Copertina

Extreme Two-View Geometry From Object Poses with Diffusion Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Sun, Yujing, Sun, Caiyi, Liu, Yuan, Ma, Yuexin, Yiu, Siu Ming
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Generalizable Single-view Object Pose Estimation by Two-side Generating and Matching
di: Sun, Yujing, et al.
Pubblicazione: (2024)

HUMOF: Human Motion Forecasting in Interactive Social Scenes
di: Sun, Caiyi, et al.
Pubblicazione: (2025)

UniBioTransfer: A Unified Framework for Multiple Biometrics Transfer
di: Sun, Caiyi, et al.
Pubblicazione: (2026)

UniDemoiré: Towards Universal Image Demoiréing with Data Generation and Synthesis
di: Yang, Zemin, et al.
Pubblicazione: (2025)

Towards Practical Human Motion Prediction with LiDAR Point Clouds
di: Han, Xiao, et al.
Pubblicazione: (2024)

PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning
di: Chen, Jianqi, et al.
Pubblicazione: (2025)

DeFakeQ: Enabling Real-Time Deepfake Detection on Edge Devices via Adaptive Bidirectional Quantization
di: Li, Xiangyu, et al.
Pubblicazione: (2026)

Sparkle: A Robust and Versatile Representation for Point Cloud based Human Motion Capture
di: Ren, Yiming, et al.
Pubblicazione: (2026)

Object Gaussian for Monocular 6D Pose Estimation from Sparse Views
di: Luo, Luqing, et al.
Pubblicazione: (2024)

ReMoGen: Real-time Human Interaction-to-Reaction Generation via Modular Learning from Diverse Data
di: Ye, Yaoqin, et al.
Pubblicazione: (2026)

TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable Questions
di: He, Xingwei, et al.
Pubblicazione: (2024)

LiveHPS++: Robust and Coherent Motion Capture in Dynamic Free Environment
di: Ren, Yiming, et al.
Pubblicazione: (2024)

RayPose: Ray Bundling Diffusion for Template Views in Unseen 6D Object Pose Estimation
di: Huang, Junwen, et al.
Pubblicazione: (2025)

EgoXtreme: A Dataset for Robust Object Pose Estimation in Egocentric Views under Extreme Conditions
di: Yoon, Taegyoon, et al.
Pubblicazione: (2026)

PRAGO: Differentiable Multi-View Pose Optimization From Objectness Detections
di: Taiana, Matteo, et al.
Pubblicazione: (2024)

TransPose: 6D Object Pose Estimation with Geometry-Aware Transformer
di: Lin, Xiao, et al.
Pubblicazione: (2023)

Emergent Extreme-View Geometry in 3D Foundation Models
di: Zhang, Yiwen, et al.
Pubblicazione: (2025)

PoseCrafter: Extreme Pose Estimation with Hybrid Video Synthesis
di: Mao, Qing, et al.
Pubblicazione: (2025)

UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References
di: Li, Ming-Feng, et al.
Pubblicazione: (2025)

HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes
di: Yao, Yichen, et al.
Pubblicazione: (2024)

Gait Recognition in Large-scale Free Environment via Single LiDAR
di: Han, Xiao, et al.
Pubblicazione: (2022)

Expanding-and-Shrinking Binary Neural Networks
di: Shi, Xulong, et al.
Pubblicazione: (2025)

FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators
di: Wang, Haiping, et al.
Pubblicazione: (2023)

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance
di: Xia, Qi, et al.
Pubblicazione: (2026)

GeoMoE: Divide-and-Conquer Motion Field Modeling with Mixture-of-Experts for Two-View Geometry
di: Le, Jiajun, et al.
Pubblicazione: (2025)

EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild
di: Liu, Yumeng, et al.
Pubblicazione: (2024)

Generic Objects as Pose Probes for Few-shot View Synthesis
di: Gao, Zhirui, et al.
Pubblicazione: (2024)

Few-View Object Reconstruction with Unknown Categories and Camera Poses
di: Jiang, Hanwen, et al.
Pubblicazione: (2022)

MVTOP: Multi-View Transformer-based Object Pose-Estimation
di: Ranftl, Lukas, et al.
Pubblicazione: (2025)

Light Field Diffusion for Single-View Novel View Synthesis
di: Xiong, Yifeng, et al.
Pubblicazione: (2023)

MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Model
di: Liu, Jian, et al.
Pubblicazione: (2025)

OneViewAll: Semantic Prior Guided One-View 6D Pose Estimation for Novel Objects
di: Luo, Yang, et al.
Pubblicazione: (2026)

PLOOD: Partial Label Learning with Out-of-distribution Objects
di: Huang, Jintao, et al.
Pubblicazione: (2024)

Learning to Adapt SAM for Segmenting Cross-domain Point Clouds
di: Peng, Xidong, et al.
Pubblicazione: (2023)

Geometry-Conditioned Diffusion for Occlusion-Robust In-Bed Pose Estimation
di: Khameneh, Navid Aslankhani, et al.
Pubblicazione: (2026)

Extreme Views: 3DGS Filter for Novel View Synthesis from Out-of-Distribution Camera Poses
di: Bowness, Damian, et al.
Pubblicazione: (2025)

DiffSurf: A Transformer-based Diffusion Model for Generating and Reconstructing 3D Surfaces in Pose
di: Yoshiyasu, Yusuke, et al.
Pubblicazione: (2024)

Object Pose Estimation via the Aggregation of Diffusion Features
di: Wang, Tianfu, et al.
Pubblicazione: (2024)

Self-transcendence: Is External Feature Guidance Indispensable for Accelerating Diffusion Transformer Training?
di: Sun, Lingchen, et al.
Pubblicazione: (2026)

Jointly Conditioned Diffusion Model for Multi-View Pose-Guided Person Image Synthesis
di: Xie, Chengyu, et al.
Pubblicazione: (2025)