Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision

• URL: http://arxiv.org/abs/2512.02339v1
• Date: Tue, 02 Dec 2025 02:17:34 GMT
• Title: Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision
• Authors: Chenshuang Zhang, Kang Zhang, Joon Son Chung, In So Kweon, Junmo Kim, Chengzhi Mao,
• Abstract summary: Distinguishing visually similar objects by their motion remains a critical challenge in computer vision.<n>We find that pre-trained video diffusion models inherently learn motion representations suitable for tracking without task-specific training.<n>Our method achieves up to a 6-point improvement over recent self-supervised approaches on established benchmarks.
• Score: 80.2787127430925
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Distinguishing visually similar objects by their motion remains a critical challenge in computer vision. Although supervised trackers show promise, contemporary self-supervised trackers struggle when visual cues become ambiguous, limiting their scalability and generalization without extensive labeled data. We find that pre-trained video diffusion models inherently learn motion representations suitable for tracking without task-specific training. This ability arises because their denoising process isolates motion in early, high-noise stages, distinct from later appearance refinement. Capitalizing on this discovery, our self-supervised tracker significantly improves performance in distinguishing visually similar objects, an underexplored failure point for existing methods. Our method achieves up to a 6-point improvement over recent self-supervised approaches on established benchmarks and our newly introduced tests focused on tracking visually similar items. Visualizations confirm that these diffusion-derived motion representations enable robust tracking of even identical objects across challenging viewpoint changes and deformations.

Related papers

• From Sight to Insight: Unleashing Eye-Tracking in Weakly Supervised Video Salient Object Detection [60.11169426478452]
  This paper aims to introduce fixation information to assist the detection of salient objects under weak supervision.<n>We propose a Position and Semantic Embedding (PSE) module to provide location and semantic guidance during the feature learning process.<n>An Intra-Inter Mixed Contrastive (MCII) model improves thetemporal modeling capabilities under weak supervision.
  arXiv  Detail & Related papers  (2025-06-30T05:01:40Z)
• TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion Models [75.20168902300166]
  We propose TrackDiffusion, a novel video generation framework affording fine-grained trajectory-conditioned motion control. A pivotal component of TrackDiffusion is the instance enhancer, which explicitly ensures inter-frame consistency of multiple objects. generated video sequences by our TrackDiffusion can be used as training data for visual perception models.
  arXiv  Detail & Related papers  (2023-12-01T15:24:38Z)
• Online Deep Clustering with Video Track Consistency [85.8868194550978]
  We propose an unsupervised clustering-based approach to learn visual features from video object tracks. We show that exploiting an unsupervised class-agnostic, yet noisy, track generator yields to better accuracy compared to relying on costly and precise track annotations.
  arXiv  Detail & Related papers  (2022-06-07T08:11:00Z)
• Semi-TCL: Semi-Supervised Track Contrastive Representation Learning [40.31083437957288]
  We design a new instance-to-track matching objective to learn appearance embedding. It compares a candidate detection to the embedding of the tracks persisted in the tracker. We implement this learning objective in a unified form following the spirit of constrastive loss.
  arXiv  Detail & Related papers  (2021-07-06T05:23:30Z)
• Crop-Transform-Paste: Self-Supervised Learning for Visual Tracking [137.26381337333552]
  In this work, we develop the Crop-Transform-Paste operation, which is able to synthesize sufficient training data. Since the object state is known in all synthesized data, existing deep trackers can be trained in routine ways without human annotation.
  arXiv  Detail & Related papers  (2021-06-21T07:40:34Z)
• Self-supervised Video Object Segmentation [76.83567326586162]
  The objective of this paper is self-supervised representation learning, with the goal of solving semi-supervised video object segmentation (a.k.a. dense tracking) We make the following contributions: (i) we propose to improve the existing self-supervised approach, with a simple, yet more effective memory mechanism for long-term correspondence matching; (ii) by augmenting the self-supervised approach with an online adaptation module, our method successfully alleviates tracker drifts caused by spatial-temporal discontinuity; (iv) we demonstrate state-of-the-art results among the self-supervised approaches on DAVIS-2017 and YouTube
  arXiv  Detail & Related papers  (2020-06-22T17:55:59Z)
• Unsupervised Multiple Person Tracking using AutoEncoder-Based Lifted Multicuts [11.72025865314187]
  We present an unsupervised multiple object tracking approach based on minimum visual features and lifted multicuts. We show that, despite being trained without using the provided annotations, our model provides competitive results on the challenging MOT Benchmark for pedestrian tracking.
  arXiv  Detail & Related papers  (2020-02-04T09:42:34Z)

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.