. Finally, all learnable parameters are optimized together. Extensive experiments on the Stereo Blur dataset and challenging real-world sequences demonstrate that our method achieves significant gains in reconstruction quality and pose estimation accuracy over prior dynamic deblurring methods.