SOURCE-LINKED INTELLIGENCE

Depth-to-Image Synthesis-Driven Generative Unguided Depth Completion

arXiv · AI, language, vision and robotics · article · Sep 5, 2026 · UTC

Guided depth completion methods heavily depend on RGB quality and alignment, while unguided ones often suffer from limited precision due to the absence of explicit visual cues. In this paper, we present Depth-to-Image Synthesis-Driven Generative Unguided Depth Completion (GUDC), a new completion paradigm that innovatively bridges advanced 2D generative models with unguided depth completion, enabling semantics-aware depth inference without real RGB inputs. Our key idea is to exploit ControlNet's powerful depth-conditioned generation capability to synthesize pseudo-images directly from sparse de

Read original source ↗ Open in workspace

recordType

paper

region

Global