Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction

• URL: http://arxiv.org/abs/2605.31595v1
• Date: Fri, 29 May 2026 17:57:41 GMT
• Title: Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction
• Abstract summary: We present C4G, a feed-forward 4D reconstruction framework built upon a compact set of timestamp-conditioned learnable Gaussian query tokens.<n>C4G achieves strong novel-view synthesis performance using significantly fewer Gaussians and without requiring camera poses.
• Score: 49.87425331212591
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dynamic scene reconstruction from monocular video remains a fundamental challenge in computer vision. Existing feed-forward methods predict 3D Gaussians pixel-wise for each frame, suffering from duplicated Gaussians and view-dependent biases that hinder effective learning of scene motion. We present C4G, a feed-forward 4D reconstruction framework built upon a compact set of timestamp-conditioned learnable Gaussian query tokens. Each token aggregates corresponding features across the full temporal context and decodes a 3D Gaussian whose position is modulated by the target timestamp, enabling globally coherent motion modeling without per-scene optimization. To capture fine-grained details, we further introduce a video diffusion model-based rendering enhancement module. Since our framework effectively aggregates features into Gaussians, we extend this capability to feature lifting, producing a 4D feature field that supports point tracking and dynamic scene understanding. C4G achieves strong novel-view synthesis performance using significantly fewer Gaussians and without requiring camera poses, while exhibiting stronger motion modeling and robustness to large temporal gaps.

Related papers

• EVolSplat4D: Efficient Volume-based Gaussian Splatting for 4D Urban Scene Synthesis [43.898895514609286]
  EvolSplat4D is a feed-forward framework that moves beyond existing per-pixel paradigms by unifying volume-based and pixel-based Gaussian prediction.<n>We show that EvolSplat4D reconstructs both static and dynamic environments with superior accuracy and consistency, outperforming both per-scene optimization and state-of-the-art feed-forward baselines.
  arXiv  Detail & Related papers  (2026-01-22T13:39:29Z)
• 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)
• ShapeGen4D: Towards High Quality 4D Shape Generation from Videos [85.45517487721257]
  We introduce a native video-to-4D shape generation framework that synthesizes a single dynamic 3D representation end-to-end from the video.<n>Our method accurately captures non-rigid motion, volume changes, and even topological transitions without per-frame optimization.
  arXiv  Detail & Related papers  (2025-10-07T17:58:11Z)
• Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-view Videos [27.595035122927204]
  We present a feed-forward 4D human reconstruction and model that efficientlycalibrates temporally aligned representations from uncalibrated sparse-view videos.<n>For novel time, we design a novel motion prediction module to predict dense motions for each 3D Gaussian between two adjacent frames.<n>Experiments demonstrate the effectiveness of our model on both in-domain and out-of-domain datasets.
  arXiv  Detail & Related papers  (2025-09-29T02:47:14Z)
• 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)
• CoDa-4DGS: Dynamic Gaussian Splatting with Context and Deformation Awareness for Autonomous Driving [12.006435326659526]
  We introduce a novel 4D Gaussian Splatting (4DGS) approach to improve dynamic scene rendering.<n> Specifically, we employ a 2D semantic segmentation foundation model to self-supervise the 4D semantic features of Gaussians.<n>By aggregating and encoding both semantic and temporal deformation features, each Gaussian is equipped with cues for potential deformation compensation.
  arXiv  Detail & Related papers  (2025-03-09T19:58:51Z)
• 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)
• Deblur4DGS: 4D Gaussian Splatting from Blurry Monocular Video [55.704264233274294]
  We propose Deblur4DGS to reconstruct a high-quality 4D model from blurry monocular video.<n>We transform continuous dynamic representations within an exposure time into the exposure time estimation.<n>Beyond novel-view synthesis, Deblur4DGS can be applied to improve blurry video from multiple perspectives.
  arXiv  Detail & Related papers  (2024-12-09T12:02:11Z)
• H3D-DGS: Exploring Heterogeneous 3D Motion Representation for Deformable 3D Gaussian Splatting [39.2960379257236]
  Dynamic scene reconstruction poses a persistent challenge in 3D vision.<n>Deformable 3D Gaussian splatting has emerged as an effective method for this task, offering real-time rendering and high visual fidelity.<n>This approach decomposes a dynamic scene into a static representation in a canonical space and time-varying scene motion.<n>Experiments on the Neu3DV and CMU-Panoptic datasets demonstrate that our method achieves superior performance over state-of-the-art deformable 3D Gaussian splatting techniques.
  arXiv  Detail & Related papers  (2024-08-23T12:51:49Z)
• MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds [27.802537831023347]
  We introduce 4D Motion Scaffolds (MoSca), a modern 4D reconstruction system designed to reconstruct and synthesize novel views of dynamic scenes from monocular videos captured casually in the wild.<n> Experiments demonstrate state-of-the-art performance on dynamic rendering benchmarks and its effectiveness on real videos.
  arXiv  Detail & Related papers  (2024-05-27T17:59:07Z)
• 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)
• Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models [94.07744207257653]
  We focus on the underexplored text-to-4D setting and synthesize dynamic, animated 3D objects. We combine text-to-image, text-to-video, and 3D-aware multiview diffusion models to provide feedback during 4D object optimization.
  arXiv  Detail & Related papers  (2023-12-21T11:41:02Z)

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.