Cover Image

SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Wenyue, Li, Peng, Zheng, Wangguandong, Zhao, Chengfeng, Li, Mengfei, Zhu, Yaolong, Dou, Zhiyang, Wang, Ronggang, Liu, Yuan
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

PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing
by: Li, Peng, et al.
Published: (2024)

SyncFix: Fixing 3D Reconstructions via Multi-View Synchronization
by: Li, Deming, et al.
Published: (2026)

CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos
by: Zhao, Chengfeng, et al.
Published: (2026)

HuPrior3R: Incorporating Human Priors for Better 3D Dynamic Reconstruction from Monocular Videos
by: Xiong, Weitao, et al.
Published: (2025)

Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models
by: Chen, Wenyue, et al.
Published: (2026)

WonderHuman: Hallucinating Unseen Parts in Dynamic 3D Human Reconstruction
by: Wang, Zilong, et al.
Published: (2025)

MVD-HuGaS: Human Gaussians from a Single Image via 3D Human Multi-view Diffusion Prior
by: Xiong, Kaiqiang, et al.
Published: (2025)

Part123: Part-aware 3D Reconstruction from a Single-view Image
by: Liu, Anran, et al.
Published: (2024)

UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass
by: Li, Mengfei, et al.
Published: (2026)

Sketch3D: Style-Consistent Guidance for Sketch-to-3D Generation
by: Zheng, Wangguandong, et al.
Published: (2024)

SyncMV4D: Synchronized Multi-view Joint Diffusion of Appearance and Motion for Hand-Object Interaction Synthesis
by: Dang, Lingwei, et al.
Published: (2025)

HumanOrbit: 3D Human Reconstruction as 360° Orbit Generation
by: Suzuki, Keito, et al.
Published: (2026)

Human as Points: Explicit Point-based 3D Human Reconstruction from Single-view RGB Images
by: Tang, Yingzhi, et al.
Published: (2023)

Dynamic Realms: 4D Content Analysis, Recovery and Generation with Geometric, Topological and Physical Priors
by: Dou, Zhiyang
Published: (2024)

HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation
by: Pan, Panwang, et al.
Published: (2025)

EgoReAct: Egocentric Video-Driven 3D Human Reaction Generation
by: Zhang, Libo, et al.
Published: (2025)

SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesis
by: He, Wenkun, et al.
Published: (2024)

SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis
by: Peng, Ziqiao, et al.
Published: (2023)

LHM++: An Efficient Large Human Reconstruction Model for Pose-free Images to 3D
by: Qiu, Lingteng, et al.
Published: (2025)

SyncVIS: Synchronized Video Instance Segmentation
by: Zheng, Rongkun, et al.
Published: (2024)

HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction
by: Rojas, Sara, et al.
Published: (2025)

Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-view Videos
by: Hu, Yingdong, et al.
Published: (2025)

SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
by: Liu, Yuan, et al.
Published: (2023)

3D Human Pose Estimation Based on 2D-3D Consistency with Synchronized Adversarial Training
by: Deng, Yicheng, et al.
Published: (2021)

GRACE: Estimating Geometry-level 3D Human-Scene Contact from 2D Images
by: Wang, Chengfeng, et al.
Published: (2025)

Disambiguating Monocular Reconstruction of 3D Clothed Human with Spatial-Temporal Transformer
by: Deng, Yong, et al.
Published: (2024)

Efficient4D: Fast Dynamic 3D Object Generation from a Single-view Video
by: Pan, Zijie, et al.
Published: (2024)

MuNet: A Mutualistic Network for Joint 3D Human Mesh Recovery and 3D Clothed Human Reconstruction from Single Images
by: Gao, Yunqi, et al.
Published: (2026)

SR3D: Unleashing Single-view 3D Reconstruction for Transparent and Specular Object Grasping
by: Zhang, Mingxu, et al.
Published: (2025)

EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views
by: Yang, Yuhang, et al.
Published: (2024)

Mono3R: Exploiting Monocular Cues for Geometric 3D Reconstruction
by: Li, Wenyu, et al.
Published: (2025)

UniRecGen: Unifying Multi-View 3D Reconstruction and Generation
by: Huang, Zhisheng, et al.
Published: (2026)

AdaHuman: Animatable Detailed 3D Human Generation with Compositional Multiview Diffusion
by: Huang, Yangyi, et al.
Published: (2025)

SHARE: Single-view Human Adversarial REconstruction
by: Revankar, Shreelekha, et al.
Published: (2023)

MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow
by: Huang, Hanzhuo, et al.
Published: (2025)

Wonder3D++: Cross-domain Diffusion for High-fidelity 3D Generation from a Single Image
by: Yang, Yuxiao, et al.
Published: (2025)

Muskie: Multi-view Masked Image Modeling for 3D Vision Pre-training
by: Li, Wenyu, et al.
Published: (2025)

SemanticHuman-HD: High-Resolution Semantic Disentangled 3D Human Generation
by: Zheng, Peng, et al.
Published: (2024)

H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction
by: Jia, Heng, et al.
Published: (2025)

CrowdGaussian: Reconstructing High-Fidelity 3D Gaussians for Human Crowd from a Single Image
by: Song, Yizheng, et al.
Published: (2026)