Image de couverture de livre

Blur2Sharp: Human Novel Pose and View Synthesis with Generative Prior Refinement

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lai, Chia-Hern, Lo, I-Hsuan, Yeh, Yen-Ku, Truong, Thanh-Nguyen, Huang, Ching-Chun
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

PoseGaussian: Pose-Driven Novel View Synthesis for Robust 3D Human Reconstruction
par: Shen, Ju, et autres
Publié: (2026)

Warm Diffusion: Recipe for Blur-Noise Mixture Diffusion Models
par: Hsueh, Hao-Chien, et autres
Publié: (2025)

From Sharp to Blur: Unsupervised Domain Adaptation for 2D Human Pose Estimation Under Extreme Motion Blur Using Event Cameras
par: Kim, Youngho, et autres
Publié: (2025)

FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors
par: Lin, Chin-Yang, et autres
Publié: (2024)

Derivation of Casimir Effect without Zeta-Regularization
par: Yen, Ching-Hsuan
Publié: (2024)

NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editing
par: Chen, Ting-Hsuan, et autres
Publié: (2024)

Human Video Generation from a Single Image with 3D Pose and View Control
par: Wang, Tiantian, et autres
Publié: (2026)

BlurDM: A Blur Diffusion Model for Image Deblurring
par: He, Jin-Ting, et autres
Publié: (2025)

OrbitNVS: Harnessing Video Diffusion Priors for Novel View Synthesis
par: Liang, Jinglin, et autres
Publié: (2026)

MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement
par: He, Xu, et autres
Publié: (2024)

Generative 4D Scene Gaussian Splatting with Object View-Synthesis Priors
par: Chu, Wen-Hsuan, et autres
Publié: (2025)

Agnostic Sharpness-Aware Minimization
par: Nguyen, Van-Anh, et autres
Publié: (2024)

XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach
par: Nguyen, Truong Thanh Hung, et autres
Publié: (2024)

On the structure and generic non-Cartesianity of polynomials in product spaces
par: Shen, Chun-Yen, et autres
Publié: (2026)

Homogenisation for the Robin eigenvalue problem on manifolds and flexibility of optimal Schrödinger potentials
par: Lo, Chia-Chun
Publié: (2024)

DeblurNVS: Geometric Latent Diffusion for Novel View Synthesis from Sparse Motion-Blurred Images
par: Shi, Changyue, et autres
Publié: (2026)

Image Compression Using Novel View Synthesis Priors
par: Peng, Luyuan, et autres
Publié: (2024)

Efficient learning of $t$-doped stabilizer states with single-copy measurements
par: Chia, Nai-Hui, et autres
Publié: (2023)

Migration, Gender and Social Justice Perspectives on Human Insecurity
par: Thanh-Dam Truong

OneViewAll: Semantic Prior Guided One-View 6D Pose Estimation for Novel Objects
par: Luo, Yang, et autres
Publié: (2026)

Sharpe-Driven Stock Selection and Liquidiy-Constrained Portfolio Optimization: Evidence from the Chinese Equity Market
par: Nguyen, Thanh
Publié: (2025)

Neural Human Pose Prior
par: Heker, Michal, et autres
Publié: (2025)

HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarse-to-fine Pose-Reversible Guidance
par: Fang, Guian, et autres
Publié: (2024)

Structure-Preserving Graph Contrastive Learning for Mathematical Information Retrieval
par: Ku, Chun-Hsi, et autres
Publié: (2026)

College Adjustment and Information Experience of First‐Generation College Students' Coursework and Extracurricular Learning
par: Tien‐I Tsai, et autres
Publié: (2024)

LiftRefine: Progressively Refined View Synthesis from 3D Lifting with Volume-Triplane Representations
par: Do, Tung, et autres
Publié: (2024)

Look Gauss, No Pose: Novel View Synthesis using Gaussian Splatting without Accurate Pose Initialization
par: Schmidt, Christian, et autres
Publié: (2024)

Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairs
par: Hong, Sunghwan, et autres
Publié: (2023)

Sharp Fourier decay estimates for measures supported on the well-approximable numbers
par: Fraser, Robert, et autres
Publié: (2024)

Blur2Blur: Blur Conversion for Unsupervised Image Deblurring on Unknown Domains
par: Pham, Bang-Dang, et autres
Publié: (2024)

Airway Tree Modeling Using Dual-channel 3D UNet 3+ with Vesselness Prior
par: Chien, Hsiang-Chin, et autres
Publié: (2022)

HumanGif: Single-View Human Diffusion with Generative Prior
par: Hu, Shoukang, et autres
Publié: (2025)

Benchmarking Efficient & Effective Camera Pose Estimation Strategies for Novel View Synthesis
par: Meza, Jhacson, et autres
Publié: (2026)

Rethinking Pose Refinement in 3D Gaussian Splatting under Pose Prior and Geometric Uncertainty
par: Kong, Mangyu, et autres
Publié: (2026)

Diffusion-based Pose Refinement and Muti-hypothesis Generation for 3D Human Pose Estimaiton
par: Kang, Hongbo, et autres
Publié: (2024)

Variational Quantum Rainbow Deep Q-Network for Optimizing Resource Allocation Problem
par: Nguyen, Truong Thanh Hung, et autres
Publié: (2025)

Extreme Views: 3DGS Filter for Novel View Synthesis from Out-of-Distribution Camera Poses
par: Bowness, Damian, et autres
Publié: (2025)

Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)
par: Hsiao, Tsu-Ching, et autres
Publié: (2023)

Generic Objects as Pose Probes for Few-shot View Synthesis
par: Gao, Zhirui, et autres
Publié: (2024)

A Sharpness Based Loss Function for Removing Out-of-Focus Blur
par: Aurangabadkar, Uditangshu, et autres
Publié: (2024)