Copertina

Free Geometry: Refining 3D Reconstruction from Longer Versions of Itself

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Dai, Yuhang, Yang, Xingyi
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Hash3D: Training-free Acceleration for 3D Generation
di: Yang, Xingyi, et al.
Pubblicazione: (2024)

Test3R: Learning to Reconstruct 3D at Test Time
di: Yuan, Yuheng, et al.
Pubblicazione: (2025)

Attention Itself Could Retrieve.RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval
di: Zou, Zichen, et al.
Pubblicazione: (2026)

WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion
di: Kong, Hanyang, et al.
Pubblicazione: (2025)

iBA: Backdoor Attack on 3D Point Cloud via Reconstructing Itself
di: Bian, Yuhao, et al.
Pubblicazione: (2024)

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

SSR: A Training-Free Approach for Streaming 3D Reconstruction
di: Deng, Hui, et al.
Pubblicazione: (2026)

GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement
di: Zhuang, Peiye, et al.
Pubblicazione: (2024)

Kinematics-based 3D Human-Object Interaction Reconstruction from Single View
di: Chen, Yuhang, et al.
Pubblicazione: (2024)

GeoHand: Unlocking Prior Geometry Knowledge for Monocular 3D Hand Reconstruction
di: Lin, Weiquan, et al.
Pubblicazione: (2026)

Gesplat: Robust Pose-Free 3D Reconstruction via Geometry-Guided Gaussian Splatting
di: Lu, Jiahui, et al.
Pubblicazione: (2025)

FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling
di: Qiu, Haonan, et al.
Pubblicazione: (2023)

Reg3D: Reconstructive Geometry Instruction Tuning for 3D Scene Understanding
di: Zheng, Hongpei, et al.
Pubblicazione: (2025)

Flash Sculptor: Modular 3D Worlds from Objects
di: Hu, Yujia, et al.
Pubblicazione: (2025)

MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly Detection
di: Cheng, Jiayi, et al.
Pubblicazione: (2025)

UAVFF3D: A Geometry-Aware Benchmark for Feed-Forward UAV 3D Reconstruction
di: Yang, Xiang, et al.
Pubblicazione: (2026)

IMFine: 3D Inpainting via Geometry-guided Multi-view Refinement
di: Shi, Zhihao, et al.
Pubblicazione: (2025)

Refined Geometry-guided Head Avatar Reconstruction from Monocular RGB Video
di: Park, Pilseo, et al.
Pubblicazione: (2025)

MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts
di: Gao, Jingnan, et al.
Pubblicazione: (2025)

CaptionQA: Is Your Caption as Useful as the Image Itself?
di: Yang, Shijia, et al.
Pubblicazione: (2025)

C4D: 4D Made from 3D through Dual Correspondences
di: Wang, Shizun, et al.
Pubblicazione: (2025)

$R^2$-Mesh: Reinforcement Learning Powered Mesh Reconstruction via Geometry and Appearance Refinement
di: Wang, Haoyang, et al.
Pubblicazione: (2024)

IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction
di: Li, Hao, et al.
Pubblicazione: (2025)

Focus on Neighbors and Know the Whole: Towards Consistent Dense Multiview Text-to-Image Generator for 3D Creation
di: Li, Bonan, et al.
Pubblicazione: (2024)

PointSplat: Efficient Geometry-Driven Pruning and Transformer Refinement for 3D Gaussian Splatting
di: Tran, Anh Thuan, et al.
Pubblicazione: (2026)

Guiding a Diffusion Model with a Bad Version of Itself
di: Karras, Tero, et al.
Pubblicazione: (2024)

Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted Images
di: Song, Qi, et al.
Pubblicazione: (2024)

LoL: Longer than Longer, Scaling Video Generation to Hour
di: Cui, Justin, et al.
Pubblicazione: (2026)

GeoRect4D: Geometry-Compatible Generative Rectification for Dynamic Sparse-View 3D Reconstruction
di: Wu, Zhenlong, et al.
Pubblicazione: (2026)

Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer
di: Nam, Hyeongjin, et al.
Pubblicazione: (2024)

A Refined 3D Gaussian Representation for High-Quality Dynamic Scene Reconstruction
di: Zhang, Bin, et al.
Pubblicazione: (2024)

TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Masking
di: Hu, Jiyuan, et al.
Pubblicazione: (2026)

Monocular Endoscopic Tissue 3D Reconstruction with Multi-Level Geometry Regularization
di: Chen, Yangsen, et al.
Pubblicazione: (2026)

Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction
di: Kim, Jin Hyeon, et al.
Pubblicazione: (2026)

GausSurf: Geometry-Guided 3D Gaussian Splatting for Surface Reconstruction
di: Wang, Jiepeng, et al.
Pubblicazione: (2024)

Unified Scene Representation and Reconstruction for 3D Large Language Models
di: Chu, Tao, et al.
Pubblicazione: (2024)

End-to-End Spatial-Temporal Transformer for Real-time 4D HOI Reconstruction
di: Zhang, Haoyu, et al.
Pubblicazione: (2026)

Joint 3D Geometry Reconstruction and Motion Generation for 4D Synthesis from a Single Image
di: Zhang, Yanran, et al.
Pubblicazione: (2025)

Multi-dimensional Preference Alignment by Conditioning Reward Itself
di: Jang, Jiho, et al.
Pubblicazione: (2025)

GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstruction
di: Huang, Yi-Chuan, et al.
Pubblicazione: (2025)