# MASAR: Motion-Appearance Synergy Refinement for Joint Detection and Trajectory Forecasting

Source: [MASAR: Motion-Appearance Synergy Refinement for Joint Detection and Trajectory Forecasting](<https://www.sota2.com/research/paper/6992a47d9ebc499c97406c37>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-17T05:00:04.915Z

Authors: Mohammed Amine Bencheikh Lehocine, Julian Schmidt, Frank Moosmann, Dikshant Gupta, Fabian Flohr

Published: 2026-02-13T15:11:50.000Z

## Abstract

Classical autonomous driving systems connect perception and prediction modules via hand-crafted bounding-box interfaces, limiting information flow and propagating errors to downstream tasks. Recent research aims to develop end-to-end models that jointly address perception and prediction; however, they often fail to fully exploit the synergy between appearance and motion cues, relying mainly on short-term visual features. We follow the idea of "looking backward to look forward", and propose MASAR, a novel fully differentiable framework for joint 3D detection and trajectory forecasting compatible with any transformer-based 3D detector. MASAR employs an object-centric spatio-temporal mechanism that jointly encodes appearance and motion features. By predicting past trajectories and refining them using guidance from appearance cues, MASAR captures long-term temporal dependencies that enhance future trajectory forecasting. Experiments conducted on the nuScenes dataset demonstrate MASAR's effectiveness, showing improvements of over 20% in minADE and minFDE while maintaining robust detection performance. Code and models are available at https://github.com/aminmed/MASAR.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Trajectory Forecasting on nuScenes (val)](<https://www.sota2.com/research/sota/trajectory-forecasting-on-nuscenes-val.md>): Trajectory Forecasting; nuScenes (val); EPA: 0.492.

- [3D Object Detection on nuScenes (val)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-val.md>): 3D Object Detection; nuScenes (val); NDS: 57.6.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.13003>)

[PDF](<https://arxiv.org/pdf/2602.13003.pdf>)