Generative 4D Scene Gaussian Splatting with Object View-Synthesis Priors

• URL: http://arxiv.org/abs/2506.12716v1
• Date: Sun, 15 Jun 2025 04:40:20 GMT
• Title: Generative 4D Scene Gaussian Splatting with Object View-Synthesis Priors
• Abstract summary: GenMOJO is a novel approach that integrates rendering-based deformable 3D Gaussian optimization with generative priors for view synthesis.<n>It decomposes the scene into individual objects, optimizing a differentiable set of deformable Gaussians per object.<n>The resulting model generates 4D object reconstructions over space and time, and produces accurate 2D and 3D point tracks from monocular input.
• Score: 22.797709893040906
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: We tackle the challenge of generating dynamic 4D scenes from monocular, multi-object videos with heavy occlusions, and introduce GenMOJO, a novel approach that integrates rendering-based deformable 3D Gaussian optimization with generative priors for view synthesis. While existing models perform well on novel view synthesis for isolated objects, they struggle to generalize to complex, cluttered scenes. To address this, GenMOJO decomposes the scene into individual objects, optimizing a differentiable set of deformable Gaussians per object. This object-wise decomposition allows leveraging object-centric diffusion models to infer unobserved regions in novel viewpoints. It performs joint Gaussian splatting to render the full scene, capturing cross-object occlusions, and enabling occlusion-aware supervision. To bridge the gap between object-centric priors and the global frame-centric coordinate system of videos, GenMOJO uses differentiable transformations that align generative and rendering constraints within a unified framework. The resulting model generates 4D object reconstructions over space and time, and produces accurate 2D and 3D point tracks from monocular input. Quantitative evaluations and perceptual human studies confirm that GenMOJO generates more realistic novel views of scenes and produces more accurate point tracks compared to existing approaches.

Related papers

• GaussianSelector: Lightweight Human-Guided Object Selection in 3D Gaussian Splatting with Graph Optimization [18.39349689479339]
  GaussianSelector is a training-free framework for interactive 3D object selection from sparse views and scribble guidance.<n>It achieves competitive selection quality against state-of-the-art multi-view SAM-based methods.<n>It is well suited for human-in-the-loop 3D scene editing and 3D asset extraction in real-world deployment scenarios.
  arXiv  Detail & Related papers  (2026-08-02T20:51:09Z)
• World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video [62.16750462940772]
  We present World from Motion, a method for generating freely renderable dynamic 3D Gaussian representations from monocular videos.<n>Our approach conditions a video model on dense, pixel-aligned renderings that encode appearance, geometry, and 3D scene motion.<n>At test time, we distill the model's generations back into a single consistent, high-quality dynamic 3DGS, improving both novel-view synthesis and the underlying 3D motion.
  arXiv  Detail & Related papers  (2026-07-01T17:41:00Z)
• Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding [54.859943475818234]
  We present Motion4D, a novel framework that integrates 2D priors from foundation models into a unified 4D Gaussian Splatting representation.<n>Our method features a two-part iterative optimization framework: 1) Sequential optimization, which updates motion and semantic fields in consecutive stages to maintain local consistency, and 2) Global optimization, which jointly refines all attributes for long-term coherence.<n>Our method significantly outperforms both 2D foundation models and existing 3D-based approaches across diverse scene understanding tasks, including point-based tracking, video object segmentation, and novel view synthesis.
  arXiv  Detail & Related papers  (2025-12-03T09:32:56Z)
• Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models [79.06910348413861]
  We introduce Diff4Splat, a feed-forward method that synthesizes controllable and explicit 4D scenes from a single image.<n>Given a single input image, a camera trajectory, and an optional text prompt, Diff4Splat directly predicts a deformable 3D Gaussian field that encodes appearance, geometry, and motion.
  arXiv  Detail & Related papers  (2025-11-01T11:16:25Z)
• FMGS-Avatar: Mesh-Guided 2D Gaussian Splatting with Foundation Model Priors for 3D Monocular Avatar Reconstruction [18.570290675633732]
  We introduce Mesh-Guided 2D Gaussian Splatting, where 2D primitives are attached directly to template mesh faces with constrained position, rotation, and movement.<n>We leverage foundation models trained on large-scale datasets, such as Sapiens, to complement the limited visual cues from monocular videos.<n> Experimental evaluation demonstrates superior reconstruction quality compared to existing methods, with notable gains in geometric accuracy and appearance fidelity.
  arXiv  Detail & Related papers  (2025-09-18T08:41:41Z)
• A Controllable 3D Deepfake Generation Framework with Gaussian Splatting [6.969908558294805]
  We propose a novel 3D deepfake generation framework based on 3D Gaussian Splatting.<n>It enables realistic, identity-preserving face swapping and reenactment in a fully controllable 3D space.<n>Our approach bridges the gap between 3D modeling and deepfake synthesis, enabling new directions for scene-aware, controllable, and immersive visual forgeries.
  arXiv  Detail & Related papers  (2025-09-15T06:34:17Z)
• HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis [59.25751939710903]
  We propose a novel deformable Gaussian splatting framework that addresses embodied view synthesis from long monocular RGB videos.<n>Our method leverages invertible Gaussian Splatting deformation networks to reconstruct large-scale, dynamic environments accurately.<n>Results highlight a practical and scalable solution for EVS in real-world scenarios.
  arXiv  Detail & Related papers  (2025-06-24T03:54:40Z)
• BulletGen: Improving 4D Reconstruction with Bullet-Time Generation [15.225127596594582]
  We introduce BulletGen, an approach that takes advantage of generative models to correct errors and complete missing information in a dynamic scene representation.<n>Our method seamlessly blends generative content with both static and dynamic scene components, achieving state-of-the-art results on both novel-view synthesis, and 2D/3D tracking tasks.
  arXiv  Detail & Related papers  (2025-06-23T13:03:42Z)
• CasaGPT: Cuboid Arrangement and Scene Assembly for Interior Design [35.11283253765395]
  We present a novel approach for indoor scene synthesis, which learns to arrange decomposed cuboid primitives to represent 3D objects within a scene.<n>Our approach, coined CasaGPT for Cuboid Arrangement and Scene Assembly, employs an autoregressive model to sequentially arrange cuboids, producing physically plausible scenes.
  arXiv  Detail & Related papers  (2025-04-28T04:35:04Z)
• 4D Gaussian Splatting: Modeling Dynamic Scenes with Native 4D Primitives [115.67081491747943]
  Dynamic 3D scene representation and novel view synthesis are crucial for enabling AR/VR and metaverse applications.<n>We reformulate the reconstruction of a time-varying 3D scene as approximating its underlying 4D volume.<n>We derive several compact variants that effectively reduce the memory footprint to address its storage bottleneck.
  arXiv  Detail & Related papers  (2024-12-30T05:30:26Z)
• HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting [47.67153284714988]
  We propose a novel hybrid representation, termed as HybridGS, using 2D Gaussians for transient objects per image.<n>We also propose a straightforward yet effective multi-stage training strategy to ensure robust training and high-quality view synthesis.<n> Experiments on benchmark datasets show our state-of-the-art performance of novel view synthesis in both indoor and outdoor scenes.
  arXiv  Detail & Related papers  (2024-12-05T03:20:35Z)
• NovelGS: Consistent Novel-view Denoising via Large Gaussian Reconstruction Model [57.92709692193132]
  NovelGS is a diffusion model for Gaussian Splatting given sparse-view images. We leverage the novel view denoising through a transformer-based network to generate 3D Gaussians.
  arXiv  Detail & Related papers  (2024-11-25T07:57:17Z)
• GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Views [67.34073368933814]
  We propose a generalizable Gaussian Splatting approach for high-resolution image rendering under a sparse-view camera setting. We train our Gaussian parameter regression module on human-only data or human-scene data, jointly with a depth estimation module to lift 2D parameter maps to 3D space. Experiments on several datasets demonstrate that our method outperforms state-of-the-art methods while achieving an exceeding rendering speed.
  arXiv  Detail & Related papers  (2024-11-18T08:18:44Z)
• DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation [10.250715657201363]
  We introduce DreamMesh4D, a novel framework combining mesh representation with geometric skinning technique to generate high-quality 4D object from a monocular video. Our method is compatible with modern graphic pipelines, showcasing its potential in the 3D gaming and film industry.
  arXiv  Detail & Related papers  (2024-10-09T10:41:08Z)
• SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfer [57.506654943449796]
  We propose an efficient, sparse-controlled video-to-4D framework named SC4D that decouples motion and appearance. Our method surpasses existing methods in both quality and efficiency. We devise a novel application that seamlessly transfers motion onto a diverse array of 4D entities.
  arXiv  Detail & Related papers  (2024-04-04T18:05:18Z)

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.