GeoMotion: Rethinking Motion Segmentation via Latent 4D Geometry

• URL: http://arxiv.org/abs/2602.21810v1
• Date: Wed, 25 Feb 2026 11:36:33 GMT
• Title: GeoMotion: Rethinking Motion Segmentation via Latent 4D Geometry
• Authors: Xiankang He, Peile Lin, Ying Cui, Dongyan Guo, Chunhua Shen, Xiaoqin Zhang,
• Abstract summary: We propose a fully learning-based approach that directly infers moving objects from latent feature representations via attention mechanisms.<n>Our key insight is to bypass explicit correspondence estimation and instead let the model learn to implicitly disentangle object and camera motion.<n>Our approach achieves state-of-the-art motion segmentation performance with high efficiency.
• Score: 61.24189040578178
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Motion segmentation in dynamic scenes is highly challenging, as conventional methods heavily rely on estimating camera poses and point correspondences from inherently noisy motion cues. Existing statistical inference or iterative optimization techniques that struggle to mitigate the cumulative errors in multi-stage pipelines often lead to limited performance or high computational cost. In contrast, we propose a fully learning-based approach that directly infers moving objects from latent feature representations via attention mechanisms, thus enabling end-to-end feed-forward motion segmentation. Our key insight is to bypass explicit correspondence estimation and instead let the model learn to implicitly disentangle object and camera motion. Supported by recent advances in 4D scene geometry reconstruction (e.g., $π^3$), the proposed method leverages reliable camera poses and rich spatial-temporal priors, which ensure stable training and robust inference for the model. Extensive experiments demonstrate that by eliminating complex pre-processing and iterative refinement, our approach achieves state-of-the-art motion segmentation performance with high efficiency. The code is available at:https://github.com/zjutcvg/GeoMotion.

Related papers

• The Dynamic Prior: Understanding 3D Structures for Casual Dynamic Videos [19.25337083769716]
  We introduce the Dynamic Prior (ourmodel) to robustly identify dynamic objects without task-specific training.<n>ourmodel can be seamlessly integrated into state-of-the-art pipelines for camera pose optimization, depth reconstruction, and 4D trajectory estimation.
  arXiv  Detail & Related papers  (2025-12-05T03:31:49Z)
• MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning [66.53533434848369]
  We propose a motion-guided self-learning framework that learns densely consistent representations.<n>We improve state-of-the-art by 1% to 6% on six image and video datasets and four evaluation benchmarks.
  arXiv  Detail & Related papers  (2025-06-10T11:20:32Z)
• Image as an IMU: Estimating Camera Motion from a Single Motion-Blurred Image [14.485182089870928]
  We propose a novel framework that leverages motion blur as a rich cue for motion estimation.<n>Our approach works by predicting a dense motion flow field and a monocular depth map directly from a single motion-blurred image.<n>Our method produces an IMU-like measurement that robustly captures fast and aggressive camera movements.
  arXiv  Detail & Related papers  (2025-03-21T17:58:56Z)
• Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera [49.82535393220003]
  Dyn-HaMR is the first approach to reconstruct 4D global hand motion from monocular videos recorded by dynamic cameras in the wild.<n>We show that our approach significantly outperforms state-of-the-art methods in terms of 4D global mesh recovery.<n>This establishes a new benchmark for hand motion reconstruction from monocular video with moving cameras.
  arXiv  Detail & Related papers  (2024-12-17T12:43:10Z)
• ESVO2: Direct Visual-Inertial Odometry with Stereo Event Cameras [41.992980062962495]
  Event-based visual odometry aims at solving tracking and mapping subproblems (typically in parallel)<n>We build an event-based stereo visual-inertial odometry system on top of a direct pipeline.<n>The resulting system scales well with modern high-resolution event cameras.
  arXiv  Detail & Related papers  (2024-10-12T05:35:27Z)
• Motion-DVAE: Unsupervised learning for fast human motion denoising [18.432026846779372]
  We introduce Motion-DVAE, a motion prior to capture the short-term dependencies of human motion. Together with Motion-DVAE, we introduce an unsupervised learned denoising method unifying regression- and optimization-based approaches.
  arXiv  Detail & Related papers  (2023-06-09T12:18:48Z)
• ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild [57.37891682117178]
  We present a robust dense indirect structure-from-motion method for videos that is based on dense correspondence from pairwise optical flow. A novel neural network architecture is proposed for processing irregular point trajectory data. Experiments on MPI Sintel dataset show that our system produces significantly more accurate camera trajectories.
  arXiv  Detail & Related papers  (2022-07-19T09:19:45Z)
• Learning to Segment Rigid Motions from Two Frames [72.14906744113125]
  We propose a modular network, motivated by a geometric analysis of what independent object motions can be recovered from an egomotion field. It takes two consecutive frames as input and predicts segmentation masks for the background and multiple rigidly moving objects, which are then parameterized by 3D rigid transformations. Our method achieves state-of-the-art performance for rigid motion segmentation on KITTI and Sintel.
  arXiv  Detail & Related papers  (2021-01-11T04:20:30Z)
• Event-based Motion Segmentation with Spatio-Temporal Graph Cuts [51.17064599766138]
  We have developed a method to identify independently objects acquired with an event-based camera. The method performs on par or better than the state of the art without having to predetermine the number of expected moving objects.
  arXiv  Detail & Related papers  (2020-12-16T04:06:02Z)

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.