CAGE-GS: High-fidelity Cage Based 3D Gaussian Splatting Deformation

• URL: http://arxiv.org/abs/2504.12800v1
• Date: Thu, 17 Apr 2025 10:00:15 GMT
• Title: CAGE-GS: High-fidelity Cage Based 3D Gaussian Splatting Deformation
• Authors: Yifei Tong, Runze Tian, Xiao Han, Dingyao Liu, Fenggen Yu, Yan Zhang,
• Abstract summary: CAGE-GS is a cage-based 3DGS deformation method that seamlessly aligns a source 3DGS scene with a user-defined target shape.<n>Our approach learns a deformation cage from the target, which guides the geometric transformation of the source scene.<n>Our method is highly flexible, accommodating various target shape representations, including texts, images, point clouds, meshes and 3DGS models.
• Score: 7.218737495375119
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As 3D Gaussian Splatting (3DGS) gains popularity as a 3D representation of real scenes, enabling user-friendly deformation to create novel scenes while preserving fine details from the original 3DGS has attracted significant research attention. We introduce CAGE-GS, a cage-based 3DGS deformation method that seamlessly aligns a source 3DGS scene with a user-defined target shape. Our approach learns a deformation cage from the target, which guides the geometric transformation of the source scene. While the cages effectively control structural alignment, preserving the textural appearance of 3DGS remains challenging due to the complexity of covariance parameters. To address this, we employ a Jacobian matrix-based strategy to update the covariance parameters of each Gaussian, ensuring texture fidelity post-deformation. Our method is highly flexible, accommodating various target shape representations, including texts, images, point clouds, meshes and 3DGS models. Extensive experiments and ablation studies on both public datasets and newly proposed scenes demonstrate that our method significantly outperforms existing techniques in both efficiency and deformation quality.

Related papers

• EG-Gaussian: Epipolar Geometry and Graph Network Enhanced 3D Gaussian Splatting [9.94641948288285]
  EG-Gaussian utilizes epipolar geometry and graph networks for 3D scene reconstruction. Our approach significantly improves reconstruction accuracy compared to 3DGS-based methods.
  arXiv  Detail & Related papers  (2025-04-18T08:10:39Z)
• Sketch-guided Cage-based 3D Gaussian Splatting Deformation [19.39701978836869]
  3D Gaussian Splatting (GS) is one of the most promising novel 3D representations. We present a sketch-guided 3D GS deformation system that allows users to intuitively modify the geometry of a 3D GS model.
  arXiv  Detail & Related papers  (2024-11-19T02:18:19Z)
• 3D Gaussian Editing with A Single Image [19.662680524312027]
  We introduce a novel single-image-driven 3D scene editing approach based on 3D Gaussian Splatting. Our method learns to optimize the 3D Gaussians to align with an edited version of the image rendered from a user-specified viewpoint. Experiments show the effectiveness of our method in handling geometric details, long-range, and non-rigid deformation.
  arXiv  Detail & Related papers  (2024-08-14T13:17:42Z)
• GSDeformer: Direct, Real-time and Extensible Cage-based Deformation for 3D Gaussian Splatting [8.727176816793179]
  We present GSDeformer, a method that enables cage-based deformation on 3D Gaussian Splatting (3DGS).<n>Our approach bridges cage-based deformation and 3DGS by using a proxy point-cloud representation.<n>Experiments demonstrate that GSDeformer delivers superior deformation results compared to existing methods, is robust under extreme deformations, requires no retraining for editing, runs in real-time, and can be extended to other 3DGS variants.
  arXiv  Detail & Related papers  (2024-05-24T12:16:28Z)
• DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus [56.45194233357833]
  We propose DoGaussian, a method that trains 3DGS distributedly. Our method accelerates the training of 3DGS by 6+ times when evaluated on large-scale scenes.
  arXiv  Detail & Related papers  (2024-05-22T19:17:58Z)
• SAGS: Structure-Aware 3D Gaussian Splatting [53.6730827668389]
  We propose a structure-aware Gaussian Splatting method (SAGS) that implicitly encodes the geometry of the scene. SAGS reflects to state-of-the-art rendering performance and reduced storage requirements on benchmark novel-view synthesis datasets.
  arXiv  Detail & Related papers  (2024-04-29T23:26:30Z)
• 3D Geometry-aware Deformable Gaussian Splatting for Dynamic View Synthesis [49.352765055181436]
  We propose a 3D geometry-aware deformable Gaussian Splatting method for dynamic view synthesis. Our solution achieves 3D geometry-aware deformation modeling, which enables improved dynamic view synthesis and 3D dynamic reconstruction.
  arXiv  Detail & Related papers  (2024-04-09T12:47:30Z)
• GaussianPro: 3D Gaussian Splatting with Progressive Propagation [49.918797726059545]
  3DGS relies heavily on the point cloud produced by Structure-from-Motion (SfM) techniques. We propose a novel method that applies a progressive propagation strategy to guide the densification of the 3D Gaussians. Our method significantly surpasses 3DGS on the dataset, exhibiting an improvement of 1.15dB in terms of PSNR.
  arXiv  Detail & Related papers  (2024-02-22T16:00:20Z)
• Mesh-based Gaussian Splatting for Real-time Large-scale Deformation [58.18290393082119]
  It is challenging for users to directly deform or manipulate implicit representations with large deformations in the real-time fashion. We develop a novel GS-based method that enables interactive deformation. Our approach achieves high-quality reconstruction and effective deformation, while maintaining the promising rendering results at a high frame rate.
  arXiv  Detail & Related papers  (2024-02-07T12:36:54Z)
• Geometry-Contrastive Transformer for Generalized 3D Pose Transfer [95.56457218144983]
  The intuition of this work is to perceive the geometric inconsistency between the given meshes with the powerful self-attention mechanism. We propose a novel geometry-contrastive Transformer that has an efficient 3D structured perceiving ability to the global geometric inconsistencies. We present a latent isometric regularization module together with a novel semi-synthesized dataset for the cross-dataset 3D pose transfer task.
  arXiv  Detail & Related papers  (2021-12-14T13:14:24Z)

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.