Imagen de Portada

RAFT-MSF++: Temporal Geometry-Motion Feature Fusion for Self-Supervised Monocular Scene Flow

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sun, Xunpei, Hou, Zuoxun, Chang, Yi, Chen, Gang, Zheng, Wei-Shi
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

U$^{2}$Flow: Uncertainty-Aware Unsupervised Optical Flow Estimation
por: Sun, Xunpei, et al.
Publicado: (2026)

Manydepth2: Motion-Aware Self-Supervised Monocular Depth Estimation in Dynamic Scenes
por: Zhou, Kaichen, et al.
Publicado: (2023)

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

Self-Supervised Monocular 4D Scene Reconstruction for Egocentric Videos
por: Yuan, Chengbo, et al.
Publicado: (2024)

MSF-Net: Multi-Stage Feature Extraction and Fusion for Robust Photometric Stereo
por: Qin, Shiyu, et al.
Publicado: (2025)

MSF-Mamba: Motion-aware State Fusion Mamba for Efficient Micro-Gesture Recognition
por: Li, Deng, et al.
Publicado: (2025)

Self-Supervised Scene Flow Estimation with Point-Voxel Fusion and Surface Representation
por: Xiang, Xuezhi, et al.
Publicado: (2024)

MotionHint: Self-Supervised Monocular Visual Odometry with Motion Constraints
por: Wang, Cong, et al.
Publicado: (2021)

SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow
por: Wang, Yihan, et al.
Publicado: (2024)

FlowDepth: Decoupling Optical Flow for Self-Supervised Monocular Depth Estimation
por: Sun, Yiyang, et al.
Publicado: (2024)

Geometry-guided Feature Learning and Fusion for Indoor Scene Reconstruction
por: Yin, Ruihong, et al.
Publicado: (2024)

Self-Supervised Geometry-Guided Initialization for Robust Monocular Visual Odometry
por: Kanai, Takayuki, et al.
Publicado: (2024)

SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving
por: Zhang, Qingwen, et al.
Publicado: (2024)

ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusion
por: Woo, Sungmin, et al.
Publicado: (2024)

MCDS-VSS: Moving Camera Dynamic Scene Video Semantic Segmentation by Filtering with Self-Supervised Geometry and Motion
por: Villar-Corrales, Angel, et al.
Publicado: (2024)

SplatFlow: Self-Supervised Dynamic Gaussian Splatting in Neural Motion Flow Field for Autonomous Driving
por: Sun, Su, et al.
Publicado: (2024)

MS-RAFT-3D: A Multi-Scale Architecture for Recurrent Image-Based Scene Flow
por: Schmid, Jakob, et al.
Publicado: (2025)

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

ReFlow: Self-correction Motion Learning for Dynamic Scene Reconstruction
por: Liang, Yanzhe, et al.
Publicado: (2026)

Learning Multi-frame and Monocular Prior for Estimating Geometry in Dynamic Scenes
por: Park, Seong Hyeon, et al.
Publicado: (2025)

Unsupervised Monocular Road Segmentation for Autonomous Driving via Scene Geometry
por: Rostami, Sara Hatami, et al.
Publicado: (2025)

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

Exploring Surround-View Fisheye Camera 3D Object Detection
por: Li, Changcai, et al.
Publicado: (2025)

Modality-Guided Dynamic Graph Fusion and Temporal Diffusion for Self-Supervised RGB-T Tracking
por: Li, Shenglan, et al.
Publicado: (2025)

Generalized Semi-Supervised Learning via Self-Supervised Feature Adaptation
por: Liang, Jiachen, et al.
Publicado: (2024)

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

HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction
por: Zhang, Wei, et al.
Publicado: (2024)

Geometry-Constrained Monocular Scale Estimation Using Semantic Segmentation for Dynamic Scenes
por: Zhang, Hui, et al.
Publicado: (2025)

Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimation
por: Nguyen, Hoang Chuong, et al.
Publicado: (2024)

GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation Models
por: Ge, Yongtao, et al.
Publicado: (2024)

TeFlow: Enabling Multi-frame Supervision for Self-Supervised Feed-forward Scene Flow Estimation
por: Zhang, Qingwen, et al.
Publicado: (2026)

MonoSelfRecon: Purely Self-Supervised Explicit Generalizable 3D Reconstruction of Indoor Scenes from Monocular RGB Views
por: Li, Runfa, et al.
Publicado: (2024)

Test-Time Adaptation for Height Completion via Self-Supervised ViT Features and Monocular Foundation Models
por: Rafaeli, Osher, et al.
Publicado: (2026)

VoteFlow: Enforcing Local Rigidity in Self-Supervised Scene Flow
por: Lin, Yancong, et al.
Publicado: (2025)

Semi-Supervised Flow Matching for Mosaiced and Panchromatic Fusion Imaging
por: Luo, Peiming, et al.
Publicado: (2026)

Gamma-from-Mono: Road-Relative, Metric, Self-Supervised Monocular Geometry for Vehicular Applications
por: Elazab, Gasser, et al.
Publicado: (2025)

Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations
por: Wang, Kewei, et al.
Publicado: (2024)

Towards Spatio-Temporal World Scene Graph Generation from Monocular Videos
por: Peddi, Rohith, et al.
Publicado: (2026)

Natural Human Motion Recovery by Aligning High-Order Temporal Dynamics from Monocular Videos
por: Wei, Dingkun, et al.
Publicado: (2026)

Object-Scene-Camera Decomposition and Recomposition for Data-Efficient Monocular 3D Object Detection
por: Kuang, Zhaonian, et al.
Publicado: (2026)