SMG: Semantic Motion Graph for Monocular Dynamic Gaussian Splatting

• URL: http://arxiv.org/abs/2608.31023v1
• Date: Mon, 31 Aug 2026 16:06:18 GMT
• Title: SMG: Semantic Motion Graph for Monocular Dynamic Gaussian Splatting
• Abstract summary: We study dynamic Gaussian splatting from monocular videos.<n>We propose Semantic Motion Graph (SMG), a novel approach models the Gaussian motion as the low-rank semantic motion.<n>SMG achieves state-of-the-art performance on monocular dynamic Gaussian splatting across challenging real-world benchmarks.
• Score: 38.701129917214146
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study dynamic Gaussian Splatting from monocular videos. While recent advancements in dynamic Gaussian splatting offer a promising foundation for modeling dynamic scenes, they often overfit to the training views and fail under occlusion or complex scene motion due to the lack of reliable regularization signals in under-constrained regions. We propose Semantic Motion Graph (SMG), a novel approach models the Gaussian motion as the low-rank semantic motion. Our key insight is that the real-world scene motion is often structured by semantic coherence: regions that are spatially close and semantically related tend to exhibit consistent dynamics. To leverage this prior, we construct SMG to model structured motion of the scene. The Gaussian motion is driven by the motion of SMG nodes. We further observe that the uncertainty of Gaussian motion arises from both unreliable off-the-shelf priors and weakly constrained regions during optimization. SMG addresses this by using reliable graph nodes to guide the motion of nearby unreliable nodes. To evaluate dynamic Gaussian splatting under challenging real-world scenarios, we introduce a new multiview dataset collected under an ego-exo setup. Extensive experiments demonstrate that SMG achieves state-of-the-art performance on monocular dynamic Gaussian splatting across challenging real-world benchmarks. Project page: https://smg-gaussian.github.io/.

Related papers

• RiGS: Rigid-aware 4D Gaussian Splatting from a Single Monocular Video [38.8840959968641]
  We present Rigid-aware 4D Gaussian Splatting (RiGS), which simultaneously captures motions across multiple temporal scales.<n>RiGS achieves state-of-the-art performance on novel view synthesis benchmarks.
  arXiv  Detail & Related papers  (2026-05-22T14:20:39Z)
• Space-Time Forecasting of Dynamic Scenes with Motion-aware Gaussian Grouping [47.282424020983996]
  MoGaF is a framework for long-term scene extrapolation built upon the 4D Gaussian Splatting representation.<n>A lightweight forecasting module predicts future motion, enabling realistic and temporally stable scene evolution.<n>Experiments on synthetic and real-world datasets demonstrate that MoGaF consistently outperforms existing baselines in rendering quality, motion plausibility, and long-term forecasting stability.
  arXiv  Detail & Related papers  (2026-02-25T08:04:07Z)
• ParticleGS: Particle-Based Dynamics Modeling of 3D Gaussians for Prior-free Motion Extrapolation [9.59448024784555]
  We propose a novel dynamic 3D Gaussian Splatting prior-free motion extrapolation framework based on particle dynamics systems.<n>Instead of simply fitting to the observed visual frame sequence, we aim to more effectively model the gaussian particle dynamics system.<n> Experimental results demonstrate that the proposed method achieves comparable rendering quality with existing approaches in reconstruction tasks.
  arXiv  Detail & Related papers  (2025-05-26T17:46:35Z)
• Motion Blender Gaussian Splatting for Dynamic Scene Reconstruction [32.64620619764744]
  Motion Blender Gaussian Splatting (MBGS) is a novel framework that uses motion graphs as an explicit and sparse motion representation.<n>MBGS achieves state-of-the-art performance on the highly challenging iPhone dataset.<n>We demonstrate the application potential of our method in animating novel object poses, synthesizing real robot demonstrations, and predicting robot actions through visual planning.
  arXiv  Detail & Related papers  (2025-03-12T03:55:16Z)
• Efficient Gaussian Splatting for Monocular Dynamic Scene Rendering via Sparse Time-Variant Attribute Modeling [64.84686527988809]
  Deformable Gaussian Splatting has emerged as a robust solution to represent real-world dynamic scenes.<n>Our approach formulates dynamic scenes using a sparse anchor-grid representation, with the motion flow of dense Gaussians calculated via a classical kernel representation.<n>Experiments on two real-world datasets demonstrate that our EDGS significantly improves the rendering speed with superior rendering quality.
  arXiv  Detail & Related papers  (2025-02-27T18:53:06Z)
• MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting [56.785233997533794]
  We propose a novel deformable 3D Gaussian splatting framework called MotionGS. MotionGS explores explicit motion priors to guide the deformation of 3D Gaussians. Experiments in the monocular dynamic scenes validate that MotionGS surpasses state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-10-10T08:19:47Z)
• Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular Videos [58.22272760132996]
  We show that existing 4D Gaussian methods dramatically fail in this setup because the monocular setting is underconstrained. We propose Dynamic Gaussian Marbles, which consist of three core modifications that target the difficulties of the monocular setting. We evaluate on the Nvidia Dynamic Scenes dataset and the DyCheck iPhone dataset, and show that Gaussian Marbles significantly outperforms other Gaussian baselines in quality.
  arXiv  Detail & Related papers  (2024-06-26T19:37:07Z)
• GaussianPrediction: Dynamic 3D Gaussian Prediction for Motion Extrapolation and Free View Synthesis [71.24791230358065]
  We introduce a novel framework that empowers 3D Gaussian representations with dynamic scene modeling and future scenario synthesis. GaussianPrediction can forecast future states from any viewpoint, using video observations of dynamic scenes. Our framework shows outstanding performance on both synthetic and real-world datasets, demonstrating its efficacy in predicting and rendering future environments.
  arXiv  Detail & Related papers  (2024-05-30T06:47:55Z)

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.