Control-DINO: Feature Space Conditioning for Controllable Image-to-Video Diffusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dominici, Edoardo A., Deixelberger, Thomas, Vardis, Konstantinos, Steinberger, Markus
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911562711695360
author Dominici, Edoardo A.
Deixelberger, Thomas
Vardis, Konstantinos
Steinberger, Markus
author_facet Dominici, Edoardo A.
Deixelberger, Thomas
Vardis, Konstantinos
Steinberger, Markus
contents Video models have recently been applied with success to problems in content generation, novel view synthesis, and, more broadly, world simulation. Many applications in generation and transfer rely on conditioning these models, typically through perceptual, geometric, or simple semantic signals, fundamentally using them as generative renderers. At the same time, high-dimensional features obtained from large-scale self-supervised learning on images or point clouds are increasingly used as a general-purpose interface for vision models. The connection between the two has been explored for subject specific editing, aligning and training video diffusion models, but not in the role of a more general conditioning signal for pretrained video diffusion models. Features obtained through self-supervised learning like DINO, contain a lot of entangled information about style, lighting and semantics of the scene. This makes them great at reconstruction tasks but limits their generative capabilities. In this paper, we show how we can use the features for tasks such as video domain transfer and video-from-3D generation. We introduce a lightweight architecture and training strategy that decouples appearance from other features that we wish to preserve, enabling robust control for appearance changes such as stylization and relighting. Furthermore, we show that low spatial resolution can be compensated by higher feature dimensionality, improving controllability in generative rendering from explicit spatial representations.
format Preprint
id arxiv_https___arxiv_org_abs_2604_01761
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Control-DINO: Feature Space Conditioning for Controllable Image-to-Video Diffusion
Dominici, Edoardo A.
Deixelberger, Thomas
Vardis, Konstantinos
Steinberger, Markus
Computer Vision and Pattern Recognition
Video models have recently been applied with success to problems in content generation, novel view synthesis, and, more broadly, world simulation. Many applications in generation and transfer rely on conditioning these models, typically through perceptual, geometric, or simple semantic signals, fundamentally using them as generative renderers. At the same time, high-dimensional features obtained from large-scale self-supervised learning on images or point clouds are increasingly used as a general-purpose interface for vision models. The connection between the two has been explored for subject specific editing, aligning and training video diffusion models, but not in the role of a more general conditioning signal for pretrained video diffusion models. Features obtained through self-supervised learning like DINO, contain a lot of entangled information about style, lighting and semantics of the scene. This makes them great at reconstruction tasks but limits their generative capabilities. In this paper, we show how we can use the features for tasks such as video domain transfer and video-from-3D generation. We introduce a lightweight architecture and training strategy that decouples appearance from other features that we wish to preserve, enabling robust control for appearance changes such as stylization and relighting. Furthermore, we show that low spatial resolution can be compensated by higher feature dimensionality, improving controllability in generative rendering from explicit spatial representations.
title Control-DINO: Feature Space Conditioning for Controllable Image-to-Video Diffusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.01761