一景，兩深度：探討單目基礎模型中的幾何歧義

摘要

一個忠實的3D世界表徵應能考慮分層幾何結構，即單一相機光線可能包含多個可見且幾何有效的表面。然而，單眼深度估計將此結構簡化為每個像素的單一深度值。透明場景使得此歧義性變得可測量：同一條光線可穿過前景玻璃並觀測到背景，使得監督目標成為一種標註、數據與訓練的慣例，而非場景固有的真實值。學習型預測器將其深度層偏好暴露於此慣例之中。我們提出了MultiDepth-3k（MD-3k），一個稀疏的雙層序數基準，用於衡量深度層偏好與多層空間關係準確度（ML-SRA）。在MD-3k上，領先的深度基礎模型在標準RGB輸入下展現出多樣的層偏好，顯示相同的分層幾何結構在不同模型中會被解析出不同結果。我們進一步發現，拉普拉斯視覺提示（LVP）——一種無需訓練的頻譜輸入變換——能顯著改變某些凍結模型所報告的層級。最強的RGB/LVP配對DAv2-L達到了75.5%的ML-SRA。這些結果表明，深度基礎模型可能表達出互補的幾何假設，而這些假設在標準RGB推論中未被表達出來。我們邀請學術界以歧義感知的角度重新思考深度監督與評估，將多種有效的3D解讀視為應被測量、保留並表達的幾何結構。

English

A faithful 3D world representation should account for layered geometry, where a single camera ray may contain multiple visible and geometrically valid surfaces. Monocular depth estimation, however, reduces this structure to one scalar depth per pixel. Transparent scenes make this ambiguity measurable: the same ray can pass through foreground glass and observe the background, turning the supervised target into a convention of annotation, data, and training rather than a scene-intrinsic truth. A learned predictor exposes this convention as its depth-layer preference. We introduce MultiDepth-3k (MD-3k), a sparse two-layer ordinal benchmark for measuring depth-layer preference and multi-layer spatial relationship accuracy (ML-SRA). On MD-3k, leading depth foundation models exhibit diverse layer preferences under standard RGB input, showing that the same layered geometry can be resolved differently across models. We further find that Laplacian Visual Prompting (LVP), a training-free spectral input transformation, can substantially change the reported layer for certain frozen models. The strongest RGB/LVP pair, DAv2-L, reaches 75.5% ML-SRA. These results suggest that depth foundation models may express complementary geometric hypotheses that standard RGB inference leaves unexpressed. We invite the community to rethink depth supervision and evaluation through an ambiguity-aware lens, where multiple valid 3D interpretations are treated as geometric structure to be measured, preserved, and expressed.