# Iris: Integrating Language into Diffusion-based Monocular Depth Estimation

arXiv: https://arxiv.org/abs/2411.16750 · HTML: https://mlsanity.com/paper/2411.16750/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2024.

## Built on by (most cited first, 5 of 5)

- [From Editor to Dense Geometry Estimator](https://mlsanity.com/paper/2509.04338/) (2025)
- [Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation](https://mlsanity.com/paper/2503.15905/) (2025)
- [ProtoDepth: Unsupervised Continual Depth Completion with Prototypes](https://mlsanity.com/paper/2503.12745/) (2025)
- [Radar-Guided Polynomial Fitting for Metric Depth Estimation](https://mlsanity.com/paper/2503.17182/) (2025)
- [Sonic-AMG: Streaming Human Motion Generation from Spatial Audio](https://mlsanity.com/paper/2610.13300/) (2026)

## Abstract (arXiv)

Traditional monocular depth estimation suffers from inherent ambiguity and visual nuisances. We demonstrate that language can enhance monocular depth estimation by providing an additional condition (rather than images alone) aligned with plausible 3D scenes, thereby reducing the solution space for depth estimation. This conditional distribution is learned during the text-to-image pre-training of diffusion models. To generate images under various viewpoints and layouts that precisely reflect textual descriptions, the model implicitly models object sizes, shapes, and scales, their spatial relationships, and the overall scene structure. In this paper, Iris, we investigate the benefits of our strategy to integrate text descriptions into training and inference of diffusion-based depth estimation models. We experiment with three different diffusion-based monocular depth estimators (Marigold, Lotus, and E2E-FT) and their variants. By training on HyperSim and Virtual KITTI, and evaluating on NYUv2, KITTI, ETH3D, ScanNet, and DIODE, we find that our strategy improves the overall monocular depth estimation accuracy, especially in small areas. It also improves the model's depth perception of specific regions described in the text. We find that by providing more details in the text, the depth prediction can be iteratively refined. Simultaneously, we find that language can act as a constraint to accelerate the convergence of both training and the inference diffusion trajectory. Code and generated text data will be released upon acceptance.