# Valeo4Cast: A Modular Approach to End-to-End Forecasting

arXiv: https://arxiv.org/abs/2406.08113 · HTML: https://mlsanity.com/paper/2406.08113/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 33 references that are in the map.
- First posted on arXiv 12 Jun 2024.

## Builds on (most cited first, 28 of 28)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking](https://mlsanity.com/paper/2009.07736/) (2020)
- [Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset](https://mlsanity.com/paper/2104.10133/) (2021)
- [AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting](https://mlsanity.com/paper/2103.14023/) (2021)
- [Wayformer: Motion Forecasting via Simple & Efficient Attention Networks](https://mlsanity.com/paper/2207.05844/) (2022)
- [Motion Transformer with Global Intention Localization and Local Movement Refinement](https://mlsanity.com/paper/2209.13508/) (2022)
- [VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking](https://mlsanity.com/paper/2303.11301/) (2023)
- [3D Object Detection with Pointformer](https://mlsanity.com/paper/2012.11409/) (2020)
- [Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction](https://mlsanity.com/paper/2104.00563/) (2021)
- [ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queries](https://mlsanity.com/paper/2208.01582/) (2022)
- [MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries](https://mlsanity.com/paper/2205.00613/) (2022)
- [LaPred: Lane-Aware Prediction of Multi-Modal Future Trajectories of Dynamic Agents](https://mlsanity.com/paper/2104.00249/) (2021)
- [FocalFormer3D : Focusing on Hard Instance for 3D Object Detection](https://mlsanity.com/paper/2308.04556/) (2023)
- [UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction](https://mlsanity.com/paper/2403.15098/) (2024)
- [Three Pillars improving Vision Foundation Model Distillation for Lidar](https://mlsanity.com/paper/2310.17504/) (2023)
- [TransCenter: Transformers with Dense Representations for Multiple-Object Tracking](https://mlsanity.com/paper/2103.15145/) (2021)
- [Towards Long-Tailed 3D Detection](https://mlsanity.com/paper/2211.08691/) (2022)
- [EA-LSS: Edge-aware Lift-splat-shot Framework for 3D BEV Object Detection](https://mlsanity.com/paper/2303.17895/) (2023)
- [Forecasting from LiDAR via Future Object Detection](https://mlsanity.com/paper/2203.16297/) (2022)
- [Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?](https://mlsanity.com/paper/2306.09281/) (2023)
- [Technical Report for Argoverse Challenges on Unified Sensor-based Detection, Tracking, and Forecasting](https://mlsanity.com/paper/2311.15615/) (2023)
- [Raising context awareness in motion forecasting](https://mlsanity.com/paper/2109.08048/) (2021)

## Built on by (most cited first, 5 of 5)

- [RefAV: Towards Planning-Centric Scenario Mining](https://mlsanity.com/paper/2505.20981/) (2025)
- [Annealed Winner-Takes-All for Motion Forecasting](https://mlsanity.com/paper/2409.11172/) (2024)
- [PPT: Pretraining with Pseudo-Labeled Trajectories for Motion Forecasting](https://mlsanity.com/paper/2412.06491/) (2024)
- [Li-ViP3D++: Query-Gated Deformable Camera-LiDAR Fusion for End-to-End Perception and Trajectory Prediction](https://mlsanity.com/paper/2601.20720/) (2026)
- [Towards Collaborative Joint Perception and Prediction: Framework, Baseline Evaluation, and Deployment Perspectives](https://mlsanity.com/paper/2608.09541/) (2026)

## Abstract (arXiv)

Motion forecasting is crucial in autonomous driving systems to anticipate the future trajectories of surrounding agents such as pedestrians, vehicles, and traffic signals. In end-to-end forecasting, the model must jointly detect and track from sensor data (cameras or LiDARs) the past trajectories of the different elements of the scene and predict their future locations. We depart from the current trend of tackling this task via end-to-end training from perception to forecasting, and instead use a modular approach. We individually build and train detection, tracking and forecasting modules. We then only use consecutive finetuning steps to integrate the modules better and alleviate compounding errors. We conduct an in-depth study on the finetuning strategies and it reveals that our simple yet effective approach significantly improves performance on the end-to-end forecasting benchmark. Consequently, our solution ranks first in the Argoverse 2 End-to-end Forecasting Challenge, with 63.82 mAPf. We surpass forecasting results by +17.1 points over last year's winner and by +13.3 points over this year's runner-up. This remarkable performance in forecasting can be explained by our modular paradigm, which integrates finetuning strategies and significantly outperforms the end-to-end-trained counterparts. The code, model weights and results are made available https://github.com/valeoai/valeo4cast.