Copertina

ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Yongwei, Wang, Tengfei, Wu, Tong, Pan, Xingang, Jia, Kui, Liu, Ziwei
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

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE
di: Chen, Yongwei, et al.
Pubblicazione: (2024)

PI-Light: Physics-Inspired Diffusion for Full-Image Relighting
di: Liang, Zhexin, et al.
Pubblicazione: (2026)

Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion
di: He, Zexin, et al.
Pubblicazione: (2024)

ThemeStation: Generating Theme-Aware 3D Assets from Few Exemplars
di: Wang, Zhenwei, et al.
Pubblicazione: (2024)

3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion
di: Chen, Zhaoxi, et al.
Pubblicazione: (2024)

ArtiLatent: Realistic Articulated 3D Object Generation via Structured Latents
di: Chen, Honghua, et al.
Pubblicazione: (2025)

MvDrag3D: Drag-based Creative 3D Editing via Multi-view Generation-Reconstruction Priors
di: Chen, Honghua, et al.
Pubblicazione: (2024)

PnP-U3D: Plug-and-Play 3D Framework Bridging Autoregression and Diffusion for Unified Understanding and Generation
di: Chen, Yongwei, et al.
Pubblicazione: (2026)

PhysX-3D: Physical-Grounded 3D Asset Generation
di: Cao, Ziang, et al.
Pubblicazione: (2025)

DiffTF++: 3D-aware Diffusion Transformer for Large-Vocabulary 3D Generation
di: Cao, Ziang, et al.
Pubblicazione: (2024)

LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation
di: Tang, Jiaxiang, et al.
Pubblicazione: (2024)

3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors
di: Hong, Fangzhou, et al.
Pubblicazione: (2024)

LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation
di: Lan, Yushi, et al.
Pubblicazione: (2024)

ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models
di: Xu, Rui, et al.
Pubblicazione: (2024)

Material Anything: Generating Materials for Any 3D Object via Diffusion
di: Huang, Xin, et al.
Pubblicazione: (2024)

Textured 3D Regenerative Morphing with 3D Diffusion Prior
di: Yang, Songlin, et al.
Pubblicazione: (2025)

MVIP-NeRF: Multi-view 3D Inpainting on NeRF Scenes via Diffusion Prior
di: Chen, Honghua, et al.
Pubblicazione: (2024)

FastMesh: Efficient Artistic Mesh Generation via Component Decoupling
di: Kim, Jeonghwan, et al.
Pubblicazione: (2025)

3DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement
di: Luo, Yihang, et al.
Pubblicazione: (2024)

3DGen-Bench: Comprehensive Benchmark Suite for 3D Generative Models
di: Zhang, Yuhan, et al.
Pubblicazione: (2025)

WonderVerse: Extendable 3D Scene Generation with Video Generative Models
di: Feng, Hao, et al.
Pubblicazione: (2025)

Consistent123: One Image to Highly Consistent 3D Asset Using Case-Aware Diffusion Priors
di: Lin, Yukang, et al.
Pubblicazione: (2023)

DecompDreamer: A Composition-Aware Curriculum for Structured 3D Asset Generation
di: Nath, Utkarsh, et al.
Pubblicazione: (2025)

DriveCombo: Benchmarking Compositional Traffic Rule Reasoning in Autonomous Driving
di: Ma, Enhui, et al.
Pubblicazione: (2026)

PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image
di: Cao, Ziang, et al.
Pubblicazione: (2025)

CineVerse: Consistent Keyframe Synthesis for Cinematic Scene Composition
di: Phung, Quynh, et al.
Pubblicazione: (2025)

ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation
di: Yang, Songlin, et al.
Pubblicazione: (2026)

Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion
di: Wang, Zhenwei, et al.
Pubblicazione: (2024)

DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling
di: Wen, Kairun, et al.
Pubblicazione: (2025)

PhyCAGE: Physically Plausible Compositional 3D Asset Generation from a Single Image
di: Yan, Han, et al.
Pubblicazione: (2024)

MultiDreamer3D: Multi-concept 3D Customization with Concept-Aware Diffusion Guidance
di: Song, Wooseok, et al.
Pubblicazione: (2025)

NOFT: Test-Time Noise Finetune via Information Bottleneck for Highly Correlated Asset Creation
di: Li, Jia, et al.
Pubblicazione: (2025)

Omni6D: Large-Vocabulary 3D Object Dataset for Category-Level 6D Object Pose Estimation
di: Zhang, Mengchen, et al.
Pubblicazione: (2024)

Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space
di: Zhou, Yifan, et al.
Pubblicazione: (2025)

REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignment
di: Han, Haonan, et al.
Pubblicazione: (2024)

DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
di: Tang, Jiaxiang, et al.
Pubblicazione: (2023)

Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images
di: Qi, Zhangyang, et al.
Pubblicazione: (2024)

Spatial As Deep: Spatial CNN for Traffic Scene Understanding
di: Pan, Xingang, et al.
Pubblicazione: (2017)

DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation
di: Zhao, Wang, et al.
Pubblicazione: (2024)

Combo: Co-speech holistic 3D human motion generation and efficient customizable adaptation in harmony
di: Xu, Chao, et al.
Pubblicazione: (2024)