paper-with-me

홈 › Papers

Back to the Features: DINO as a Foundation for Video World Models

2025-07-25 · Federico Baldassarre, Marc Szafraniec, Basile Terver, Vasil Khalidov, Francisco Massa, Yann LeCun, Patrick Labatut, Maximilian Seitzer, Piotr Bojanowski arxiv

We present DINO-world, a powerful generalist video world model trained to predict future frames in the latent space of DINOv2. By leveraging a pre-trained image encoder and training a future predictor on a large-scale uncurated video dataset, DINO-world learns the temporal dynamics of diverse scenes, from driving and indoor scenes to simulated environments. We show that DINO-world outperforms previous models on a variety of video prediction benchmarks, e.g. segmentation and depth forecasting, and demonstrates strong understanding of intuitive physics. Furthermore, we show that it is possible to fine-tune the predictor on observation-action trajectories. The resulting action-conditioned world model can be used for planning by simulating candidate trajectories in latent space.

📄 PDF Abstract BibTeX arXiv:2507.19468

Code (0)

등록된 구현이 없습니다.

Tasks

Video Prediction

Similar Papers 제목 키워드 기반

DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Models

2024-02-20 · Norman Di Palo, Edward Johns

We propose DINOBot, a novel imitation learning framework for robot manipulation, which leverages the image-level and pixel-level capabilities of features extracted from Vision Transformers trained with DINO. When interac…

Imitation LearningObjectRetrievalRobot Manipulation

Driving with DINO: Vision Foundation Features as a Unified Bridge for Sim-to-Real Generation in Autonomous Driving

2026-02-05 · Xuyang Chen, Conglang Zhang, Chuanheng Fu, Zihao Yang 외 arxiv

Driven by the emergence of Controllable Video Diffusion, existing Sim2Real methods for autonomous driving video generation typically rely on explicit intermediate representations to bridge the domain gap. However, these …

Dimensionality ReductionAutonomous DrivingVideo Generation

DINO-QPM: Adapting Visual Foundation Models for Globally Interpretable Image Classification

2026-04-08 · Robert Zimmermann, Thomas Norrenbrock, Bodo Rosenhahn arxiv

Although visual foundation models like DINOv2 provide state-of-the-art performance as feature extractors, their complex, high-dimensional representations create substantial hurdles for interpretability. This work propose…

Image Classification

Dino U-Net: Exploiting High-Fidelity Dense Features from Foundation Models for Medical Image Segmentation

2025-08-28 · Haoyue Li, Yifan Gao, Feng Yuan, Xiaosong Wang 외 arxiv

Foundation models pre-trained on large-scale natural image datasets offer a powerful paradigm for medical image segmentation. However, effectively transferring their learned representations for precise clinical applicati…

Medical Image SegmentationDimensionality Reduction

DINO-Mix: Enhancing Visual Place Recognition with Foundational Vision Model and Feature Mixing

2023-11-01 · Gaoshuang Huang, Yang Zhou, Xiaofei Hu, Chenglong Zhang 외

Utilizing visual place recognition (VPR) technology to ascertain the geographical location of publicly available images is a pressing issue for real-world VPR applications. Although most current VPR methods achieve favor…

Visual Place Recognition