DP-DeGauss: Dynamic Probabilistic Gaussian Decomposition for Egocentric 4D Scene Reconstruction

• URL: http://arxiv.org/abs/2604.07986v1
• Date: Thu, 09 Apr 2026 08:55:39 GMT
• Title: DP-DeGauss: Dynamic Probabilistic Gaussian Decomposition for Egocentric 4D Scene Reconstruction
• Abstract summary: We introduce DP-DeGauss, a dynamic probabilistic Gaussian decomposition framework for egocentric 4D reconstruction.<n>Our method initializes a unified 3D Gaussian set from COLMAP priors, augments each with a learnable category probability, and dynamically routes them into specialized deformation branches.<n>Experiments show that DP-DeGauss outperforms baselines by +1.70dB in PSNR on average with SSIM and LPIPS gains.
• Score: 23.80176859000243
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Egocentric video is crucial for next-generation 4D scene reconstruction, with applications in AR/VR and embodied AI. However, reconstructing dynamic first-person scenes is challenging due to complex ego-motion, occlusions, and hand-object interactions. Existing decomposition methods are ill-suited, assuming fixed viewpoints or merging dynamics into a single foreground. To address these limitations, we introduce DP-DeGauss, a dynamic probabilistic Gaussian decomposition framework for egocentric 4D reconstruction. Our method initializes a unified 3D Gaussian set from COLMAP priors, augments each with a learnable category probability, and dynamically routes them into specialized deformation branches for background, hands, or object modeling. We employ category-specific masks for better disentanglement and introduce brightness and motion-flow control to improve static rendering and dynamic reconstruction. Extensive experiments show that DP-DeGauss outperforms baselines by +1.70dB in PSNR on average with SSIM and LPIPS gains. More importantly, our framework achieves the first and state-of-the-art disentanglement of background, hand, and object components, enabling explicit, fine-grained separation, paving the way for more intuitive ego scene understanding and editing.

Related papers

• Hand-4DGS: Feed-Forward 3D Gaussian Splatting for 4D Hand Reconstruction from Egocentric Videos [54.612320509347825]
  We introduce Hand-4DGS, the first feed-forward framework for reconstructing dynamic 4D hands directly from egocentric videos.<n>Our approach incorporates a mesh-guided representation for structural priors and temporal convolutions to model dynamic motion.
  arXiv  Detail & Related papers  (2026-06-17T14:58:37Z)
• JOintGS: Joint Optimization of Cameras, Bodies and 3D Gaussians for In-the-Wild Monocular Reconstruction [18.636227266388218]
  We present JOintGS, a unified framework that jointly optimize camera extrinsics, human poses, and 3D Gaussian representations.<n>Experiments on NeuMan and EMDB datasets demonstrate that JOintGS achieves superior reconstruction quality.
  arXiv  Detail & Related papers  (2026-02-04T08:33:51Z)
• Tessellation GS: Neural Mesh Gaussians for Robust Monocular Reconstruction of Dynamic Objects [41.62908563782648]
  3D Gaussian Splatting (GS) enables highly photorealistic scene reconstruction from posed image sequences but struggles with viewpoint extrapolation.<n>We propose Tessellation GS, a structured 2D GS approach anchored on mesh faces, to reconstruct dynamic scenes from a single continuously moving or static camera.<n>Our method constrains 2D Gaussians to localized regions and infers their attributes via hierarchical neural features on mesh faces.
  arXiv  Detail & Related papers  (2025-12-08T10:16:14Z)
• 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos [52.89084603734664]
  We present 4D3R, a pose-free dynamic neural rendering framework that decouples static and dynamic components through a two-stage approach.<n>Our approach achieves up to 1.8dB PSNR improvement over state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-11-07T13:25:50Z)
• 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)
• UAV4D: Dynamic Neural Rendering of Human-Centric UAV Imagery using Gaussian Splatting [54.883935964137706]
  We introduce UAV4D, a framework for enabling photorealistic rendering for dynamic real-world scenes captured by UAVs.<n>We use a combination of a 3D foundation model and a human mesh reconstruction model to reconstruct both the scene background and humans.<n>Our results demonstrate the benefits of our approach over existing methods in novel view synthesis, achieving a 1.5 dB PSNR improvement and superior visual sharpness.
  arXiv  Detail & Related papers  (2025-06-05T13:21:09Z)
• UnIRe: Unsupervised Instance Decomposition for Dynamic Urban Scene Reconstruction [36.00679909382783]
  We propose UnIRe, a 3D Splatting (3DGS) based approach that decomposes a scene into a static background and individual dynamic instances.<n>At its core, we introduce 4D superpoints, a novel representation that clusters multi-frame LiDAR points in 4D space.<n>Experiments show that our method outperforms existing methods in dynamic scene reconstruction while enabling accurate and flexible instance-level editing.
  arXiv  Detail & Related papers  (2025-04-01T13:15:58Z)
• Event-boosted Deformable 3D Gaussians for Dynamic Scene Reconstruction [50.873820265165975]
  We introduce the first approach combining event cameras, which capture high-temporal-resolution, continuous motion data, with deformable 3D-GS for dynamic scene reconstruction.<n>We propose a GS-Threshold Joint Modeling strategy, creating a mutually reinforcing process that greatly improves both 3D reconstruction and threshold modeling.<n>We contribute the first event-inclusive 4D benchmark with synthetic and real-world dynamic scenes, on which our method achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-11-25T08:23:38Z)
• DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes [71.61083731844282]
  We present DeSiRe-GS, a self-supervised gaussian splatting representation.<n>It enables effective static-dynamic decomposition and high-fidelity surface reconstruction in complex driving scenarios.
  arXiv  Detail & Related papers  (2024-11-18T05:49:16Z)
• EgoGaussian: Dynamic Scene Understanding from Egocentric Video with 3D Gaussian Splatting [95.44545809256473]
  EgoGaussian is a method capable of simultaneously reconstructing 3D scenes and dynamically tracking 3D object motion from RGB egocentric input alone. We show significant improvements in terms of both dynamic object and background reconstruction quality compared to the state-of-the-art.
  arXiv  Detail & Related papers  (2024-06-28T10:39:36Z)

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.