Cover Image

Injecting Frame-Event Complementary Fusion into Diffusion for Optical Flow in Challenging Scenes

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Haonan, Zhou, Hanyu, Liu, Haoyue, Yan, Luxin
Format:	Preprint
Published:	2025
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

Bridge Frame and Event: Common Spatiotemporal Fusion for High-Dynamic Scene Optical Flow
by: Zhou, Hanyu, et al.
Published: (2025)

STD-GS: Exploring Frame-Event Interaction for SpatioTemporal-Disentangled Gaussian Splatting to Reconstruct High-Dynamic Scene
by: Zhou, Hanyu, et al.
Published: (2025)

4D-VGGT: A General Foundation Model with SpatioTemporal Awareness for Dynamic Scene Geometry Estimation
by: Wang, Haonan, et al.
Published: (2025)

NEC-Diff: Noise-Robust Event-RAW Complementary Diffusion for Seeing Motion in Extreme Darkness
by: Liu, Haoyue, et al.
Published: (2026)

Bring Event into RGB and LiDAR: Hierarchical Visual-Motion Fusion for Scene Flow
by: Zhou, Hanyu, et al.
Published: (2024)

Cog2Gen3D: Sculpturing 3D Semantic-Geometric Cognition for 3D Generation
by: Wang, Haonan, et al.
Published: (2026)

TimeTracker: Event-based Continuous Point Tracking for Video Frame Interpolation with Non-linear Motion
by: Liu, Haoyue, et al.
Published: (2025)

Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical Flow
by: Zhou, Hanyu, et al.
Published: (2024)

LLaFEA: Frame-Event Complementary Fusion for Fine-Grained Spatiotemporal Understanding in LMMs
by: Zhou, Hanyu, et al.
Published: (2025)

Seeing Motion at Nighttime with an Event Camera
by: Liu, Haoyue, et al.
Published: (2024)

ST-Gen4D: Embedding 4D Spatiotemporal Cognition into World Model for 4D Generation
by: Wang, Haonan, et al.
Published: (2026)

Adapting Depth Anything to Adverse Imaging Conditions with Events
by: Peng, Shihan, et al.
Published: (2026)

CoSEC: A Coaxial Stereo Event Camera Dataset for Autonomous Driving
by: Peng, Shihan, et al.
Published: (2024)

Adverse Weather Optical Flow: Cumulative Homogeneous-Heterogeneous Adaptation
by: Zhou, Hanyu, et al.
Published: (2024)

High-Quality and Efficient Turbulence Mitigation with Events
by: Zhang, Xiaoran, et al.
Published: (2026)

JSTR: Joint Spatio-Temporal Reasoning for Event-based Moving Object Detection
by: Zhou, Hanyu, et al.
Published: (2024)

BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation using RGB Frames and Events
by: Li, Yijin, et al.
Published: (2024)

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

Dense Continuous-Time Optical Flow from Events and Frames
by: Gehrig, Mathias, et al.
Published: (2022)

Tracking Any Point with Frame-Event Fusion Network at High Frame Rate
by: Liu, Jiaxiong, et al.
Published: (2024)

6-DoF Object Tracking with Event-based Optical Flow and Frames
by: Li, Zhichao, et al.
Published: (2025)

RecurGS: Interactive Scene Modeling via Discrete-State Recurrent Gaussian Fusion
by: Hu, Wenhao, et al.
Published: (2025)

ST-$π$: Structured SpatioTemporal VLA for Robotic Manipulation
by: Ma, Chuanhao, et al.
Published: (2026)

CurriFlow: Curriculum-Guided Depth Fusion with Optical Flow-Based Temporal Alignment for 3D Semantic Scene Completion
by: Lin, Jinzhou, et al.
Published: (2025)

IGFuse: Interactive 3D Gaussian Scene Reconstruction via Multi-Scans Fusion
by: Hu, Wenhao, et al.
Published: (2025)

TAPFormer: Robust Arbitrary Point Tracking via Transient Asynchronous Fusion of Frames and Events
by: Liu, Jiaxiong, et al.
Published: (2026)

Hierarchical Flow Diffusion for Efficient Frame Interpolation
by: Hai, Yang, et al.
Published: (2025)

DriveEditor: A Unified 3D Information-Guided Framework for Controllable Object Editing in Driving Scenes
by: Liang, Yiyuan, et al.
Published: (2024)

Bilateral Event Mining and Complementary for Event Stream Super-Resolution
by: Huang, Zhilin, et al.
Published: (2024)

Scene Summarization: Clustering Scene Videos into Spatially Diverse Frames
by: Chen, Chao, et al.
Published: (2023)

StyleInject: Parameter Efficient Tuning of Text-to-Image Diffusion Models
by: Zhou, Mohan, et al.
Published: (2024)

LLaVA-4D: Embedding SpatioTemporal Prompt into LMMs for 4D Scene Understanding
by: Zhou, Hanyu, et al.
Published: (2025)

Learning Efficient Meshflow and Optical Flow from Event Cameras
by: Luo, Xinglong, et al.
Published: (2025)

E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization
by: Li, Wenpu, et al.
Published: (2025)

Efficient Event-Based Semantic Segmentation via Exploiting Frame-Event Fusion: A Hybrid Neural Network Approach
by: Li, Hebei, et al.
Published: (2025)

Self-Supervised Multi-Frame Neural Scene Flow
by: Liu, Dongrui, et al.
Published: (2024)

EventDiff: A Unified and Efficient Diffusion Model Framework for Event-based Video Frame Interpolation
by: Zheng, Hanle, et al.
Published: (2025)

EGVD: Event-Guided Video Diffusion Model for Physically Realistic Large-Motion Frame Interpolation
by: Zhang, Ziran, et al.
Published: (2025)

Complementary Information Guided Occupancy Prediction via Multi-Level Representation Fusion
by: Xu, Rongtao, et al.
Published: (2025)

DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Diffusion Model
by: Liu, Jiuming, et al.
Published: (2023)