arXiv cs.AI· Alejandro Ca\~nada, Chema Garabito·· 1 天前AI 评分58
Iris-Z：用单一生成模型超越专用几何模型
Iris-Z: Scaling One Generative Model Past Specialist Geometry Models
AI 导读
Iris-Z 是一个通用图像生成器，用同一套权重同时生成图像与深度、从照片估计深度、按给定深度生成图像，无需专用层。作者称在足够规模下，它在既有深度基准上超过 SOTA 专用模型，同时保留原主干的生成能力，并已向社区发布两个模型。论文共 14 页、9 图、6 表，代码与模型已公开。
正文 · 原文
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.
| Comments: | 14 pages, 9 figures, 6 tables. Code and models: this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| ACM classes: | I.2.10; I.4.8 |
| Cite as: | arXiv:2611.16010 [cs.CV] |
| (or arXiv:2611.16010v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.16010 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Chema Garabito [view email]
[v1]
Wed, 11 Nov 2026 21:08:37 UTC (8,141 KB)
来源：arXiv cs.AI · arxiv.org