# Polycepta: Object-Centric Appearance Estimation for Multi-Object Tracking

arXiv: https://arxiv.org/abs/2606.23604 · HTML: https://mlsanity.com/paper/2606.23604/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 49 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Builds on (most cited first, 25 of 25)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [HiPPO: Recurrent Memory with Optimal Polynomial Projections](https://mlsanity.com/paper/2008.07669/) (2020)
- [HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking](https://mlsanity.com/paper/2009.07736/) (2020)
- [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019)
- [MOT20: A benchmark for multi object tracking in crowded scenes](https://mlsanity.com/paper/2003.09003/) (2020)
- [StrongSORT: Make DeepSORT Great Again](https://mlsanity.com/paper/2202.13514/) (2022)
- [MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking](https://mlsanity.com/paper/2010.07548/) (2020)
- [MeMOT: Multi-Object Tracking with Memory](https://mlsanity.com/paper/2203.16761/) (2022)
- [MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking](https://mlsanity.com/paper/2307.15700/) (2023)
- [Virtual Sparse Convolution for Multimodal 3D Object Detection](https://mlsanity.com/paper/2303.02314/) (2023)
- [DeepFusionMOT: A 3D Multi-Object Tracking Framework Based on Camera-LiDAR Fusion with Deep Association](https://mlsanity.com/paper/2202.12100/) (2022)
- [PolarMOT: How Far Can Geometric Relations Take Us in 3D Multi-Object Tracking?](https://mlsanity.com/paper/2208.01957/) (2022)
- [Joint Multi-Object Detection and Tracking with Camera-LiDAR Fusion for Autonomous Driving](https://mlsanity.com/paper/2108.04602/) (2021)
- [Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking](https://mlsanity.com/paper/2410.01806/) (2024)
- [MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous Driving](https://mlsanity.com/paper/2409.16149/) (2024)
- [PNAS-MOT: Multi-Modal Object Tracking with Pareto Neural Architecture Search](https://mlsanity.com/paper/2403.15712/) (2024)
- [RobMOT: Robust 3D Multi-Object Tracking by Observational Noise and State Estimation Drift Mitigation on LiDAR PointCloud](https://mlsanity.com/paper/2405.11536/) (2024)
- [FastTracker: Real-Time and Accurate Visual Tracking](https://mlsanity.com/paper/2508.14370/) (2025)
- [Towards Accurate State Estimation: Motion Dynamics Kalman Filter for 3D Multi-Object Tracking](https://mlsanity.com/paper/2505.07254/) (2025)

## Built on by (most cited first, 1 of 1)

- [ReWorld-Track: A Recursive Event World Model for Language-Guided Multi-Camera Tracking](https://mlsanity.com/paper/2609.36677/) (2026)

## Abstract (arXiv)

The tracking-by-detection paradigm in multi-object tracking (MOT) typically relies on static appearance descriptors to complement motion estimation. However, these descriptors are frame-independent, limiting their robustness as visual cues. Since such descriptors are often obtained from computationally intensive pretrained backbones, real-time MOT systems frequently abandon appearance cues altogether and rely solely on motion prediction and geometric association. In this work, we introduce Polycepta, an object-centric appearance state estimation framework that reformulates appearance modeling as a recursive estimation problem rather than a frame-wise matching task. Polycepta constructs and continuously updates an independent appearance state for each tracked object, enabling future appearance representations to be estimated from accumulated observations. Polycepta is encouraged to learn the appearance-state construction of object-specific representations rather than memorize them through a proposed learning strategy, enabling appearance estimation for unseen classes. A key property of Polycepta is that the quality of appearance estimation improves as object states evolve during inference. While conventional appearance descriptors remain static or degrade over time, Polycepta progressively refines appearance estimates as additional observations are accumulated. Extensive experiments on KITTI, the Waymo Open Dataset, and MOT17 demonstrate consistent reductions in identity switches and improvements in tracking performance when integrated into the tracking-by-detection pipelines. Polycepta operates at 90.57 Hz and delivers state-of-the-art performance on the KITTI benchmark, achieving a MOTA of 92.27%.