Sparse3DTrack: Monocular 3D Object Tracking Using Sparse Supervision

• URL: http://arxiv.org/abs/2603.18298v1
• Date: Wed, 18 Mar 2026 21:36:41 GMT
• Title: Sparse3DTrack: Monocular 3D Object Tracking Using Sparse Supervision
• Abstract summary: Monocular 3D object tracking aims to estimate temporally consistent 3D object poses across video frames.<n>Existing state-the-art approaches are fully supervised and rely on dense 3D annotations over long video sequences.<n>We propose the first supervised framework for monocular 3D object tracking.
• Score: 16.586885757497203
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Monocular 3D object tracking aims to estimate temporally consistent 3D object poses across video frames, enabling autonomous agents to reason about scene dynamics. However, existing state-of-the-art approaches are fully supervised and rely on dense 3D annotations over long video sequences, which are expensive to obtain and difficult to scale. In this work, we address this fundamental limitation by proposing the first sparsely supervised framework for monocular 3D object tracking. Our approach decomposes the task into two sequential sub-problems: 2D query matching and 3D geometry estimation. Both components leverage the spatio-temporal consistency of image sequences to augment a sparse set of labeled samples and learn rich 2D and 3D representations of the scene. Leveraging these learned cues, our model automatically generates high-quality 3D pseudolabels across entire videos, effectively transforming sparse supervision into dense 3D track annotations. This enables existing fully-supervised trackers to effectively operate under extreme label sparsity. Extensive experiments on the KITTI and nuScenes datasets demonstrate that our method significantly improves tracking performance, achieving an improvement of up to 15.50 p.p. while using at most four ground truth annotations per track.

Related papers

• Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels [67.36972154532761]
  Estimating the 3D trajectory of every pixel from a monocular video is crucial and promising for a comprehensive understanding of the 3D dynamics of videos.<n>Recent monocular 3D tracking works demonstrate impressive performance, but are limited to either tracking sparse points on the first frame or a slow optimization-based framework for dense tracking.<n>We propose a feedforward model, called Track4World, enabling an efficient holistic 3D tracking of every pixel in the world-centric coordinate system.
  arXiv  Detail & Related papers  (2026-03-03T03:45:43Z)
• SpatialTrackerV2: 3D Point Tracking Made Easy [73.0350898700048]
  SpatialTrackerV2 is a feed-forward 3D point tracking method for monocular videos.<n>It decomposes world-space 3D motion into scene geometry, camera ego-motion, and pixel-wise object motion.<n>By learning geometry and motion jointly from such heterogeneous data, SpatialTrackerV2 outperforms existing 3D tracking methods by 30%.
  arXiv  Detail & Related papers  (2025-07-16T17:59:03Z)
• Street Gaussians without 3D Object Tracker [84.89933388445185]
  Most existing methods rely on labor-intensive manual labeling of object poses.<n>We propose a stable object tracking module by leveraging associations from 2D deep trackers within a 3D object fusion strategy.<n>We address inevitable tracking errors by further introducing a motion learning strategy in an implicit feature space that autonomously corrects trajectory errors and recovers missed detections.
  arXiv  Detail & Related papers  (2024-12-07T05:49:42Z)
• TAPVid-3D: A Benchmark for Tracking Any Point in 3D [63.060421798990845]
  We introduce a new benchmark, TAPVid-3D, for evaluating the task of Tracking Any Point in 3D. This benchmark will serve as a guidepost to improve our ability to understand precise 3D motion and surface deformation from monocular video.
  arXiv  Detail & Related papers  (2024-07-08T13:28:47Z)
• Tracking by 3D Model Estimation of Unknown Objects in Videos [122.56499878291916]
  We argue that this representation is limited and instead propose to guide and improve 2D tracking with an explicit object representation. Our representation tackles a complex long-term dense correspondence problem between all 3D points on the object for all video frames. The proposed optimization minimizes a novel loss function to estimate the best 3D shape, texture, and 6DoF pose.
  arXiv  Detail & Related papers  (2023-04-13T11:32:36Z)
• Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous Driving [3.8073142980733]
  We propose jointly training 3D detection and 3D tracking from only monocular videos in an end-to-end manner. Time3D achieves 21.4% AMOTA, 13.6% AMOTP on the nuScenes 3D tracking benchmark, surpassing all published competitors.
  arXiv  Detail & Related papers  (2022-05-30T06:41:10Z)
• 3D Visual Tracking Framework with Deep Learning for Asteroid Exploration [22.808962211830675]
  In this paper, we focus on the studied accurate and real-time method for 3D tracking. A new large-scale 3D asteroid tracking dataset is presented, including binocular video sequences, depth maps, and point clouds of diverse asteroids. We propose a deep-learning based 3D tracking framework, named as Track3D, which involves 2D monocular tracker and a novel light-weight amodal axis-aligned bounding-box network, A3BoxNet.
  arXiv  Detail & Related papers  (2021-11-21T04:14:45Z)
• Monocular Quasi-Dense 3D Object Tracking [99.51683944057191]
  A reliable and accurate 3D tracking framework is essential for predicting future locations of surrounding objects and planning the observer's actions in numerous applications such as autonomous driving. We propose a framework that can effectively associate moving objects over time and estimate their full 3D bounding box information from a sequence of 2D images captured on a moving platform.
  arXiv  Detail & Related papers  (2021-03-12T15:30:02Z)
• Tracking Emerges by Looking Around Static Scenes, with Neural 3D Mapping [23.456046776979903]
  We propose to leverage multiview data of textitstatic points in arbitrary scenes (static or dynamic) to learn a neural 3D mapping module. The neural 3D mapper consumes RGB-D data as input, and produces a 3D voxel grid of deep features as output. We show that our unsupervised 3D object trackers outperform prior unsupervised 2D and 2.5D trackers, and approach the accuracy of supervised trackers.
  arXiv  Detail & Related papers  (2020-08-04T02:59:23Z)

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.