SOURCE-LINKED INTELLIGENCE

When Depth Hurts: Reliability-Aware Geometry Distillation for Depth-Free RGB-D Salient Object Detection

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Depth can resolve appearance ambiguity in RGB-D salient object detection (SOD), yet sensor depth is not uniformly reliable. Missing regions, blurred boundaries, and structural artifacts can propagate through multimodal fusion and make an RGB-D detector less accurate than its RGB-only counterpart. Existing quality-aware approaches regulate observed depth but remain dependent on the same potentially defective modality. We propose \method, a reliability-aware geometry distillation framework developed for RGB-D SOD benchmarks without using dataset-provided depth during training or inference. A fro

Read original source ↗ Open in workspace

recordType

paper

region

Global