Cover Image

MegaFlow: Zero-Shot Large Displacement Optical Flow

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Dingxi, Wang, Fangjinhua, Pollefeys, Marc, Xu, Haofei
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DepthSplat: Connecting Gaussian Splatting and Depth
by: Xu, Haofei, et al.
Published: (2024)

Lightweight and Accurate Multi-View Stereo with Confidence-Aware Diffusion Model
by: Wang, Fangjinhua, et al.
Published: (2025)

R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization
by: Jiang, Xudong, et al.
Published: (2025)

ImLoc: Revisiting Visual Localization with Image-based Representation
by: Jiang, Xudong, et al.
Published: (2026)

GLACE: Global Local Accelerated Coordinate Encoding
by: Wang, Fangjinhua, et al.
Published: (2024)

From Indoor to Open World: Revealing the Spatial Reasoning Gap in MLLMs
by: Wu, Mingrui, et al.
Published: (2025)

ReSplat: Learning Recurrent Gaussian Splatting
by: Xu, Haofei, et al.
Published: (2025)

Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces
by: Zhang, Chenyangguang, et al.
Published: (2025)

Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints
by: Zhang, Chenyangguang, et al.
Published: (2026)

UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections
by: Wang, Fangjinhua, et al.
Published: (2023)

YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting
by: Ye, Botao, et al.
Published: (2025)

FlowComposer: Composable Flows for Compositional Zero-Shot Learning
by: He, Zhenqi, et al.
Published: (2026)

UniFlow: Zero-Shot LiDAR Scene Flow for Autonomous Vehicles
by: Li, Siyi, et al.
Published: (2025)

Learning-based Multi-View Stereo: A Survey
by: Wang, Fangjinhua, et al.
Published: (2024)

Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detection
by: Qu, Zhen, et al.
Published: (2025)

Zero-Shot Monocular Scene Flow Estimation in the Wild
by: Liang, Yiqing, et al.
Published: (2025)

VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation
by: Chen, Hanzhi, et al.
Published: (2025)

ZS-VCOS: Zero-Shot Video Camouflaged Object Segmentation By Optical Flow and Open Vocabulary Object Detection
by: Guo, Wenqi, et al.
Published: (2025)

ProjFlow: Projection Sampling with Flow Matching for Zero-Shot Exact Spatial Motion Control
by: Watanabe, Akihisa, et al.
Published: (2026)

FlowR: Flowing from Sparse to Dense 3D Reconstructions
by: Fischer, Tobias, et al.
Published: (2025)

MuRF: Multi-Baseline Radiance Fields
by: Xu, Haofei, et al.
Published: (2023)

No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images
by: Ye, Botao, et al.
Published: (2024)

Dense Monocular Motion Segmentation Using Optical Flow and Pseudo Depth Map: A Zero-Shot Approach
by: Huang, Yuxiang, et al.
Published: (2024)

Learning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR Fusion
by: Liu, Haisong, et al.
Published: (2023)

CL-Splats: Continual Learning of Gaussian Splatting with Local Optimization
by: Ackermann, Jan, et al.
Published: (2025)

MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era
by: Zhang, Lei, et al.
Published: (2026)

SplatFlow: Learning Multi-frame Optical Flow via Splatting
by: Wang, Bo, et al.
Published: (2023)

Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends
by: Liu, Jiuming, et al.
Published: (2026)

MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images
by: Chen, Yuedong, et al.
Published: (2024)

Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images
by: Liang, Yingping, et al.
Published: (2025)

SG-Tailor: Inter-Object Commonsense Relationship Reasoning for Scene Graph Manipulation
by: Shang, Haoliang, et al.
Published: (2025)

GenOpticalFlow: A Generative Approach to Unsupervised Optical Flow Learning
by: Luo, Yixuan, et al.
Published: (2026)

NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos
by: Li, Hongyu, et al.
Published: (2025)

MemFlow: Optical Flow Estimation and Prediction with Memory
by: Dong, Qiaole, et al.
Published: (2024)

ProbDiffFlow: An Efficient Learning-Free Framework for Probabilistic Single-Image Optical Flow Estimation
by: Zhou, Mo, et al.
Published: (2025)

DiFlow-TTS: Compact and Low-Latency Zero-Shot Text-to-Speech with Factorized Discrete Flow Matching
by: Nguyen, Ngoc-Son, et al.
Published: (2025)

Hybrid Cost Volume for Memory-Efficient Optical Flow
by: Zhao, Yang, et al.
Published: (2024)

SciFlow: Empowering Lightweight Optical Flow Models with Self-Cleaning Iterations
by: Lin, Jamie Menjay, et al.
Published: (2024)

Exploring Cross-Modal Flows for Few-Shot Learning
by: Jiang, Ziqi, et al.
Published: (2025)

Zero-Shot Generative De-identification: Inversion-Free Flow for Privacy-Preserving Skin Image Analysis
by: Moutselos, Konstantinos, et al.
Published: (2026)