# DPG-CD: Depth-Prior-Guided Cross-Modal Joint 2D-3D Change Detection

arXiv: https://arxiv.org/abs/2605.07151 · HTML: https://mlsanity.com/paper/2605.07151/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 53 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 15 of 15)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Fully Convolutional Siamese Networks for Change Detection](https://mlsanity.com/paper/1810.08462/) (2018)
- [A Transformer-Based Siamese Network for Change Detection](https://mlsanity.com/paper/2201.01293/) (2022)
- [MambaVision: A Hybrid Mamba-Transformer Vision Backbone](https://mlsanity.com/paper/2407.08083/) (2024)
- [ChangeMamba: Remote Sensing Change Detection With Spatiotemporal State Space Model](https://mlsanity.com/paper/2404.03425/) (2024)
- [Deep Learning in Multimodal Remote Sensing Data Fusion: A Comprehensive Review](https://mlsanity.com/paper/2205.01380/) (2022)
- [Adjacent-Level Feature Cross-Fusion With 3-D CNN for Remote Sensing Image Change Detection](https://mlsanity.com/paper/2302.05109/) (2023)
- [Inferring 3D change detection from bitemporal optical images](https://mlsanity.com/paper/2205.15903/) (2022)
- [R2FD2: Fast and Robust Matching of Multimodal Remote Sensing Image via Repeatable Feature Detector and Rotation-invariant Feature Descriptor](https://mlsanity.com/paper/2212.02277/) (2022)
- [Transformer-based Multimodal Change Detection with Multitask Consistency Constraints](https://mlsanity.com/paper/2310.09276/) (2023)
- [ME-CPT: Multi-Task Enhanced Cross-Temporal Point Transformer for Urban 3D Change Detection](https://mlsanity.com/paper/2501.14004/) (2025)
- [MSSDF: Modality-Shared Self-supervised Distillation for High-Resolution Multi-modal Remote Sensing Image Learning](https://mlsanity.com/paper/2506.09327/) (2025)
- [HiRes-FusedMIM: A High-Resolution RGB-DSM Pre-trained Model for Building-Level Remote Sensing Applications](https://mlsanity.com/paper/2503.18540/) (2025)

## Abstract (arXiv)

Urban spatial evolution is manifested not only through horizontal expansion but also through vertical structural changes. Consequently, jointly capturing 2D semantic changes and 3D height changes is essential for urban morphology analysis and emergency management. In practical scenarios, collecting 3D observations is often constrained by high acquisition costs and the inability to support frequent updates. The multi-temporal cross-modal input consisting of pre-event Digital Surface Model (DSM) and post-event imagery provides a practical solution for 3D change detection in high-frequency urban monitoring, disaster assessment, and emergency response scenarios. However, this setting remains challenging as imagery and DSM data exhibit significant spectral-geometric representation gaps. Moreover, modality differences may be confused with actual changes, and robust change detection requires effective fusion of semantic and geometric features from multi-temporal data. In this paper, we propose DPG-CD, a depth-prior-guided multi-temporal cross-modal fusion framework for joint 2D semantic and 3D height change detection. Specifically, an estimated depth prior is introduced into the imagery to mitigate the modality gap with DSM. A gated fusion mechanism then selectively injects geometric cues from depth prior while preserving discriminative spectral representations. Subsequently, a multi-stage cross-temporal cross-modal feature fusion architecture is employed to extract change-aware features. Finally, a multi-task decoder jointly predicts 2D semantic changes and 3D height changes, complemented by an auxiliary DSM prediction task to improve structural consistency and height estimation accuracy. Experiments on two public datasets, Hi-BCD and 3DCD, and a new dataset, NYC-MMCD, demonstrate that DPG-CD outperforms state-of-the-art methods on both 2D and 3D change detection tasks.