Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos

• URL: http://arxiv.org/abs/2506.05546v2
• Date: Sun, 22 Jun 2025 15:25:15 GMT
• Title: Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos
• Authors: Vadim Tschernezki, Diane Larlus, Iro Laina, Andrea Vedaldi,
• Abstract summary: We propose to improve dynamic segmentation in 3D by fusing motion segmentation predictions from a 2D-based model into layered radiance fields.<n>We address this issue through test-time refinement, which helps the model to focus on specific frames, thereby reducing the data complexity.<n>This demonstrates that 3D techniques can enhance 2D analysis even for dynamic phenomena in a challenging and realistic setting.
• Score: 71.24593306228145
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Computer vision is largely based on 2D techniques, with 3D vision still relegated to a relatively narrow subset of applications. However, by building on recent advances in 3D models such as neural radiance fields, some authors have shown that 3D techniques can at last improve outputs extracted from independent 2D views, by fusing them into 3D and denoising them. This is particularly helpful in egocentric videos, where the camera motion is significant, but only under the assumption that the scene itself is static. In fact, as shown in the recent analysis conducted by EPIC Fields, 3D techniques are ineffective when it comes to studying dynamic phenomena, and, in particular, when segmenting moving objects. In this paper, we look into this issue in more detail. First, we propose to improve dynamic segmentation in 3D by fusing motion segmentation predictions from a 2D-based model into layered radiance fields (Layered Motion Fusion). However, the high complexity of long, dynamic videos makes it challenging to capture the underlying geometric structure, and, as a result, hinders the fusion of motion cues into the (incomplete) scene geometry. We address this issue through test-time refinement, which helps the model to focus on specific frames, thereby reducing the data complexity. This results in a synergy between motion fusion and the refinement, and in turn leads to segmentation predictions of the 3D model that surpass the 2D baseline by a large margin. This demonstrates that 3D techniques can enhance 2D analysis even for dynamic phenomena in a challenging and realistic setting.

Related papers

• DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation [51.43837087865105]
  Vision foundation models (VFMs) trained on large-scale image datasets provide high-quality features that have significantly advanced 2D visual recognition.<n>Their potential in 3D vision remains largely untapped, despite the common availability of 2D images alongside 3D point cloud datasets.<n>We introduce DITR, a simple yet effective approach that extracts 2D foundation model features, projects them to 3D, and finally injects them into a 3D point cloud segmentation model.
  arXiv  Detail & Related papers  (2025-03-24T17:59:11Z)
• xMOD: Cross-Modal Distillation for 2D/3D Multi-Object Discovery from 2D motion [4.878192303432336]
  DIOD-3D is the first baseline for multi-object discovery in 3D data using 2D motion.<n>xMOD is a cross-modal training framework that integrates 2D and 3D data while always using 2D motion cues.<n>Our approach yields a substantial performance improvement compared with the 2D object discovery state-of-the-art on all datasets.
  arXiv  Detail & Related papers  (2025-03-19T09:20:35Z)
• Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach [42.581066866708085]
  We present a novel video generation framework that integrates 3-dimensional geometry and dynamic awareness.<n>To achieve this, we augment 2D videos with 3D point trajectories and align them in pixel space.<n>The resulting 3D-aware video dataset, PointVid, is then used to fine-tune a latent diffusion model.<n>We regularize the shape and motion of objects in the video to eliminate undesired artifacts.
  arXiv  Detail & Related papers  (2025-02-05T21:49:06Z)
• 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)
• SpatialTracker: Tracking Any 2D Pixels in 3D Space [71.58016288648447]
  We propose to estimate point trajectories in 3D space to mitigate the issues caused by image projection. Our method, named SpatialTracker, lifts 2D pixels to 3D using monocular depth estimators. Tracking in 3D allows us to leverage as-rigid-as-possible (ARAP) constraints while simultaneously learning a rigidity embedding that clusters pixels into different rigid parts.
  arXiv  Detail & Related papers  (2024-04-05T17:59:25Z)
• DO3D: Self-supervised Learning of Decomposed Object-aware 3D Motion and Depth from Monocular Videos [76.01906393673897]
  We propose a self-supervised method to jointly learn 3D motion and depth from monocular videos. Our system contains a depth estimation module to predict depth, and a new decomposed object-wise 3D motion (DO3D) estimation module to predict ego-motion and 3D object motion. Our model delivers superior performance in all evaluated settings.
  arXiv  Detail & Related papers  (2024-03-09T12:22:46Z)
• Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation [87.54570024320354]
  State-of-the-art methods for large-scale driving-scene LiDAR semantic segmentation often project and process the point clouds in the 2D space. A straightforward solution to tackle the issue of 3D-to-2D projection is to keep the 3D representation and process the points in the 3D space. We develop a 3D cylinder partition and a 3D cylinder convolution based framework, termed as Cylinder3D, which exploits the 3D topology relations and structures of driving-scene point clouds.
  arXiv  Detail & Related papers  (2020-08-04T13:56:19Z)
• Unsupervised object-centric video generation and decomposition in 3D [36.08064849807464]
  We propose to model a video as the view seen while moving through a scene with multiple 3D objects and a 3D background. Our model is trained from monocular videos without any supervision, yet learns to generate coherent 3D scenes containing several moving objects.
  arXiv  Detail & Related papers  (2020-07-07T18:01:29Z)

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.