Copertina

MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jiang, Hanwen, Xu, Zexiang, Xie, Desai, Chen, Ziwen, Jin, Haian, Luan, Fujun, Shu, Zhixin, Zhang, Kai, Bi, Sai, Sun, Xin, Gu, Jiuxiang, Huang, Qixing, Pavlakos, Georgios, Tan, Hao
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

Real3D: Scaling Up Large Reconstruction Models with Real-World Images
di: Jiang, Hanwen, et al.
Pubblicazione: (2024)

RayZer: A Self-supervised Large View Synthesis Model
di: Jiang, Hanwen, et al.
Pubblicazione: (2025)

LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias
di: Jin, Haian, et al.
Pubblicazione: (2024)

Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats
di: Ziwen, Chen, et al.
Pubblicazione: (2024)

LRM-Zero: Training Large Reconstruction Models with Synthesized Data
di: Xie, Desai, et al.
Pubblicazione: (2024)

CoFie: Learning Compact Neural Surface Representations with Coordinate Fields
di: Jiang, Hanwen, et al.
Pubblicazione: (2024)

RelitLRM: Generative Relightable Radiance for Large Reconstruction Models
di: Zhang, Tianyuan, et al.
Pubblicazione: (2024)

Neural Gaffer: Relighting Any Object via Diffusion
di: Jin, Haian, et al.
Pubblicazione: (2024)

MeshLRM: Large Reconstruction Model for High-Quality Meshes
di: Wei, Xinyue, et al.
Pubblicazione: (2024)

Reconstructing Humans with a Biomechanically Accurate Skeleton
di: Xia, Yan, et al.
Pubblicazione: (2025)

Atlas Gaussians Diffusion for 3D Generation
di: Yang, Haitao, et al.
Pubblicazione: (2024)

Gaussian Mixture Flow Matching Models
di: Chen, Hansheng, et al.
Pubblicazione: (2025)

Neural BRDF Importance Sampling by Reparameterization
di: Wu, Liwen, et al.
Pubblicazione: (2025)

KFC-W: Generating 3D-Consistent Videos from Unposed Internet Photos
di: Chou, Gene, et al.
Pubblicazione: (2024)

EP-CFG: Energy-Preserving Classifier-Free Guidance
di: Zhang, Kai, et al.
Pubblicazione: (2024)

Turbo3D: Ultra-fast Text-to-3D Generation
di: Hu, Hanzhe, et al.
Pubblicazione: (2024)

Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling
di: Wu, Liwen, et al.
Pubblicazione: (2024)

PBIR-NIE: Glossy Object Capture under Non-Distant Lighting
di: Cai, Guangyan, et al.
Pubblicazione: (2024)

Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priors
di: Kuang, Zhengfei, et al.
Pubblicazione: (2024)

GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting
di: Zhang, Kai, et al.
Pubblicazione: (2024)

PointRecon: Online Point-based 3D Reconstruction via Ray-based 2D-3D Matching
di: Ziwen, Chen, et al.
Pubblicazione: (2024)

Long-LRM++: Preserving Fine Details in Feed-Forward Wide-Coverage Reconstruction
di: Ziwen, Chen, et al.
Pubblicazione: (2025)

LRM: Large Reconstruction Model for Single Image to 3D
di: Hong, Yicong, et al.
Pubblicazione: (2023)

Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning
di: Xie, Desai, et al.
Pubblicazione: (2023)

Reconstructing Hand-Held Objects in 3D from Images and Videos
di: Wu, Jane, et al.
Pubblicazione: (2024)

Generating 360° Video is What You Need For a 3D Scene
di: Zhang, Zhaoyang, et al.
Pubblicazione: (2025)

4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time
di: Ma, Ziqiao, et al.
Pubblicazione: (2025)

DATENeRF: Depth-Aware Text-based Editing of NeRFs
di: Rojas, Sara, et al.
Pubblicazione: (2024)

TensoIR: Tensorial Inverse Rendering
di: Jin, Haian, et al.
Pubblicazione: (2023)

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

FIction: 4D Future Interaction Prediction from Video
di: Ashutosh, Kumar, et al.
Pubblicazione: (2024)

Evaluating Zero-Shot GPT-4V Performance on 3D Visual Question Answering Benchmarks
di: Singh, Simranjit, et al.
Pubblicazione: (2024)

E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training
di: Zhao, Qitao, et al.
Pubblicazione: (2025)

Test-Time Training Done Right
di: Zhang, Tianyuan, et al.
Pubblicazione: (2025)

Enhancing Monocular 3D Hand Reconstruction with Learned Texture Priors
di: Karvounas, Giorgos, et al.
Pubblicazione: (2025)

NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Support
di: Wei, Xinyue, et al.
Pubblicazione: (2023)

Softmax-GS: Generalized Gaussians Learning When to Blend or Bound
di: Ziwen, Chen, et al.
Pubblicazione: (2026)

SynthGuard: An Open Platform for Detecting AI-Generated Multimedia with Multimodal LLMs
di: Desai, Shail, et al.
Pubblicazione: (2025)

Age-Inclusive 3D Human Mesh Recovery for Action-Preserving Data Anonymization
di: Chatzichristodoulou, Georgios, et al.
Pubblicazione: (2025)

HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Image
di: Hu, Hezhen, et al.
Pubblicazione: (2026)