RDANet: Parameter-Efficient Cross-Dataset Adaptation for Event-Based Monocular Depth Estimation
Source abstract
Abstract
Event cameras capture sparse, high-temporal-resolution visual information, making them attractive for challenging scenarios with fast motion and severe illumination changes. However, event-based depth models trained on one real-world benchmark often degrade substantially when transferred to another, revealing a practical cross-dataset domain shift between real sensor datasets. In this work, we study parameter-efficient adaptation from MVSEC to DSEC using a frozen VFM-based recurrent depth backbone. We systematically compare several parameter-efficient fine-tuning (PEFT) strategies, including Bias-only, Adapter, Decoder Weight Tuning, ConvLSTM-only, and FiLM-based modulation, under labeled few-shot adaptation. Across three random seeds, Bias-only achieves the best few-shot accuracy, reaching 0.189 AbsRel with 150 calibration samples. Decoder-side FiLM provides the best accuracy–efficiency trade-off, maintaining stable performance while updating only 2048 parameters, and reaches 0.176 AbsRel when trained with the full DSEC training set under our protocol. Our study shows that tuning native pretrained parameters is a strong baseline in this specific MVSEC → DSEC event-depth adaptation setting, whereas higher-capacity auxiliary modules are less effective under limited target-domain supervision. These results establish a controlled MVSEC → DSEC benchmark and provide practical guidance for adapting event-based monocular depth models under cross-dataset transfer.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Memory and Neural Computing · Advanced Optical Sensing Technologies · Advanced Vision and Imaging
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computing, Gachon University, Seongnam-si 13120, Republic of Korea
Funding
National Research Foundation of Korea · Gachon University
References (40)
Show source-provided references
1. Eigen, D., Puhrsch, C., and Fergus, R. (2014). Depth Map Prediction from a Single Image Using a Multi-Scale Deep Network. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Curran Associates.
2. Make3D: Learning 3D Scene Structure from a Single Still Image10.1109/TPAMI.2008.132 ↗
3. Godard, C., Mac Aodha, O., and Brostow, G.J. (2019). Digging into Self-Supervised Monocular Depth Estimation. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), IEEE.10.1109/ICCV.2019.00393 ↗
4. Ranftl, R., Bochkovskiy, A., and Koltun, V. (2021). Vision Transformers for Dense Prediction. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), IEEE.10.1109/ICCV48922.2021.01196 ↗
5. Event-Based Vision: A Survey10.1109/TPAMI.2020.3008413 ↗
6. A 240 × 180 130 dB 3 μs Latency Global Shutter Spatiotemporal Vision Sensor10.1109/JSSC.2014.2342715 ↗
7. A 128 × 128 120 dB 15 μs Latency Asynchronous Temporal Contrast Vision Sensor10.1109/JSSC.2007.914337 ↗
8. Bartolomei, L., Mannocci, E., Tosi, F., Poggi, M., and Mattoccia, S. (2025). Depth AnyEvent: A Cross-Modal Distillation Paradigm for Event-Based Monocular Depth Estimation. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), IEEE.10.1109/ICCV51701.2025.01829 ↗
9. Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., and Zhao, H. (2024). Depth Anything V2. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Curran Associates.
10. Combining Events and Frames Using Recurrent Asynchronous Multimodal Networks10.1109/LRA.2021.3060707 ↗
11. DSEC: A Stereo Event Camera Dataset for Driving Scenarios10.1109/LRA.2021.3068942 ↗
12. The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception10.1109/LRA.2018.2800793 ↗
13. Li, Y., Wang, N., Shi, J., Liu, J., and Hou, X. (2016). Revisiting Batch Normalization for Practical Domain Adaptation. arXiv.
14. Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., and El-Nouby, A. (2024). DINOv2: Learning Robust Visual Features without Supervision. Trans. Mach. Learn. Res.
15. Jia, M., Tang, L., Chen, B., Cardie, C., Belongie, S., Hariharan, B., and Lim, S. (2022). Visual Prompt Tuning. Proceedings of the European Conference on Computer Vision (ECCV), Springer.10.1007/978-3-031-19827-4_41 ↗
16. Zhou, T., Brown, M., Snavely, N., and Lowe, D.G. (2017). Unsupervised Learning of Depth and Ego-Motion from Video. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.10.1109/CVPR.2017.700 ↗
17. Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross-Dataset Transfer10.1109/TPAMI.2020.3019967 ↗
18. Gao, X., Shi, Y., Zhao, Y., Wang, Y., Wang, J., and Wu, G. (2025). CAPDepth: 360 Monocular Depth Estimation by Content-Aware Projection. Appl. Sci., 15.10.3390/app15020769 ↗
19. Hidalgo-Carrió, J., Gehrig, D., and Scaramuzza, D. (2020). Learning Monocular Dense Depth from Events. Proceedings of the International Conference on 3D Vision (3DV), IEEE.10.1109/3DV50981.2020.00063 ↗
20. Event-Based Monocular Depth Estimation with Recurrent Transformers10.1109/TCSVT.2024.3378742 ↗
21. Deep Event Stereo Leveraged by Event-to-Image Translation10.1609/aaai.v35i2.16171 ↗
22. Unsupervised Deep Event Stereo for Depth Estimation10.1109/TCSVT.2022.3189480 ↗
23. Two-stage cross-fusion network for stereo event-based depth estimation10.1016/j.eswa.2023.122743 ↗
24. Depth cue fusion for event-based stereo depth estimation10.1016/j.inffus.2024.102891 ↗
25. Zheng, C., Cham, T.J., and Cai, J. (2018). T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks. Proceedings of the European Conference on Computer Vision (ECCV), Springer.10.1007/978-3-030-01234-2_47 ↗
26. Casser, V., Pirk, S., Mahajan, R., and Angelova, A. (2019). Depth Prediction Without the Sensors. Proceedings of the AAAI Conference on Artificial Intelligence, AAAI.10.1609/aaai.v33i01.33018001 ↗
27. Zhao, S., Fu, H., Gong, M., and Tao, D. (2020). Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.10.1109/CVPR.2019.01002 ↗
28. Ganin, Y., and Lempitsky, V. (2015). Unsupervised Domain Adaptation by Backpropagation. Proceedings of the International Conference on Machine Learning (ICML), PMLR.
29. Wang, D., Shelhamer, E., Liu, S., Olshausen, B., and Darrell, T. (2021, January 3–7). Tent: Fully Test-Time Adaptation by Entropy Minimization. Proceedings of the International Conference on Learning Representations (ICLR), Virtual Event, Austria.
30. Liang, J., Hu, D., and Feng, J. (2020). Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation. Proceedings of the International Conference on Machine Learning (ICML), PMLR.
31. Parameter-Efficient Fine-Tuning of Large-Scale Pre-Trained Language Models10.1038/s42256-023-00626-4 ↗
32. Houlsby, N., Giurgiu, A., Jastrzebski, S., Morrone, B., Laroussilhe, Q., Gesmundo, A., Attariyan, M., and Gelly, S. (2019). Parameter-Efficient Transfer Learning for NLP. Proceedings of the International Conference on Machine Learning (ICML), PMLR.
33. Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., and Chen, W. (2022, January 25). LoRA: Low-Rank Adaptation of Large Language Models. Proceedings of the International Conference on Learning Representations (ICLR), Virtual.
34. Perez, E., Strub, F., de Vries, H., Dumoulin, V., and Courville, A. (2018). FiLM: Visual Reasoning with a General Conditioning Layer. Proceedings of the AAAI Conference on Artificial Intelligence, AAAI.10.1609/aaai.v32i1.11671 ↗
35. Oreshkin, B.N., Rodríguez López, P., and Lacoste, A. (2018). TADAM: Task Dependent Adaptive Metric for Improved Few-Shot Learning. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Curran Associates.
36. Huang, X., and Belongie, S. (2017). Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), IEEE.10.1109/ICCV.2017.167 ↗
37. Zhang, J., and Singh, S. (2014). LOAM: Lidar Odometry and Mapping in Real-Time. Proceedings of Robotics: Science and Systems (RSS), MIT Press.10.15607/RSS.2014.X.007 ↗
38. Huang, Z., Sun, L., Zhao, C., Li, S., and Su, S. (2023). EventPoint: Self-Supervised Interest Point Detection and Description for Event-Based Camera. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), IEEE.10.1109/WACV56688.2023.00536 ↗
39. Shi, X., Chen, Z., Wang, H., Yeung, D., Wong, W., and Woo, W. (2015). Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Curran Associates.
40. Loshchilov, I., and Hutter, F. (2019, January 6–9). Decoupled Weight Decay Regularization. Proceedings of the International Conference on Learning Representations (ICLR), New Orleans, LA, USA.