Objaverse: A Universe of Annotated 3D Objects
Explore this paper's citation graph
- Type
- preprint
- Published
- 2022-12-15
- Cited by
- 1,809
- References
- 88
- Access
- Open access
- OpenAlex
- https://openalex.org/W4311730898
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:254685588
Keywords
Computer science, Robustness (evolution), Artificial intelligence, Field (mathematics), Benchmark (surveying)
References
- Physically Based Rendering: From Theory to Implementation
- BigBIRD: A large-scale 3D database of object instances
- Parsing IKEA Objects: Fine Pose Estimation
- WordNet: A Lexical Database for English
- ImageNet: A large-scale hierarchical image database
- ImageNet Large Scale Visual Recognition Challenge
- The KIT object models database: An object model database for object recognition, localization and manipulation in service robotics
- ShapeNet: An Information-Rich 3D Model Repository
- Deep Residual Learning for Image Recognition
- YFCC100M
- GloVe: Global Vectors for Word Representation
- A Large Dataset of Object Scans
- Bag of Tricks for Efficient Text Classification
- FastText.zip: Compressing text classification models
- ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes
- AI2-THOR: An Interactive 3D Environment for Visual AI
- Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings
- Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning
- PhotoShape
- The Open Images Dataset V4
Cited by
- Neural Shape Compiler: A Unified Framework for Transforming between Text, Point Cloud, and Program
- 3DGen: Triplane Latent Diffusion for Textured Mesh Generation
- SATR: Zero-Shot Semantic Segmentation of 3D Shapes
- ArK: Augmented Reality with Knowledge Interactive Emergent Ability
- Towards A Foundation Model for Generalist Robots: Diverse Skill Learning at Scale via Automated Task and Scene Generation
- OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding
- LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model
- Weakly Supervised 3D Open-vocabulary Segmentation
- Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape
- Connecting Multi-modal Contrastive Representations
- ZeroAvatar: Zero-shot 3D Avatar Generation from a Single Image
- Aladdin: Zero-Shot Hallucination of Stylized 3D Assets from Abstract Scene Descriptions
- Scalable 3D Captioning with Pretrained Models
- Generating Images with 3D Annotations Using Diffusion Models
- NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations
- UniG3D: A Unified 3D Object Generation Dataset
- Pushing the Limits of 3D Shape Generation at Scale
- One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization
- ID-Pose: Sparse-view Camera Pose Estimation by Inverting Diffusion Models
- Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
Related papers
- Theoretical Analysis of the Benchmark for Choosing Manipulative Instruments of Monetary Policies
- Some considerations of bridging stresses for fiber-reinforced ceramics
- Bridging the gap between science and politics : The role of precaution in chemicals control
- OS1322-394 Fracture mechanism of intralaminar crack propagation under mode II loading for CFRP laminates
- Exploring disk performance benchmarks