Newest papers

Foundation Model Driven Optical Flow

Praroop Chanda, Suryansh Kumar · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26690 · cited by 0 works (OpenAlex) · open-access PDF

Chinese

我们研究了冻结的预测转换器(DPT)功能解码和粗糙到细微的改进阶段如何支持密集的光流,当与受监督的匹配网络相结合时。 基于TTSFlow,本论文研究了密集的预测转换器(DPT)功能解码和一个粗糙到细微的改进阶段。 我们的方法将来自冻结的DINOv2和深度任何V2模型的功能合并,并通过可训练的变压器基于的匹配管道估计光流量。 在FlyingChairs和FlyingThings3D上进行光流训练后,它在Sintel训练分区上实现了2.37终点错误(EPE),最终通行,与这里报道的FlowSeek(T)配置的2.52相比。

Machine translation (Meta M2M100); the English original follows.

Abstract

We investigate how frozen pretrained visual and depth representations support dense optical flow when coupled with a supervised matching network. Building on TTSFlow, this paper studies Dense Prediction Transformer (DPT) feature decoding and one coarse-to-fine refinement stage. Our method fuses features from frozen DINOv2 and Depth Anything V2 models and estimates optical flow through a trainable transformer-based matching pipeline. After optical-flow training on FlyingChairs and FlyingThings3D, it achieves 2.37 endpoint error (EPE) on the Sintel training split, Final pass, compared with 2.52 for the FlowSeek (T) configuration reported here. Our RoCo-Spring 2026 entry, RoCo-29.VSAI, obtains a robustness-balanced score of 1.1038, Spring EPE of 1.411, and RobustSpring proxy EPE of 4.739, with a lower balanced score than seven of the twelve listed reference baselines. These results characterize the complete pipeline, which reuses frozen foundation backbones and performs one refinement stage. Code is available at: \url{https://github.com/Visual-and-Spatial-AI-Lab/FFlow}

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Optical flow, Transformer, Matching (statistics), Artificial intelligence, Code (set theory)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange