Imagen de Portada

MS-RAFT-3D: A Multi-Scale Architecture for Recurrent Image-Based Scene Flow

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Schmid, Jakob, Jahedi, Azin, Senn, Noah Berenguel, Bruhn, Andrés
Formato:	Preprint
Publicado:	2025
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

Multi-Scale RAFT: Combining Hierarchical Concepts for Learning-based Optical FLow Estimation
por: Jahedi, Azin, et al.
Publicado: (2022)

High Resolution Multi-Scale RAFT (Robust Vision Challenge 2022)
por: Jahedi, Azin, et al.
Publicado: (2022)

CCMR: High Resolution Optical Flow Estimation via Coarse-to-Fine Context-Guided Motion Reasoning
por: Jahedi, Azin, et al.
Publicado: (2023)

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

RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo
por: Oei, Victor, et al.
Publicado: (2025)

RAFT-MSF++: Temporal Geometry-Motion Feature Fusion for Self-Supervised Monocular Scene Flow
por: Sun, Xunpei, et al.
Publicado: (2026)

GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
por: Schmid, Katharina, et al.
Publicado: (2026)

Scaled 360 layouts: Revisiting non-central panoramas
por: Berenguel-Baeta, Bruno, et al.
Publicado: (2024)

OmniSCV: An Omnidirectional Synthetic Image Generator for Computer Vision
por: Berenguel-Baeta, Bruno, et al.
Publicado: (2024)

GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation
por: von Lützow, Nicolas, et al.
Publicado: (2026)

RMS-FlowNet++: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds
por: Battrawy, Ramy, et al.
Publicado: (2024)

Atlanta Scaled layouts from non-central panoramas
por: Berenguel-Baeta, Bruno, et al.
Publicado: (2024)

MegaScenes: Scene-Level View Synthesis at Scale
por: Tung, Joseph, et al.
Publicado: (2024)

Online 3D Scene Reconstruction Using Neural Object Priors
por: Chabal, Thomas, et al.
Publicado: (2025)

MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation
por: Huang, Zehuan, et al.
Publicado: (2024)

Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flow
por: Meng, Quan, et al.
Publicado: (2026)

LiFlow: Flow Matching for 3D LiDAR Scene Completion
por: Matteazzi, Andrea, et al.
Publicado: (2026)

ArchSym: Detecting 3D-Grounded Architectural Symmetries in the Wild
por: Chen, Hanyu, et al.
Publicado: (2026)

MedDIFT: Multi-Scale Diffusion-Based Correspondence in 3D Medical Imaging
por: Zhang, Xingyu, et al.
Publicado: (2025)

Implicit-Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes
por: Ma, Qi, et al.
Publicado: (2024)

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

GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring
por: Lee, Dongwoo, et al.
Publicado: (2024)

Fast SceneScript: Fast and Accurate Language-Based 3D Scene Understanding via Multi-Token Prediction
por: Yin, Ruihong, et al.
Publicado: (2025)

A Luminance-Aware Multi-Scale Network for Polarization Image Fusion with a Multi-Scene Dataset
por: Huang, Zhuangfan, et al.
Publicado: (2025)

SynFlow: Scaling Up LiDAR Scene Flow Estimation with Synthetic Data
por: Zhang, Qingwen, et al.
Publicado: (2026)

MS23D: A 3D Object Detection Method Using Multi-Scale Semantic Feature Points to Construct 3D Feature Layer
por: Shao, Yongxin, et al.
Publicado: (2023)

GigaGS: Scaling up Planar-Based 3D Gaussians for Large Scene Surface Reconstruction
por: Chen, Junyi, et al.
Publicado: (2024)

3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling
por: Jiang, Chaokang, et al.
Publicado: (2024)

Scenes as Tokens: Multi-Scale Normal Distributions Transform Tokenizer for General 3D Vision-Language Understanding
por: Tang, Yutao, et al.
Publicado: (2025)

StyleCity: Large-Scale 3D Urban Scenes Stylization
por: Chen, Yingshu, et al.
Publicado: (2024)

Multi-Body Neural Scene Flow
por: Vidanapathirana, Kavisha, et al.
Publicado: (2023)

Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image Generation
por: Eldesokey, Abdelrahman, et al.
Publicado: (2024)

ReMATF: Recurrent Motion-Adaptive Multi-scale Turbulence Mitigation for Dynamic Scenes
por: Liu, Zhiming, et al.
Publicado: (2026)

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

Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion
por: Li, Zuoyue, et al.
Publicado: (2024)

X-RAFT: Cross-Modal Non-Rigid Registration of Blue and White Light Neurosurgical Hyperspectral Images
por: Budd, Charlie, et al.
Publicado: (2025)

Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale
por: Wei, Dongxu, et al.
Publicado: (2026)

FreeScale: Scaling 3D Scenes via Certainty-Aware Free-View Generation
por: Jiang, Chenhan, et al.
Publicado: (2026)

Multi-Resolution Alignment for Voxel Sparsity in Camera-Based 3D Semantic Scene Completion
por: Yang, Zhiwen, et al.
Publicado: (2026)

GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objects
por: Moon, Sungphill, et al.
Publicado: (2024)