Cover Image

Flow3r: Factored Flow Prediction for Scalable Visual Geometry Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cong, Zhongxiao, Zhao, Qitao, Jeon, Minsik, Tulsiani, Shubham
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

Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis
by: Zhao, Qitao, et al.
Published: (2024)

DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion
by: Zhao, Qitao, et al.
Published: (2025)

RayRoPE: Projective Ray Positional Encoding for Multi-view Attention
by: Wu, Yu, et al.
Published: (2026)

E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training
by: Zhao, Qitao, et al.
Published: (2025)

SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation
by: Bokhovkin, Alexey, et al.
Published: (2024)

Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation
by: Bharadhwaj, Homanga, et al.
Published: (2024)

MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation
by: Hu, Hanzhe, et al.
Published: (2024)

FlowCast: Trajectory Forecasting for Scalable Zero-Cost Speculative Flow Matching
by: Bajpai, Divya Jyoti, et al.
Published: (2026)

UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulation
by: Mittal, Himangi, et al.
Published: (2025)

AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis
by: Vuong, Khiem, et al.
Published: (2025)

LightSwitch: Multi-view Relighting with Material-guided Diffusion
by: Litman, Yehonathan, et al.
Published: (2025)

G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis
by: Ye, Yufei, et al.
Published: (2024)

Diverse Score Distillation
by: Xu, Yanbo, et al.
Published: (2024)

LC-Flow: Learning Local Continuous Optical Flow and Confidence from events
by: Jeon, Gunwoo, et al.
Published: (2026)

DA-RAW: Domain Adaptive Object Detection for Real-World Adverse Weather Conditions
by: Jeon, Minsik, et al.
Published: (2023)

OW-Rep: Open World Object Detection with Instance Representation Learning
by: Lee, Sunoh, et al.
Published: (2024)

Predicting 4D Hand Trajectory from Monocular Videos
by: Ye, Yufei, et al.
Published: (2025)

DressRecon: Freeform 4D Human Reconstruction from Monocular Video
by: Tan, Jeff, et al.
Published: (2024)

UpFusion: Novel View Diffusion from Unposed Sparse View Observations
by: Kani, Bharath Raj Nagoor, et al.
Published: (2023)

Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representations
by: Zheng, Xunzhi, et al.
Published: (2025)

Geometry-Aware Image Flow Matching
by: Lee, Junho, et al.
Published: (2026)

P-Flow: Prompting Visual Effects Generation
by: Zhao, Rui, et al.
Published: (2026)

Novel View Synthesis as Video Completion
by: Wu, Qi, et al.
Published: (2026)

Dex4D: Task-Agnostic Point Track Policy for Sim-to-Real Dexterous Manipulation
by: Kuang, Yuxuan, et al.
Published: (2026)

Let Occ Flow: Self-Supervised 3D Occupancy Flow Prediction
by: Liu, Yili, et al.
Published: (2024)

DGFamba: Learning Flow Factorized State Space for Visual Domain Generalization
by: Bi, Qi, et al.
Published: (2025)

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

Turbo3D: Ultra-fast Text-to-3D Generation
by: Hu, Hanzhe, et al.
Published: (2024)

ZeroFlow: Scalable Scene Flow via Distillation
by: Vedder, Kyle, et al.
Published: (2023)

GaussianFlow SLAM: Monocular Gaussian Splatting SLAM Guided by GaussianFlow
by: Seo, Dong-Uk, et al.
Published: (2026)

MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems
by: Chen, Shuhang, et al.
Published: (2025)

JOLT3D: Joint Learning of Talking Heads and 3DMM Parameters with Application to Lip-Sync
by: Park, Sungjoon, et al.
Published: (2025)

Unlocking the Power of Critical Factors for 3D Visual Geometry Estimation
by: Xu, Guangkai, et al.
Published: (2026)

Toward Scalable, Flexible Scene Flow for Point Clouds
by: Vedder, Kyle
Published: (2025)

TrajVG: 3D Trajectory-Coupled Visual Geometry Learning
by: Miao, Xingyu, et al.
Published: (2026)

UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation
by: Yue, Zhengrong, et al.
Published: (2025)

Pyramidal Patchification Flow for Visual Generation
by: Li, Hui, et al.
Published: (2025)

GenFlowRL: Shaping Rewards with Generative Object-Centric Flow in Visual Reinforcement Learning
by: Yu, Kelin, et al.
Published: (2025)

CacheFlow: Fast Human Motion Prediction by Cached Normalizing Flow
by: Maeda, Takahiro, et al.
Published: (2025)

$π^3$: Permutation-Equivariant Visual Geometry Learning
by: Wang, Yifan, et al.
Published: (2025)