REArtGS++: Generalizable Articulation Reconstruction with Temporal Geometry Constraint via Planar Gaussian Splatting

• URL: http://arxiv.org/abs/2511.17059v2
• Date: Mon, 24 Nov 2025 04:58:36 GMT
• Title: REArtGS++: Generalizable Articulation Reconstruction with Temporal Geometry Constraint via Planar Gaussian Splatting
• Abstract summary: We propose REArtGS++, a novel method towards generalizable articulated object reconstruction.<n>We first model a decoupled screw motion for each joint without type prior, and jointly optimize part-aware Gaussians with joint parameters.<n>Experiments on both synthetic and real-world articulated objects demonstrate our superiority in generalizable part-level surface reconstruction and joint parameter estimation.
• Score: 44.02799256666578
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Articulated objects are pervasive in daily environments, such as drawers and refrigerators. Towards their part-level surface reconstruction and joint parameter estimation, REArtGS introduces a category-agnostic approach using multi-view RGB images at two different states. However, we observe that REArtGS still struggles with screw-joint or multi-part objects and lacks geometric constraints for unseen states. In this paper, we propose REArtGS++, a novel method towards generalizable articulated object reconstruction with temporal geometry constraint and planar Gaussian splatting. We first model a decoupled screw motion for each joint without type prior, and jointly optimize part-aware Gaussians with joint parameters through part motion blending. To introduce time-continuous geometric constraint for articulated modeling, we encourage Gaussians to be planar and propose a temporally consistent regularization between planar normal and depth through Taylor first-order expansion. Extensive experiments on both synthetic and real-world articulated objects demonstrate our superiority in generalizable part-level surface reconstruction and joint parameter estimation, compared to existing approaches. Project Site: https://sites.google.com/view/reartgs2/home.

Related papers

• Artic-O: End-to-End Articulated Object Reconstruction via Latent Geometry Learning [105.35529379360186]
  Artic-O is an end-to-end, feed-forward framework for articulated object reconstruction.<n>It maps sparse multi-state observations into a pretrained latent geometry space.<n>A frozen flow-matching decoder provides a complete-shape prior for recovering visible and occluded structures.
  arXiv  Detail & Related papers  (2026-06-20T08:15:30Z)
• ArtSplat: Feed-Forward Articulated 3D Gaussian Splatting from Sparse Multi-State Uncalibrated Views [26.73085272044419]
  ArtSplat is the first feed-forward framework for articulated 3D Gaussian Splatting.<n>It reconstructs both geometry and joint parameters from sparse multi-view images across multiple articulation states in a single forward pass.<n>Experiments on 68 articulated objects from PartNet-Mobility, including both single- and multi-joint configurations, demonstrate that ArtSplat achieves competitive performance in both geometry and joint estimation, while being over 400 times faster than baselines.
  arXiv  Detail & Related papers  (2026-05-23T00:31:47Z)
• Mind the Gap: Geometrically Accurate Generative Reconstruction from Disjoint Views [0.8435195043404353]
  We introduce Generative Reconstruction from Disjoint Views as a new paradigm.<n>We propose GLADOS, a general, modular framework that operates through three stages.<n>As an architectureagnostic framework, GLADOS enables seamless integration of future advances in generation, reconstruction, and inpainting.
  arXiv  Detail & Related papers  (2026-05-08T10:24:23Z)
• GEAR: GEometry-motion Alternating Refinement for Articulated Object Modeling with Gaussian Splatting [47.344503859540914]
  We propose GEAR, an EM-style alternating optimization framework that jointly models geometry and motion as interdependent components.<n>GEAR treats part segmentation as a latent variable and joint motion parameters as explicit variables, alternately refining them for improved convergence and geometric-motion consistency.<n>Experiments on multiple benchmarks and our newly constructed dataset GEAR-Multi demonstrate that GEAR achieves state-of-the-art results in geometric reconstruction and motion parameters estimation.
  arXiv  Detail & Related papers  (2026-04-09T02:24:39Z)
• Joint Geometry-Appearance Human Reconstruction in a Unified Latent Space via Bridge Diffusion [57.09673862519791]
  This paper introduces textbfJGA-LBD, a novel framework that unifies the modeling of geometry and appearance into a joint latent representation.<n> Experiments demonstrate that JGA-LBD outperforms current state-of-the-art approaches in terms of both geometry fidelity and appearance quality.
  arXiv  Detail & Related papers  (2026-01-01T12:48:56Z)
• G3Splat: Geometrically Consistent Generalizable Gaussian Splatting [30.752029360892504]
  We introduce G3Splat, which enforces geometric priors to obtain geometrically consistent 3D scene representations.<n>Trained on RE10K, our approach achieves state-of-the-art performance in (i) geometrically consistent reconstruction, (ii) relative pose estimation, and (iii) novel-view synthesis.
  arXiv  Detail & Related papers  (2025-12-19T13:11:55Z)
• OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting [78.70702961852119]
  OracleGS reconciles generative completeness with regressive fidelity for sparse view Gaussian Splatting.<n>Our approach conditions the powerful generative prior on multi-view geometric evidence, filtering hallucinatory artifacts while preserving plausible completions in under-constrained regions.
  arXiv  Detail & Related papers  (2025-09-27T11:19:32Z)
• On the Geometric Accuracy of Implicit and Primitive-based Representations Derived from View Rendering Constraints [15.120134539151236]
  We compare implicit and explicit Novel View Synthesis methods for space-based 3D object reconstruction.<n>We show embeddings do not translate into meaningful gains in geometric accuracy.<n>Our findings clarify the limits of appearance embeddings for geometry-centric tasks.
  arXiv  Detail & Related papers  (2025-09-12T13:37:18Z)
• Follow My Hold: Hand-Object Interaction Reconstruction through Geometric Guidance [61.41904916189093]
  We propose a novel diffusion-based framework for reconstructing 3D geometry of hand-held objects from monocular RGB images.<n>We use hand-object interaction as geometric guidance to ensure plausible hand-object interactions.
  arXiv  Detail & Related papers  (2025-08-25T17:11:53Z)
• GaussianArt: Unified Modeling of Geometry and Motion for Articulated Objects [4.717906057951389]
  We introduce a unified representation that jointly models geometry and motion using articulated 3D Gaussians.<n>This formulation improves robustness in motion decomposition and supports articulated objects with up to 20 parts.<n>We show that our method consistently achieves superior accuracy in part-level geometry reconstruction and motion estimation across a broad range of object types.
  arXiv  Detail & Related papers  (2025-08-20T17:59:08Z)
• A Mixed-Primitive-based Gaussian Splatting Method for Surface Reconstruction [61.205927223522174]
  We propose a novel framework that enables Gaussian Splatting to incorporate multiple types of primitives during its surface reconstruction process.<n>Specifically, in our framework, we first propose a compositional splatting strategy, enabling the splatting and rendering of different types of primitives.
  arXiv  Detail & Related papers  (2025-07-15T13:52:40Z)
• VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction [47.603017811399624]
  We propose a Depth-Normal regularizer that directly couples normal with other geometric parameters, leading to full updates of the geometric parameters from normal regularization. We also introduce a densification and splitting strategy to regularize the size and distribution of 3D Gaussians for more accurate surface modeling.
  arXiv  Detail & Related papers  (2024-06-09T13:15:43Z)
• Learning Constrained Dynamic Correlations in Spatiotemporal Graphs for Motion Prediction [4.504430414983527]
  Human motion prediction is challenging due to the complextemporal feature modeling. Within a graph convolution network (GCN), the graph adjacency matrix drives feature aggregation. We propose dynamictemporal GC (D-STD-GC), which only takes 28.6% of the state-of-the-art GC.
  arXiv  Detail & Related papers  (2022-04-04T08:11:06Z)

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.