image-generation

3D Generation

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in image-generation

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find image-generation models and implementations

threestudio-project/threestudio

3 papers 5,569

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following

P. Heng, Hongsheng Li, Renrui Zhang, Peng Gao, Ziyu Guo, Ke Chen, Jiaming Han, Xiangyang Zhu, Yiwen Tang, Xianzheng Ma, Xianzhi Li•Thu Aug 31 2023

Point-LLM is presented, the first 3D large language model (LLM) following 3D multi-modal instructions, which injects the semantics of Point-Bind into pre-trained LLMs, e.g., LLaMA, which requires no 3D instruction data, but exhibits superior 3D and multi- modal question-answering capacity.

Content

Pointcept/GPT4Point

2 papers 249

faceonlive/ai-research

2 papers 103

192

0

Paper Graph

LION: Latent Point Diffusion Models for 3D Shape Generation

S. Fidler, Arash Vahdat, Karsten Kreis, O. Litany, Francis Williams, Zan Gojcic, Xiaohui Zeng•Tue Oct 11 2022

The hierarchical Latent Point Diffusion Model (LION) is introduced, set up as a variational autoencoder (VAE) with a hierarchical latent space that combines a global shape latent representation with a point-structured latent space for 3D shape generation.

631 0

Paper Graph

Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures

Or Patashnik, D. Cohen-Or, G. Metzer, Elad Richardson, R. Giryes•Sun Nov 13 2022

This work adapts the score distillation to the publicly available, and computationally efficient, Latent Diffusion Models, which apply the entire diffusion process in a compact latent space of a pretrained autoencoder.

564 0

Paper Graph

ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation

Zhengyi Wang, Hang Su, Cheng Lu, Chongxuan Li, Fan Bao, Jun Zhu•Wed May 24 2023

This work proposes to model the 3D parameter as a random variable instead of a constant as in SDS and presents variational score distillation (VSD), a principled particle-based variational framework to explain and address the aforementioned issues in text-to-3D generation.

1182 0

Paper Graph

StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation

Chunhua Shen, Tao Chen, YU Gang, Guosheng Lin, Chi Zhang, Yiwen Chen, Yijun Fu, Zheng-Yang Zhou, Billzb Wang, Bin Fu•Mon May 29 2023

This paper presents a novel method for generating high-quality, stylized 3D avatars that utilizes pre-trained image-text diffusion models for data generation and a Generative Adversarial Network (GAN)-based 3D generation network for training.

32 0

Paper Graph

SyncDreamer: Generating Multiview-consistent Images from a Single-view Image

Lingjie Liu, Yuan Liu, Chu-Hsing Lin, Zijiao Zeng, Xiaoxiao Long, Taku Komura, Wenping Wang•Wed Sep 06 2023

Experiments show that SyncDreamer generates images with high consistency across different views, thus making it well-suited for various 3D generation tasks such as novel-view-synthesis, text-to-3D, and image-to -3D.

625 0

Paper Graph

GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation

Junsheng Zhou, Baorui Ma, Yu-Shen Liu, Tiejun Huang, Xinlong Wang, Haoge Deng•Tue Nov 28 2023

GeoDream is presented, a novel method that incorporates explicit generalized 3D priors with 2D diffusion priors to enhance the capability of obtaining unambiguous 3D consistent geometric structures without sacrificing diversity or fidelity and provides superior guidance for the refinement of 3D geometric priors.

34 0

Paper Graph

VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation

Zekun Qi, Runpei Dong, Kaisheng Ma, Muzhou Yu•Thu Jul 27 2023

This work revisits the impact of different 3D representations on generation quality and efficiency and proposes a progressive generation method through Voxel-Point Progressive Representation (VPP), which efficiently generates high-fidelity and diverse 3D shapes across different categories, while also exhibiting excellent representation transfer performance.

20 0

Paper Graph

MVDream: Multi-view Diffusion for 3D Generation

X. Yang, Kejie Li, Yichun Shi, Jianglong Ye, Peng Wang, Mai Long•Wed Aug 30 2023

MVDream, a diffusion model that is able to generate consistent multi-view images from a given text prompt, is introduced and it is demonstrated that such a multi-view diffusion model is implicitly a generalizable 3D prior agnostic to 3D representations.

874 0

Paper Graph

V3D: Video Diffusion Models are Effective 3D Generators

Zilong Chen, Yikai Wang, Feng Wang, Zhengyi Wang, Huaping Liu•Sun Mar 10 2024

V3D is introduced, which leverages the world simulation capacity of pre-trained video diffusion models to facilitate 3D generation and can be extended to scene-level novel view synthesis, achieving precise control over the camera path with sparse input views.

95 0

Paper Graph

Adding a benchmark result helps the community track progress.