Free-DyGS: Camera-Pose-Free Scene Reconstruction based on Gaussian Splatting for Dynamic Surgical Videos

• URL: http://arxiv.org/abs/2409.01003v2
• Date: Wed, 9 Oct 2024 02:08:56 GMT
• Title: Free-DyGS: Camera-Pose-Free Scene Reconstruction based on Gaussian Splatting for Dynamic Surgical Videos
• Authors: Qian Li, Shuojue Yang, Daiyun Shen, Yueming Jin,
• Abstract summary: This paper presents the first camera-pose-free scene reconstruction framework, Free-DyGS, tailored for dynamic surgical videos. Our approach employs a frame-by-frame reconstruction strategy and is delineated into four distinct phases. Experiments underscore that Free-DyGS surpasses conventional baseline models in both rendering fidelity and computational efficiency.
• Score: 12.199333372665373
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reconstructing endoscopic videos is crucial for high-fidelity visualization and the efficiency of surgical operations. Despite the importance, existing 3D reconstruction methods encounter several challenges, including stringent demands for accuracy, imprecise camera positioning, intricate dynamic scenes, and the necessity for rapid reconstruction. Addressing these issues, this paper presents the first camera-pose-free scene reconstruction framework, Free-DyGS, tailored for dynamic surgical videos, leveraging 3D Gaussian splatting technology. Our approach employs a frame-by-frame reconstruction strategy and is delineated into four distinct phases: Scene Initialization, Joint Learning, Scene Expansion, and Retrospective Learning. We introduce a Generalizable Gaussians Parameterization module within the Scene Initialization and Expansion phases to proficiently generate Gaussian attributes for each pixel from the RGBD frames. The Joint Learning phase is crafted to concurrently deduce scene deformation and camera pose, facilitated by an innovative flexible deformation module. In the scene expansion stage, the Gaussian points gradually grow as the camera moves. The Retrospective Learning phase is dedicated to enhancing the precision of scene deformation through the reassessment of prior frames. The efficacy of the proposed Free-DyGS is substantiated through experiments on two datasets: the StereoMIS and Hamlyn datasets. The experimental outcomes underscore that Free-DyGS surpasses conventional baseline models in both rendering fidelity and computational efficiency.

Related papers

• Deformable Gaussian Splatting for Efficient and High-Fidelity Reconstruction of Surgical Scenes [11.151168064680444]
  EH-SurGS is an efficient and high-fidelity reconstruction algorithm for deformable surgical scenes. We present an adaptive motion hierarchy strategy that distinguishes between static and deformable regions within the surgical scene.
  arXiv  Detail & Related papers  (2025-01-02T06:50:25Z)
• Event-boosted Deformable 3D Gaussians for Dynamic Scene Reconstruction [50.873820265165975]
  We introduce the first approach combining event cameras, which capture high-temporal-resolution, continuous motion data, with deformable 3D-GS for dynamic scene reconstruction. We propose a GS-Threshold Joint Modeling strategy, creating a mutually reinforcing process that greatly improves both 3D reconstruction and threshold modeling. We contribute the first event-inclusive 4D benchmark with synthetic and real-world dynamic scenes, on which our method achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-11-25T08:23:38Z)
• SCIGS: 3D Gaussians Splatting from a Snapshot Compressive Image [11.391665055835249]
  Snapshot Compressive Imaging (SCI) offers a possibility for capturing information in high-speed dynamic scenes. Current deep learning-based reconstruction methods struggle to maintain 3D structural consistency within scenes. We propose SCIGS, a variant of 3DGS, and develop a primitive-level transformation network that utilizes camera pose stamps and Gaussian primitive coordinates as embedding.
  arXiv  Detail & Related papers  (2024-11-19T12:52:37Z)
• EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting [76.02450110026747]
  Event cameras, inspired by biological vision, record pixel-wise intensity changes asynchronously with high temporal resolution. We propose Event-Aided Free-Trajectory 3DGS, which seamlessly integrates the advantages of event cameras into 3DGS. We evaluate our method on the public Tanks and Temples benchmark and a newly collected real-world dataset, RealEv-DAVIS.
  arXiv  Detail & Related papers  (2024-10-20T13:44:24Z)
• 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)
• 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)
• Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion [25.54868552979793]
  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.
  arXiv  Detail & Related papers  (2024-03-20T06:19:41Z)
• FLex: Joint Pose and Dynamic Radiance Fields Optimization for Stereo Endoscopic Videos [79.50191812646125]
  Reconstruction of endoscopic scenes is an important asset for various medical applications, from post-surgery analysis to educational training. We adress the challenging setup of a moving endoscope within a highly dynamic environment of deforming tissue. We propose an implicit scene separation into multiple overlapping 4D neural radiance fields (NeRFs) and a progressive optimization scheme jointly optimizing for reconstruction and camera poses from scratch. This improves the ease-of-use and allows to scale reconstruction capabilities in time to process surgical videos of 5,000 frames and more; an improvement of more than ten times compared to the state of the art while being agnostic to external tracking information
  arXiv  Detail & Related papers  (2024-03-18T19:13:02Z)
• 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)
• BASED: Bundle-Adjusting Surgical Endoscopic Dynamic Video Reconstruction using Neural Radiance Fields [5.773068487121897]
  Reconstruction of deformable scenes from endoscopic videos is important for many applications. Our work adopts the Neural Radiance Fields (NeRF) approach to learning 3D implicit representations of scenes. We demonstrate this approach on endoscopic surgical scenes from robotic surgery.
  arXiv  Detail & Related papers  (2023-09-27T00:20:36Z)
• SceNeRFlow: Time-Consistent Reconstruction of General Dynamic Scenes [75.9110646062442]
  We propose SceNeRFlow to reconstruct a general, non-rigid scene in a time-consistent manner. Our method takes multi-view RGB videos and background images from static cameras with known camera parameters as input. We show experimentally that, unlike prior work that only handles small motion, our method enables the reconstruction of studio-scale motions.
  arXiv  Detail & Related papers  (2023-08-16T09:50:35Z)
• Rolling Shutter Inversion: Bring Rolling Shutter Images to High Framerate Global Shutter Video [111.08121952640766]
  This paper presents a novel deep-learning based solution to the RS temporal super-resolution problem. By leveraging the multi-view geometry relationship of the RS imaging process, our framework successfully achieves high framerate GS generation. Our method can produce high-quality GS image sequences with rich details, outperforming the state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-10-06T16:47:12Z)
• Context-Aware Video Reconstruction for Rolling Shutter Cameras [52.28710992548282]
  In this paper, we propose a context-aware GS video reconstruction architecture. We first estimate the bilateral motion field so that the pixels of the two RS frames are warped to a common GS frame. Then, a refinement scheme is proposed to guide the GS frame synthesis along with bilateral occlusion masks to produce high-fidelity GS video frames.
  arXiv  Detail & Related papers  (2022-05-25T17:05:47Z)
• Class-agnostic Reconstruction of Dynamic Objects from Videos [127.41336060616214]
  We introduce REDO, a class-agnostic framework to REconstruct the Dynamic Objects from RGBD or calibrated videos. We develop two novel modules. First, we introduce a canonical 4D implicit function which is pixel-aligned with aggregated temporal visual cues. Second, we develop a 4D transformation module which captures object dynamics to support temporal propagation and aggregation.
  arXiv  Detail & Related papers  (2021-12-03T18:57:47Z)
• Learning to Segment Rigid Motions from Two Frames [72.14906744113125]
  We propose a modular network, motivated by a geometric analysis of what independent object motions can be recovered from an egomotion field. It takes two consecutive frames as input and predicts segmentation masks for the background and multiple rigidly moving objects, which are then parameterized by 3D rigid transformations. Our method achieves state-of-the-art performance for rigid motion segmentation on KITTI and Sintel.
  arXiv  Detail & Related papers  (2021-01-11T04:20:30Z)

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.