Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion
- URL: http://arxiv.org/abs/2403.13327v3
- Date: Wed, 17 Jul 2024 07:50:14 GMT
- Title: Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion
- Authors: Otto Seiskari, Jerry Ylilammi, Valtteri Kaatrasalo, Pekka Rantalankila, Matias Turkulainen, Juho Kannala, Esa Rahtu, Arno Solin,
- Abstract summary: We present a method that adapts to camera motion and allows high-quality scene reconstruction with handheld video data.
Our results with both synthetic and real data demonstrate superior performance in mitigating camera motion over existing methods.
- Score: 25.54868552979793
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: High-quality scene reconstruction and novel view synthesis based on Gaussian Splatting (3DGS) typically require steady, high-quality photographs, often impractical to capture with handheld cameras. We present a method that adapts to camera motion and allows high-quality scene reconstruction with handheld video data suffering from motion blur and rolling shutter distortion. Our approach is based on detailed modelling of the physical image formation process and utilizes velocities estimated using visual-inertial odometry (VIO). Camera poses are considered non-static during the exposure time of a single image frame and camera poses are further optimized in the reconstruction process. We formulate a differentiable rendering pipeline that leverages screen space approximation to efficiently incorporate rolling-shutter and motion blur effects into the 3DGS framework. Our results with both synthetic and real data demonstrate superior performance in mitigating camera motion over existing methods, thereby advancing 3DGS in naturalistic settings.
Related papers
- CRiM-GS: Continuous Rigid Motion-Aware Gaussian Splatting from Motion Blur Images [12.603775893040972]
We propose continuous rigid motion-aware gaussian splatting (CRiM-GS) to reconstruct accurate 3D scene from blurry images with real-time rendering speed.
We leverage rigid body transformations to model the camera motion with proper regularization, preserving the shape and size of the object.
Furthermore, we introduce a continuous deformable 3D transformation in the textitSE(3) field to adapt the rigid body transformation to real-world problems.
arXiv Detail & Related papers (2024-07-04T13:37:04Z) - Modeling Ambient Scene Dynamics for Free-view Synthesis [31.233859111566613]
We introduce a novel method for dynamic free-view synthesis of an ambient scenes from a monocular capture.
Our method builds upon the recent advancements in 3D Gaussian Splatting (3DGS) that can faithfully reconstruct complex static scenes.
arXiv Detail & Related papers (2024-06-13T17:59:11Z) - EvaGaussians: Event Stream Assisted Gaussian Splatting from Blurry Images [39.584967370302735]
3D Gaussian Splatting (3D-GS) has demonstrated exceptional capabilities in 3D scene reconstruction and novel view synthesis.
We introduce Event Stream Assisted Gaussian Splatting (EvaGaussians), a novel approach that integrates event streams captured by an event camera to assist in reconstructing high-quality 3D-GS from blurry images.
arXiv Detail & Related papers (2024-05-29T04:59:27Z) - DeblurGS: Gaussian Splatting for Camera Motion Blur [45.13521168573883]
We propose DeblurGS, a method to optimize sharp 3D Gaussian Splatting from motion-blurred images.
We restore a fine-grained sharp scene by leveraging the remarkable reconstruction capability of 3D Gaussian Splatting.
Our approach estimates the 6-Degree-of-Freedom camera motion for each blurry observation and synthesizes corresponding blurry renderings.
arXiv Detail & Related papers (2024-04-17T13:14:52Z) - Motion-aware 3D Gaussian Splatting for Efficient Dynamic Scene Reconstruction [89.53963284958037]
We propose a novel motion-aware enhancement framework for dynamic scene reconstruction.
Specifically, we first establish a correspondence between 3D Gaussian movements and pixel-level flow.
For the prevalent deformation-based paradigm that presents a harder optimization problem, a transient-aware deformation auxiliary module is proposed.
arXiv Detail & Related papers (2024-03-18T03:46:26Z) - GGRt: Towards Pose-free Generalizable 3D Gaussian Splatting in Real-time [112.32349668385635]
GGRt is a novel approach to generalizable novel view synthesis that alleviates the need for real camera poses.
As the first pose-free generalizable 3D-GS framework, GGRt achieves inference at $ge$ 5 FPS and real-time rendering at $ge$ 100 FPS.
arXiv Detail & Related papers (2024-03-15T09:47:35Z) - Cinematic Behavior Transfer via NeRF-based Differentiable Filming [63.1622492808519]
Existing SLAM methods face limitations in dynamic scenes and human pose estimation often focuses on 2D projections.
We first introduce a reverse filming behavior estimation technique.
We then introduce a cinematic transfer pipeline that is able to transfer various shot types to a new 2D video or a 3D virtual environment.
arXiv Detail & Related papers (2023-11-29T15:56:58Z) - Motion-from-Blur: 3D Shape and Motion Estimation of Motion-blurred
Objects in Videos [115.71874459429381]
We propose a method for jointly estimating the 3D motion, 3D shape, and appearance of highly motion-blurred objects from a video.
Experiments on benchmark datasets demonstrate that our method outperforms previous methods for fast moving object deblurring and 3D reconstruction.
arXiv Detail & Related papers (2021-11-29T11:25:14Z) - Visual Odometry with an Event Camera Using Continuous Ray Warping and
Volumetric Contrast Maximization [31.627936023222052]
We present a new solution to tracking and mapping with an event camera.
The motion of the camera contains both rotation and translation, and the displacements happen in an arbitrarily structured environment.
We introduce a new solution to this problem by performing contrast in 3D.
The practical validity of our approach is supported by an application to AGV motion estimation and 3D reconstruction with a single vehicle-mounted event camera.
arXiv Detail & Related papers (2021-07-07T04:32:57Z) - Spatiotemporal Bundle Adjustment for Dynamic 3D Human Reconstruction in
the Wild [49.672487902268706]
We present a framework that jointly estimates camera temporal alignment and 3D point triangulation.
We reconstruct 3D motion trajectories of human bodies in events captured by multiple unsynchronized and unsynchronized video cameras.
arXiv Detail & Related papers (2020-07-24T23:50:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.