SynFlow: Scaling Up LiDAR Scene Flow Estimation with Synthetic Data
Reliable 3D dynamic perception requires models that can anticipate motion beyond predefined categories, yet progress is hindered by the scarcity of dense, high-quality motion annotations. While self-supervision on unlabeled real data offers a path forward, empirical evidence suggests that scaling unlabeled data fails to close the performance gap due to noisy proxy signals. In this paper, we propose learning robust real-world motion priors entirely from scalable simulation. We introduce SynFlow, a data generation pipeline for large-scale synthetic LiDAR scene flow. Unlike prior works that prioritize sensor-specific realism, SynFlow employs a motion-oriented strategy to synthesize diverse k...
| Authors | Qingwen Zhang, Xiaomeng Zhu, Chenhan Jiang et al. |
|---|---|
| Primary category | cs.CV |
| Published | 10 April 2026 |
| Last updated at source | 28 July 2026 |
Models and datasets referencing this paper
- KTH/SynFlowDataset
- kin-zhang/multidata-sf-challengeDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.