TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking

• URL: http://arxiv.org/abs/2507.19908v1
• Date: Sat, 26 Jul 2025 10:41:55 GMT
• Title: TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking
• Authors: Mengmeng Wang, Haonan Wang, Yulong Li, Xiangjie Kong, Jiaxin Du, Guojiang Shen, Feng Xia,
• Abstract summary: TrackAny3D is the first framework to transfer large-scale pretrained 3D models for category-agnostic 3D SOT.<n>MoGE architecture adaptively activates specialized 3works based on distinct geometric characteristics.<n>Experiments show that TrackAny3D establishes new state-of-the-art performance on category-agnostic 3D SOT.
• Score: 25.788917457593673
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D LiDAR-based single object tracking (SOT) relies on sparse and irregular point clouds, posing challenges from geometric variations in scale, motion patterns, and structural complexity across object categories. Current category-specific approaches achieve good accuracy but are impractical for real-world use, requiring separate models for each category and showing limited generalization. To tackle these issues, we propose TrackAny3D, the first framework to transfer large-scale pretrained 3D models for category-agnostic 3D SOT. We first integrate parameter-efficient adapters to bridge the gap between pretraining and tracking tasks while preserving geometric priors. Then, we introduce a Mixture-of-Geometry-Experts (MoGE) architecture that adaptively activates specialized subnetworks based on distinct geometric characteristics. Additionally, we design a temporal context optimization strategy that incorporates learnable temporal tokens and a dynamic mask weighting module to propagate historical information and mitigate temporal drift. Experiments on three commonly-used benchmarks show that TrackAny3D establishes new state-of-the-art performance on category-agnostic 3D SOT, demonstrating strong generalization and competitiveness. We hope this work will enlighten the community on the importance of unified models and further expand the use of large-scale pretrained models in this field.

Related papers

• SeqAffordSplat: Scene-level Sequential Affordance Reasoning on 3D Gaussian Splatting [85.87902260102652]
  We introduce the novel task of Sequential 3D Gaussian Affordance Reasoning.<n>We then propose SeqSplatNet, an end-to-end framework that directly maps an instruction to a sequence of 3D affordance masks.<n>Our method sets a new state-of-the-art on our challenging benchmark, effectively advancing affordance reasoning from single-step interactions to complex, sequential tasks at the scene level.
  arXiv  Detail & Related papers  (2025-07-31T17:56:55Z)
• UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting [64.31900521467362]
  No existing pre-training method is equally effective for both object- and scene-level point clouds.<n>We introduce UniPre3D, the first unified pre-training method that can be seamlessly applied to point clouds of any scale and 3D models of any architecture.
  arXiv  Detail & Related papers  (2025-06-11T17:23:21Z)
• On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentation [52.96632954620623]
  We introduce a novel geometry-aware PEFT module specifically designed for 3D point cloud transformers.<n>Our approach sets a new benchmark for efficient, scalable, and geometry-aware fine-tuning of large-scale 3D point cloud models.
  arXiv  Detail & Related papers  (2025-05-28T15:08:36Z)
• Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification [59.68055837500357]
  We propose the first prototype-based framework named Proto-FG3D for fine-grained 3D shape classification.<n>Proto-FG3D establishes joint multi-view and multi-category representation learning via Prototype Association.<n>Proto-FG3D surpasses state-of-the-art methods in accuracy, transparent predictions, and ad-hoc interpretability with visualizations.
  arXiv  Detail & Related papers  (2025-05-23T09:31:02Z)
• MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion [118.74385965694694]
  We present Motion DUSt3R (MonST3R), a novel geometry-first approach that directly estimates per-timestep geometry from dynamic scenes.<n>By simply estimating a pointmap for each timestep, we can effectively adapt DUST3R's representation, previously only used for static scenes, to dynamic scenes.<n>We show that by posing the problem as a fine-tuning task, identifying several suitable datasets, and strategically training the model on this limited data, we can surprisingly enable the model to handle dynamics.
  arXiv  Detail & Related papers  (2024-10-04T18:00:07Z)
• Towards Category Unification of 3D Single Object Tracking on Point Clouds [10.64650098374183]
  Category-specific models are provenly valuable methods in 3D single object tracking (SOT) regardless of Siamese or motion-centric paradigms. This paper first introduces unified models that can simultaneously track objects across all categories using a single network with shared model parameters.
  arXiv  Detail & Related papers  (2024-01-20T10:38:28Z)
• Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception [122.53774221136193]
  State-of-the-art methods for driving-scene LiDAR-based perception often project the point clouds to 2D space and then process them via 2D convolution. A natural remedy is to utilize the 3D voxelization and 3D convolution network. We propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pattern.
  arXiv  Detail & Related papers  (2021-09-12T06:25:11Z)
• BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models [1.14219428942199]
  This work proposes BundleTrack, a general framework for 6D pose tracking of objects. An efficient implementation of the framework provides a real-time performance of 10Hz for the entire framework.
  arXiv  Detail & Related papers  (2021-08-01T18:14:46Z)
• Learning Compositional Shape Priors for Few-Shot 3D Reconstruction [36.40776735291117]
  We show that complex encoder-decoder architectures exploit large amounts of per-category data. We propose three ways to learn a class-specific global shape prior, directly from data. Experiments on the popular ShapeNet dataset show that our method outperforms a zero-shot baseline by over 40%.
  arXiv  Detail & Related papers  (2021-06-11T14:55:49Z)
• Monocular 3D Detection with Geometric Constraints Embedding and Semi-supervised Training [3.8073142980733]
  We propose a novel framework for monocular 3D objects detection using only RGB images, called KM3D-Net. We design a fully convolutional model to predict object keypoints, dimension, and orientation, and then combine these estimations with perspective geometry constraints to compute position attribute.
  arXiv  Detail & Related papers  (2020-09-02T00:51:51Z)
• Few-Shot Single-View 3-D Object Reconstruction with Compositional Priors [30.262308825799167]
  We show that complex encoder-decoder architectures perform similarly to nearest-neighbor baselines in standard benchmarks. We propose three approaches that efficiently integrate a class prior into a 3D reconstruction model.
  arXiv  Detail & Related papers  (2020-04-14T04:53:34Z)

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.