# QualiaNet: An Experience-Before-Inference Network

arXiv: https://arxiv.org/abs/2604.14193 · HTML: https://mlsanity.com/paper/2604.14193/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 13 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Builds on (most cited first, 5 of 5)

- [The 3D-PC: a benchmark for visual perspective taking in humans and machines](https://mlsanity.com/paper/2406.04138/) (2024)
- [Approaching human 3D shape perception with neurally mappable models](https://mlsanity.com/paper/2308.11300/) (2023)
- [A topological solution to object segmentation and tracking](https://mlsanity.com/paper/2107.02036/) (2021)
- [Human-level 3D shape perception emerges from multi-view learning](https://mlsanity.com/paper/2602.17650/) (2026)
- [Linton Stereo Illusion](https://mlsanity.com/paper/2408.00770/) (2024)

## Abstract (arXiv)

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.