DERD-Net: Learning Depth from Event-based Ray Densities (NeurIPS 2025 Spotlight)

Project page: https://github.com/tub-rip/DERD-Net
PDF: https://arxiv.org/pdf/2504.15863

Event cameras offer a promising avenue for multi-view stereo depth estimation and Simultaneous Localization And Mapping (SLAM) due to their ability to detect blur-free 3D edges at high-speed and over broad illumination conditions. However, traditional deep learning frameworks designed for conventional cameras struggle with the asynchronous, stream-like nature of event data, as their architectures are optimized for discrete, image-like inputs. We propose a scalable, flexible and adaptable framework for pixel-wise depth estimation with event cameras in both monocular and stereo setups. The 3D scene structure is encoded into disparity space images (DSIs), representing spatial densities of rays obtained by back-projecting events into space via known camera poses. Our neural network processes local subregions of the DSIs combining 3D convolutions and a recurrent structure to recognize valuable patterns for depth prediction. Local processing enables fast inference with full parallelization and ensures constant ultra-low model complexity and memory costs, regardless of camera resolution. Experiments on standard benchmarks (MVSEC and DSEC datasets) demonstrate unprecedented effectiveness: (i) using purely monocular data, our method achieves comparable results to existing stereo methods; (ii) when applied to stereo data, it strongly outperforms all state-of-the-art (SOTA) approaches, reducing the mean absolute error by at least 42%; (iii) our method also allows for increases in depth completeness by more than 3-fold while still yielding a reduction in median absolute error of at least 30%. Given its remarkable performance and effective processing of event-data, our framework holds strong potential to become a standard approach for using deep learning for event-based depth estimation and SLAM.

Reference:
Diego Hitzges, Suman Ghosh, Guillermo Gallego,
DERD-Net: Learning Depth from Event-based Ray Densities,
39th Conference on Neural Information Processing Systems (NeurIPS 2025).

Affiliations:
The authors are with TU Berlin, the Einstein Center Digital Future, the SCIoI Excellence Cluster, Berlin, and the Robotics Institute Germany (RIG), Berlin, Germany.

Event-based Vision:
Research: https://sites.google.com/view/guiller...
Code: https://github.com/tub-rip/event-visi...
Survey paper (TPAMI 2022): https://arxiv.org/abs/1904.08405
Survey on Event-based Stereo (TPAMI 2025): https://github.com/tub-rip/EventStere...
Course at TU Berlin: https://sites.google.com/view/guiller...