MASAR: Motion-Appearance Synergy Refinement for Joint Detection and Trajectory Forecasting
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914328404295680 |
|---|---|
| author | Lehocine, Mohammed Amine Bencheikh Schmidt, Julian Moosmann, Frank Gupta, Dikshant Flohr, Fabian |
| author_facet | Lehocine, Mohammed Amine Bencheikh Schmidt, Julian Moosmann, Frank Gupta, Dikshant Flohr, Fabian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13003 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MASAR: Motion-Appearance Synergy Refinement for Joint Detection and Trajectory Forecasting Lehocine, Mohammed Amine Bencheikh Schmidt, Julian Moosmann, Frank Gupta, Dikshant Flohr, Fabian Computer Vision and Pattern Recognition Machine Learning 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. |
| title | MASAR: Motion-Appearance Synergy Refinement for Joint Detection and Trajectory Forecasting |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2602.13003 |