Iris-Z 论文：单一生成模型在深度估计上超越专用几何模型
Iris-Z: Scaling One Generative Model Past Specialist Geometry Models
AI 导读
arXiv 论文 arXiv:2611.16010 提出 Iris-Z，一个通用图像生成模型，单一骨干网络同时去噪、推理并生成外观与几何，无需专用层即可生成带深度的图像、从照片估计深度以及按给定深度上色。作者认为 bitter lesson 同样适用于视觉智能，在足够规模下该模型在既有深度基准上超过 SOTA 专用模型，并已向社区开源两个模型。
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