# Depth Any Seen: Which Surfaces and How Far?

arXiv: https://arxiv.org/abs/2609.32027 · HTML: https://mlsanity.com/paper/2609.32027/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 41 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Builds on (most cited first, 2 of 2)

- [World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible](https://mlsanity.com/paper/2606.13652/) (2026)
- [Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation](https://mlsanity.com/paper/2606.02552/) (2026)

## Abstract (arXiv)

When several surfaces are visible along a ray, recovering visible 3D structure from one image requires jointly estimating their presence and metric depth. Depth Any Seen represents these surfaces as image-conditioned multi-Bernoulli depth sets, whose components each contribute one depth or remain absent. Its auxiliary-free Exact Multi-Bernoulli objective (ExactMB) learns depth and presence by marginalizing one-to-one assignments to complete, distinct targets. Our analysis shows that matching expected count can leave component-surface assignment unresolved. We extend real and synthetic layered-depth benchmarks to evaluate depth accuracy, recovered support, and overprediction. Compared to depth stacking, ExactMB reduces overprediction by a relative 88.2% on LD-Real and 80.5% on MD-3K while retaining most ordinal accuracy, with comparable conditional metric-depth error on LD-Syn. Further ablation studies show that ordered assignment improves depth-accurate recall and precision over marginalization, whereas the count-regularized configuration achieves higher deeper-rank precision than ordered assignment at lower recall. Our code will be publicly released.