# Iris-Z: Scaling One Generative Model Past Specialist Geometry Models

DevFeed: [Iris-Z: Scaling One Generative Model Past Specialist Geometry Models](<https://devfeed.tech/articles/iris-z-scaling-one-generative-model-past-specialist-geometry-models-132188.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.16010>)

Author: Alejandro Ca\\~nada, Chema Garabito

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Image](<https://devfeed.tech/topics/image.md>), [3D](<https://devfeed.tech/topics/3d.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [generative](<https://devfeed.tech/tags/generative.md>), [generator](<https://devfeed.tech/tags/generator.md>), [image](<https://devfeed.tech/tags/image.md>), [model](<https://devfeed.tech/tags/model.md>), [scaling](<https://devfeed.tech/tags/scaling.md>), [spatial](<https://devfeed.tech/tags/spatial.md>), [vision](<https://devfeed.tech/tags/vision.md>)

## AI overview

Iris-Z uses one image-generating backbone and shared weights to produce images with depth, estimate depth from photographs, and render images onto supplied depth maps. The authors report that, at sufficient scale, it exceeds specialist models on established depth benchmarks while retaining its starting backbone's generative abilities without specialized layers. The abstract describes this as evidence for scaling a unified architecture on monocular geometry and says two models are being released.

## Source excerpt

arXiv:2611.16010v1 Announce Type: cross Abstract: Language moved from many task-specific models to one unified model: a single generative model with a single generative training task that handles all of them within the same backbone, and keeps improving with data, parameters and compute. We believe the bitter lesson applies just as much to computer vision, 3D and spatial understanding, in the end to visual intelligence: the effort should go into general architectures that solve all these tasks in a unified way, and into scaling them, rather than into task-specific designs. We test this on monocular geometry, a task that has belonged to specialised architectures for years. Iris-Z is a general image generator that produces appearance and geometry together. A single backbone denoises, reasons about and understands the image and its depth at the same time, and one set of weights generates images with their depth, estimates depth from photographs and paints images onto a given depth. At enough scale it surpasses state-of-the-art specialists on established depth benchmarks while keeping the generative abilities of the backbone it started from without specialized layers. We release two models for the community.