Papers
arxiv:2506.20877

THIRDEYE: Cue-Aware Monocular Depth Estimation via Brain-Inspired Multi-Stage Fusion

Published on Jun 25
Authors:

Abstract

ThirdEye enhances monocular depth estimation by integrating specialized cues through pre-trained networks and a hierarchical fusion mechanism, leading to more accurate disparity maps.

AI-generated summary

Monocular depth estimation methods traditionally train deep models to infer depth directly from RGB pixels. This implicit learning often overlooks explicit monocular cues that the human visual system relies on, such as occlusion boundaries, shading, and perspective. Rather than expecting a network to discover these cues unaided, we present ThirdEye, a cue-aware pipeline that deliberately supplies each cue through specialised, pre-trained, and frozen networks. These cues are fused in a three-stage cortical hierarchy (V1->V2->V3) equipped with a key-value working-memory module that weights them by reliability. An adaptive-bins transformer head then produces a high-resolution disparity map. Because the cue experts are frozen, ThirdEye inherits large amounts of external supervision while requiring only modest fine-tuning. This extended version provides additional architectural detail, neuroscientific motivation, and an expanded experimental protocol; quantitative results will appear in a future revision.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2506.20877 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2506.20877 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2506.20877 in a Space README.md to link it from this page.

Collections including this paper 1