RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenes

• URL: http://arxiv.org/abs/2403.09419v2
• Date: Wed, 17 Jul 2024 13:43:54 GMT
• Title: RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenes
• Authors: Thang-Anh-Quan Nguyen, Luis Roldão, Nathan Piasco, Moussab Bennehar, Dzmitry Tsishkou,
• Abstract summary: We present RoDUS, a pipeline for decomposing static and dynamic elements in urban scenes. Our approach utilizes a robust kernel-based initialization coupled with 4D semantic information to selectively guide the learning process. Notably, experimental evaluations on KITTI-360 and Pandaset datasets demonstrate the effectiveness of our method in decomposing challenging urban scenes into precise static and dynamic components.
• Score: 3.1224202646855903
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The task of separating dynamic objects from static environments using NeRFs has been widely studied in recent years. However, capturing large-scale scenes still poses a challenge due to their complex geometric structures and unconstrained dynamics. Without the help of 3D motion cues, previous methods often require simplified setups with slow camera motion and only a few/single dynamic actors, leading to suboptimal solutions in most urban setups. To overcome such limitations, we present RoDUS, a pipeline for decomposing static and dynamic elements in urban scenes, with thoughtfully separated NeRF models for moving and non-moving components. Our approach utilizes a robust kernel-based initialization coupled with 4D semantic information to selectively guide the learning process. This strategy enables accurate capturing of the dynamics in the scene, resulting in reduced floating artifacts in the reconstructed background, all by using self-supervision. Notably, experimental evaluations on KITTI-360 and Pandaset datasets demonstrate the effectiveness of our method in decomposing challenging urban scenes into precise static and dynamic components.

Related papers

• Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction [78.27956235915622]
  Traditional SLAM systems struggle with highly dynamic scenes commonly found in casual videos. This work leverages a 3D point tracker to separate the camera-induced motion from the observed motion of dynamic objects. Our framework combines the core of traditional SLAM -- bundle adjustment -- with a robust learning-based 3D tracker front-end.
  arXiv  Detail & Related papers  (2025-04-20T07:29:42Z)
• DeGauss: Dynamic-Static Decomposition with Gaussian Splatting for Distractor-free 3D Reconstruction [10.683829048617897]
  We introduce DeGauss, a self-supervised framework for dynamic scene reconstruction based on a decoupled dynamic-static Gaussian Splatting design. DeGauss generalizes robustly across a wide range of real-world scenarios, from casual image collections to long, dynamic egocentric videos. Experiments on benchmarks including NeRF-on-the-go, ADT, AEA, Hot3D, and EPIC-Fields demonstrate that DeGauss consistently outperforms existing methods.
  arXiv  Detail & Related papers  (2025-03-17T13:53:04Z)
• UrbanGS: Semantic-Guided Gaussian Splatting for Urban Scene Reconstruction [86.4386398262018]
  UrbanGS uses 2D semantic maps and an existing dynamic Gaussian approach to distinguish static objects from the scene. For potentially dynamic objects, we aggregate temporal information using learnable time embeddings. Our approach outperforms state-of-the-art methods in reconstruction quality and efficiency.
  arXiv  Detail & Related papers  (2024-12-04T16:59:49Z)
• 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. We propose a GS-Threshold Joint Modeling strategy, creating a mutually reinforcing process that greatly improves both 3D reconstruction and threshold modeling. 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)
• MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion [118.74385965694694]
  We present Motion DUSt3R (MonST3R), a novel geometry-first approach that directly estimates per-timestep geometry from dynamic scenes. By simply estimating a pointmap for each timestep, we can effectively adapt DUST3R's representation, previously only used for static scenes, to dynamic scenes. We show that by posing the problem as a fine-tuning task, identifying several suitable datasets, and strategically training the model on this limited data, we can surprisingly enable the model to handle dynamics.
  arXiv  Detail & Related papers  (2024-10-04T18:00:07Z)
• DENSER: 3D Gaussians Splatting for Scene Reconstruction of Dynamic Urban Environments [0.0]
  We propose DENSER, a framework that significantly enhances the representation of dynamic objects. The proposed approach significantly outperforms state-of-the-art methods by a wide margin.
  arXiv  Detail & Related papers  (2024-09-16T07:11:58Z)
• Dynamic Scene Understanding through Object-Centric Voxelization and Neural Rendering [57.895846642868904]
  We present a 3D generative model named DynaVol-S for dynamic scenes that enables object-centric learning. voxelization infers per-object occupancy probabilities at individual spatial locations. Our approach integrates 2D semantic features to create 3D semantic grids, representing the scene through multiple disentangled voxel grids.
  arXiv  Detail & Related papers  (2024-07-30T15:33:58Z)
• Shape of Motion: 4D Reconstruction from a Single Video [51.04575075620677]
  We introduce a method capable of reconstructing generic dynamic scenes, featuring explicit, full-sequence-long 3D motion. We exploit the low-dimensional structure of 3D motion by representing scene motion with a compact set of SE3 motion bases. Our method achieves state-of-the-art performance for both long-range 3D/2D motion estimation and novel view synthesis on dynamic scenes.
  arXiv  Detail & Related papers  (2024-07-18T17:59:08Z)
• 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)
• Modeling Ambient Scene Dynamics for Free-view Synthesis [31.233859111566613]
  We introduce a novel method for dynamic free-view synthesis of an ambient scenes from a monocular capture. Our method builds upon the recent advancements in 3D Gaussian Splatting (3DGS) that can faithfully reconstruct complex static scenes.
  arXiv  Detail & Related papers  (2024-06-13T17:59:11Z)
• Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sampling [70.34875558830241]
  We present a way for learning a-temporal (4D) embedding, based on semantic semantic gears to allow for stratified modeling of dynamic regions of rendering the scene. At the same time, almost for free, our tracking approach enables free-viewpoint of interest - a functionality not yet achieved by existing NeRF-based methods.
  arXiv  Detail & Related papers  (2024-06-06T03:37:39Z)
• Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Rendering [36.111845416439095]
  We present a unified representation model, called Periodic Vibration Gaussian (PVG) PVG builds upon the efficient 3D Gaussian splatting technique, originally designed for static scene representation. PVG exhibits 900-fold acceleration in rendering over the best alternative.
  arXiv  Detail & Related papers  (2023-11-30T13:53:50Z)
• EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision [85.17951804790515]
  EmerNeRF is a simple yet powerful approach for learning spatial-temporal representations of dynamic driving scenes. It simultaneously captures scene geometry, appearance, motion, and semantics via self-bootstrapping. Our method achieves state-of-the-art performance in sensor simulation.
  arXiv  Detail & Related papers  (2023-11-03T17:59:55Z)

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.