Static Scene Reconstruction from Dynamic Egocentric Videos

• URL: http://arxiv.org/abs/2603.22450v1
• Date: Mon, 23 Mar 2026 18:19:46 GMT
• Title: Static Scene Reconstruction from Dynamic Egocentric Videos
• Abstract summary: Egocentric videos present unique challenges for 3D reconstruction due to rapid camera motion and frequent dynamic interactions.<n>We propose a robust pipeline that adapts static reconstruction backbones to long-form egocentric video.
• Score: 0.08594140167290099
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Egocentric videos present unique challenges for 3D reconstruction due to rapid camera motion and frequent dynamic interactions. State-of-the-art static reconstruction systems, such as MapAnything, often degrade in these settings, suffering from catastrophic trajectory drift and "ghost" geometry caused by moving hands. We bridge this gap by proposing a robust pipeline that adapts static reconstruction backbones to long-form egocentric video. Our approach introduces a mask-aware reconstruction mechanism that explicitly suppresses dynamic foreground in the attention layers, preventing hand artifacts from contaminating the static map. Furthermore, we employ a chunked reconstruction strategy with pose-graph stitching to ensure global consistency and eliminate long-term drift. Experiments on HD-EPIC and indoor drone datasets demonstrate that our pipeline significantly improves absolute trajectory error and yields visually clean static geometry compared to naive baselines, effectively extending the capability of foundation models to dynamic first-person scenes.

Related papers

• ReFlow: Self-correction Motion Learning for Dynamic Scene Reconstruction [37.05324860060443]
  ReFlow is a unified framework for monocular dynamic scene reconstruction.<n>It learns 3D motion in a novel self-varying manner from raw video.
  arXiv  Detail & Related papers  (2026-04-02T03:14:26Z)
• MoRe: Motion-aware Feed-forward 4D Reconstruction Transformer [45.19539316971492]
  MoRe is a feedforward 4D reconstruction network that efficiently recovers dynamic 3D scenes from monocular videos.<n>Built upon a strong static reconstruction backbone, MoRe employs an attention-forcing strategy to disentangle dynamic motion from static structure.<n>Experiments on multiple benchmarks demonstrate that MoRe achieves high-quality dynamic reconstructions with exceptional efficiency.
  arXiv  Detail & Related papers  (2026-03-05T11:51:07Z)
• MUT3R: Motion-aware Updating Transformer for Dynamic 3D Reconstruction [24.474529522394405]
  We introduce MUT3R, a training-free framework that applies the attention-derived motion cue to suppress dynamic content during inference.<n>We do not retrain or fine-tune the model; we let the pretrained transformer diagnose its own motion cues and correct itself.
  arXiv  Detail & Related papers  (2025-12-03T16:36:53Z)
• SplitGaussian: Reconstructing Dynamic Scenes via Visual Geometry Decomposition [14.381223353489062]
  We propose textbfSplitGaussian, a novel framework that explicitly decomposes scene representations into static and dynamic components.<n>SplitGaussian outperforms prior state-of-the-art methods in rendering quality, geometric stability, and motion separation.
  arXiv  Detail & Related papers  (2025-08-06T09:00:13Z)
• Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction [86.099855111676]
  Traditional SLAM systems struggle with highly dynamic scenes commonly found in casual videos.<n>This work leverages a 3D point tracker to separate the camera-induced motion from the observed motion of dynamic objects.<n>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)
• D$^2$USt3R: Enhancing 3D Reconstruction for Dynamic Scenes [54.886845755635754]
  This work addresses the task of 3D reconstruction in dynamic scenes, where object motions frequently degrade the quality of previous 3D pointmap regression methods.<n>By explicitly incorporating both spatial and temporal aspects, our approach successfully encapsulates 3D dense correspondence to the proposed pointmaps.
  arXiv  Detail & Related papers  (2025-04-08T17:59:50Z)
• T-3DGS: Removing Transient Objects for 3D Scene Reconstruction [83.05271859398779]
  Transient objects in video sequences can significantly degrade the quality of 3D scene reconstructions.<n>We propose T-3DGS, a novel framework that robustly filters out transient distractors during 3D reconstruction using Gaussian Splatting.
  arXiv  Detail & Related papers  (2024-11-29T07:45:24Z)
• 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.<n>By simply estimating a pointmap for each timestep, we can effectively adapt DUST3R's representation, previously only used for static scenes, to dynamic scenes.<n>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)
• SMORE: Simultaneous Map and Object REconstruction [66.66729715211642]
  We present a method for dynamic surface reconstruction of large-scale urban scenes from LiDAR.<n>We take a holistic perspective and optimize a compositional model of a dynamic scene that decomposes the world into rigidly-moving objects and the background.
  arXiv  Detail & Related papers  (2024-06-19T23:53:31Z)
• RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenes [3.1224202646855903]
  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.
  arXiv  Detail & Related papers  (2024-03-14T14:08:59Z)
• Limited-angle tomographic reconstruction of dense layered objects by dynamical machine learning [68.9515120904028]
  Limited-angle tomography of strongly scattering quasi-transparent objects is a challenging, highly ill-posed problem. Regularizing priors are necessary to reduce artifacts by improving the condition of such problems. We devised a recurrent neural network (RNN) architecture with a novel split-convolutional gated recurrent unit (SC-GRU) as the building block.
  arXiv  Detail & Related papers  (2020-07-21T11:48:22Z)

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.