Jinfu Yang

Accurate perception of scene geometry is a critical aspect of enabling Internet of Video Things (IoVT) devices to perform environmental perception and interaction. Monocular depth estimation has garnered widespread attention due to its configuration simplicity. However, existing methods often struggle to fully exploit the uniqueness and complementarity between single-frame and multiframe cues, resulting in degraded accuracy and robustness in dynamic environments. In this article, we propose a multiframe monocular depth estimation method based on dual-branch cost volume fusion (DB-CVF) in dynamic environments, which addresses the aforementioned issues through the unique representation and complementary fusion of cost volumes. DB-CVF represents the single-frame and multiframe cues as multiscale self-cost volume and attention-aware cross-cost volume, respectively, and achieves complementary fusion through a multicue cost volume fusion (MC-CVF) module. A single-frame cue generation (SFCG) module and an attention-aware multiframe cue generation (A²-MFCG) module are designed in a dual-stream structure to separately generate two types of cost volumes within the same latent space. The two types of cost volumes, each with its own uniqueness, realize information interaction and mutual benefit by the designed MC-CVF module based on the cross-attention mechanism. Extensive quantitative and qualitative results demonstrate that DB-CVF achieves outstanding performance on the KITTI, DDAD, and Cityscapes datasets. Compared to the state-of-the-art method, DB-CVF reduces the depth error in dynamic regions by 17.8%, showcasing the broad potential of cue fusion for monocular depth estimation.