Browse State-of-the-Art › Motion Segmentation
Motion Segmentation
62 papers with code · 4 benchmarks · 7 datasets archive 2025-07-28
Motion Segmentation is an essential task in many applications in Computer Vision and Robotics, such as surveillance, action recognition and scene understanding. The classic way to state the problem is the following: given a set of feature points that are tracked through a sequence of images, the goal is to cluster those trajectories according to the different motions they belong to. It is assumed that the scene contains multiple objects that are moving rigidly and independently in 3D-space.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
4 leaderboard tables shown for this task, 4 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| ApolloScape (5 rows) | Rule Based | Understanding Dynamic Scenes using Graph Convolution Networks | code | — | Compare |
| Hopkins155 (4 rows) | MVC | Motion Segmentation by Exploiting Complementary Geometric Models | code | — | Compare |
| KT3DMoSeg (1 row) | MultiViewClustering | Motion Segmentation by Exploiting Complementary Geometric Models | code | — | Compare |
| MTPV62 (1 row) | MVC | Motion Segmentation by Exploiting Complementary Geometric Models | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
7 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 212 · with a code link: 62 · where Syntology ran a sample: 15 (14 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (15 of 212 tagged: 14 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 3: papers 1 to 100 of 212, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
4 Jun 2018 10 repositories listed Syntology official (archive's flag): 1 ran · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples) · 1 pointer-only (licence)In this work, we propose a novel deep neural network named FlowNet3D that learns scene flow from point clouds in an end-to-end fashion.
-
5 Mar 2012 4 repositories listedIn this paper, we propose and study an algorithm, called Sparse Subspace Clustering (SSC), to cluster data points that lie in a union of low-dimensional subspaces.
-
29 Sep 2019 3 repositories listedTo handle the nonrigid background like a sea, we also propose a robust fusion mechanism between motion and appearance-based features.
-
2 Mar 2022 2 repositories listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified (of 12 harvested samples) · 1 pointer-only (licence)Scene flow allows autonomous vehicles to reason about the arbitrary motion of multiple independent objects which is the key to long-term mobile autonomy.
-
15 Jan 2020 2 repositories listedDuring about 30 years, a lot of research teams have worked on the big challenge of detection of moving objects in various challenging environments.
-
5 Jun 2019 2 repositories listedThe Progressive-X algorithm, Prog-X in short, is proposed for geometric multi-model fitting.
-
17 Jun 2025 1 repository listedTo handle the severe imbalance between moving and non-moving classes, we decouple them and apply tailored distillation strategies, allowing the teacher model to better learn key motion-related features.
-
9 Jun 2025 1 repository listed Syntology official (archive's flag): 6 ran · 7 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples) · 8 pointer-only (licence)In this paper, we aim to model 3D scene geometry, appearance, and the underlying physics purely from multi-view videos.
-
25 Apr 2025 1 repository listedEvent cameras provide rich signals that are suitable for motion estimation since they respond to changes in the scene.
-
10 Feb 2025 1 repository listedActive vision enables dynamic visual perception, offering an alternative to static feedforward architectures in computer vision, which rely on large datasets and high computational resources.
-
25 Aug 2024 1 repository listedWhen performing the motion object segmentation (MOS) task, effectively leveraging motion information from objects becomes a primary challenge in improving the recognition of moving objects.
-
24 May 2024 1 repository listedAerial surveillance demands rapid and precise detection of moving objects in dynamic environments.
-
23 May 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples)As such, prior work has looked at unsupervised instance detection and segmentation, but in the absence of annotated boxes, it is unclear how pixels must be grouped into objects and which objects are of interest.
-
18 Apr 2024 1 repository listedThe objective of this paper is motion segmentation -- discovering and segmenting the moving objects in a video.
-
16 Oct 2023 1 repository listedWe find that both contributions to the attention mechanism and the encoder architecture additively improve the quality of generated text (BLEU and semantic equivalence), but also of synchronization.
-
18 Sep 2023 1 repository listedMobile autonomy relies on the precise perception of dynamic environments.
-
28 Jul 2023 1 repository listedMotion segmentation is a formidable computer vision task, aiming to segment moving targets from a dynamic scene.
-
17 Apr 2023 1 repository listedThe Gestalt law of common fate, i. e., what move at the same speed belong together, has inspired unsupervised object discovery based on motion segmentation.
-
1 Mar 2023 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)This work proposes a novel approach to 4D radar-based scene flow estimation via cross-modal learning.
-
1 Jan 2023 1 repository listedIn this paper, we propose an original unsupervised spatio-temporal framework for motion segmentation from optical flow that fully investigates the temporal dimension of the problem.
-
7 Oct 2022 1 repository listedScene flow represents the motion information of each point in the 3D point clouds.
-
17 Sep 2022 1 repository listed Syntology official (archive's flag): 15 ran · 15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 16 harvested samples) · 3 pointer-only (licence)Learning-based visual odometry (VO) algorithms achieve remarkable performance on common static scenes, benefiting from high-capacity models and massive annotated data, but tend to fail in dynamic, populated environments.
-
19 Jul 2022 1 repository listed Syntology official (archive's flag): 2 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples) · 5 pointer-only (licence)In addition, our method is able to retain reasonable accuracy of camera poses on fully static scenes, which consistently outperforms strong state-of-the-art dense correspondence based methods with end-to-end deep…
-
5 Jul 2022 1 repository listed Syntology official (archive's flag): 16 ran · 16 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified (of 21 harvested samples)The objective of this paper is a model that is able to discover, track and segment multiple moving objects in a video.
-
18 Mar 2022 1 repository listedOur experiments demonstrate that, despite only capturing a small subset of the objects that move, this signal is enough to generalize to segment both moving and static instances of dynamic objects.
-
3 Mar 2022 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples)We present HOI4D, a large-scale 4D egocentric dataset with rich annotations, to catalyze the research of category-level human-object interaction.
-
6 Jan 2022 1 repository listedThe core idea of our work is to leverage the Expectation-Maximization (EM) framework in order to design in a well-founded manner a loss function and a training procedure of our motion segmentation neural network that…
-
12 Dec 2021 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)Event cameras are novel bio-inspired sensors that measure per-pixel brightness differences asynchronously.
-
22 Nov 2021 1 repository listedWe propose a method for discovery and segmentation of objects that are, or their parts are, independently moving in the scene.
-
5 Nov 2021 1 repository listedIn this paper, we present a cascaded two-level multi-model fitting method for identifying independently moving objects (i. e., the motion segmentation problem) with a monocular event camera.
-
13 Oct 2021 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)
-
28 Jul 2021 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
22 Jun 2021 1 repository listed
-
8 Jun 2021 1 repository listed
-
10 May 2021 1 repository listed
-
19 Mar 2021 1 repository listed
-
15 Feb 2021 1 repository listed
-
21 Jan 2021 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 5 samples that ran constructed an object rather than computing a result (of 7 harvested samples) · 7 pointer-only (licence)
-
17 Jan 2021 1 repository listed
-
11 Jan 2021 1 repository listed
-
16 Dec 2020 1 repository listed
-
27 Oct 2020 1 repository listed
-
1 Aug 2020 1 repository listed
-
11 Jun 2020 1 repository listed
-
9 May 2020 1 repository listed
-
18 Apr 2020 1 repository listed
-
31 Mar 2020 1 repository listed
-
1 Jun 2019 1 repository listed
-
22 May 2019 1 repository listed
-
2 Apr 2019 1 repository listed
-
11 Feb 2019 1 repository listed
-
1 Sep 2018 1 repository listed
-
24 May 2018 1 repository listed Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 14 harvested samples) · 1 pointer-only (licence)
-
6 Apr 2018 1 repository listed
-
17 Jul 2017 1 repository listed
-
2 Jun 2017 1 repository listed
-
30 Oct 2015 1 repository listed
-
9 Sep 2015 1 repository listed
-
18 Aug 2015 1 repository listed
-
5 Feb 2015 1 repository listed
-
Channel-wise Motion Features for Efficient Motion Segmentation17 Jul 2025 0 repositories listed
-
Temporal Rate Reduction Clustering for Human Motion Segmentation26 Jun 2025 0 repositories listed
-
EV-LayerSegNet: Self-supervised Motion Segmentation using Event Cameras7 Jun 2025 0 repositories listed
-
Event-based Egocentric Human Pose Estimation in Dynamic Environment28 May 2025 0 repositories listed
-
Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction20 Mar 2025 0 repositories listed
-
BEVMOSNet: Multimodal Fusion for BEV Moving Object Segmentation5 Mar 2025 0 repositories listed
-
Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos1 Jan 2025 0 repositories listed
-
Deep Learning and Hybrid Approaches for Dynamic Scene Analysis, Object Detection and Motion Tracking5 Dec 2024 0 repositories listed
-
On Moving Object Segmentation from Monocular Video with Transformers28 Nov 2024 0 repositories listed
-
RoMo: Robust Motion Segmentation Improves Structure from Motion27 Nov 2024 0 repositories listed
-
DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild20 Nov 2024 0 repositories listed
-
Human Insights Driven Latent Space for Different Driving Perspectives: A Unified Encoder for Efficient Multi-Task Inference16 Sep 2024 0 repositories listed
-
Retina-Inspired Object Motion Segmentation for Event-Cameras18 Aug 2024 0 repositories listed
-
Hardware-Algorithm Re-engineering of Retinal Circuit for Intelligent Object Motion Segmentation31 Jul 2024 0 repositories listed
-
Dense Monocular Motion Segmentation Using Optical Flow and Pseudo Depth Map: A Zero-Shot Approach27 Jun 2024 0 repositories listed
-
Zero-Shot Monocular Motion Segmentation in the Wild by Combining Deep Learning with Geometric Motion Model Fusion2 May 2024 0 repositories listed
-
Turb-Seg-Res: A Segment-then-Restore Pipeline for Dynamic Videos with Atmospheric Turbulence21 Apr 2024 0 repositories listed
-
Neuromorphic Vision-based Motion Segmentation with Graph Transformer Neural Network16 Apr 2024 0 repositories listed
-
Out of the Room: Generalizing Event-Based Dynamic Motion Segmentation for Complex Scenes7 Mar 2024 0 repositories listed
-
A Unified Model Selection Technique for Spectral Clustering Based Motion Segmentation3 Mar 2024 0 repositories listed
-
Learned Trajectory Embedding for Subspace Clustering1 Jan 2024 0 repositories listed
-
WoodScape Motion Segmentation for Autonomous Driving -- CVPR 2023 OmniCV Workshop Challenge31 Dec 2023 0 repositories listed
-
Appearance-Based Refinement for Object-Centric Motion Segmentation18 Dec 2023 0 repositories listed
-
Un-EvMoSeg: Unsupervised Event-based Independent Motion Segmentation30 Nov 2023 0 repositories listed
-
Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes29 Oct 2023 0 repositories listed
-
Segmenting the motion components of a video: A long-term unsupervised model2 Oct 2023 0 repositories listed
-
Motion Segmentation from a Moving Monocular Camera24 Sep 2023 0 repositories listed
-
Joint Self-supervised Depth and Optical Flow Estimation towards Dynamic Objects7 Sep 2023 0 repositories listed
-
LiDAR-BEVMTN: Real-Time LiDAR Bird's-Eye View Multi-Task Perception Network for Autonomous Driving17 Jul 2023 0 repositories listed
-
Divided Attention: Unsupervised Multi-Object Discovery with Contextually Separated Slots4 Apr 2023 0 repositories listed
-
Segmentation Guided Deep HDR Deghosting4 Jul 2022 0 repositories listed
-
Self-Supervised Deep Subspace Clustering with Entropy-norm10 Jun 2022 0 repositories listed
-
EVIMO2: An Event Camera Dataset for Motion Segmentation, Optical Flow, Structure from Motion, and Visual Inertial Odometry in Indoor Scenes with Monocular or Stereo Algorithms6 May 2022 0 repositories listed
-
Quantum Motion Segmentation24 Mar 2022 0 repositories listed
-
ProgressiveMotionSeg: Mutually Reinforced Framework for Event-Based Motion Segmentation22 Mar 2022 0 repositories listed
-
The Right Spin: Learning Object Motion from Rotation-Compensated Flow Fields28 Feb 2022 0 repositories listed
-
Consistency and Diversity induced Human Motion Segmentation10 Feb 2022 0 repositories listed
-
LiMoSeg: Real-time Bird's Eye View based LiDAR Motion Segmentation8 Nov 2021 0 repositories listed
Syntology lines on 16 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections