SOURCE-LINKED INTELLIGENCE

CrossDepth: Geometry-Constrained Attention for Generalizable Multi-View Surround Depth Estimation

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

Reliable 3D understanding of the surrounding environment is a core requirement for autonomous driving. Multi-view surround camera rigs provide broad scene coverage, but the spatially adjacent images typically overlap only minimally. Consequently, the depth of most pixels must be inferred from monocular appearance cues. These cues can appear differently across images and may therefore be interpreted differently by the depth estimation model. We target two main sources of cross-image inconsistency: differences in camera intrinsics and the limited receptive field of each image. We address the for

Read original source ↗ Open in workspace

recordType

paper

region

Global