用视觉经验推断距离，仅靠视差梯度就能还原深度。
QualiaNet: An Experience-Before-Inference Network
- 分两阶段建模：先生成人类立体视觉体验，再推理场景深度。
- 仅凭视差梯度即可准确恢复距离，无需绝对深度信息。
- 适合研究感知机制或生物启发视觉系统的学者。
人类3D视觉包含两个阶段：经验模块中，相对于注视点提取立体深度；推断模块中，基于此经验估计场景三维属性。矛盾的是，尽管立体视觉不提供绝对距离信息，却仍影响我们对距离的判断。我们提出推断模块利用自然场景统计规律：近处景物产生鲜明的视差梯度，远处则相对平坦。QualiaNet计算实现了这一双阶段架构：模拟人类立体视觉的视差图输入一个训练过的CNN以估计距离。该网络仅依靠视差梯度即可恢复距离，验证了该方法的有效性。
原文摘要 · Abstract (English)
Human 3D vision involves two distinct stages: an Experience Module, where stereo depth is extracted relative to fixation, and an Inference Module, where this experience is interpreted to estimate 3D scene properties. Paradoxically, although stereo vision does not provide us with absolute distance information, it nonetheless affects our inferences about distance. We propose the Inference Module exploits a natural scene statistic: near scenes produce vivid disparity gradients, while far scenes appear comparatively flat. QualiaNet implements this two-stage architecture computationally: disparity maps simulating human stereo experience are passed to a CNN trained to estimate distance. The network can recover distance from disparity gradients alone, validating this approach.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。