Research map / 3D vision / 3D generation
Objaverse-XL: A Universe of 10M+ 3D Objects
Matt Deitke, Ruoshi Liu, Matthew Wallingford, Huong Ngo, Oscar Michel, Aditya Kusupati, Alan Fan, Christian Laforte, Vikram Voleti, Samir Yitzhak Gadre, Eli VanderBilt, Aniruddha Kembhavi and 5 more
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| finetune on the high-quality alignment subset (ablation) | Zero123-XL · Google Scanned Objects | PSNR: 18.225 -> 19.876 | Improved |
| finetune on the high-quality alignment subset (ablation) | Zero123-XL · Google Scanned Objects | SSIM: 0.877 -> 0.888 | Improved |
| finetune on the high-quality alignment subset (ablation) | Zero123-XL · Google Scanned Objects | LPIPS: 0.088 -> 0.075 | Improved |
| finetune on the high-quality alignment subset (ablation) | Zero123-XL · Google Scanned Objects | FID: 0.070 -> 0.056 | Improved |
| increase pretraining dataset size | Zero123 · Google Scanned Objects | rvisual similarity score | Improved |
| increase pretraining dataset size | PixelNeRF · held-out Objaverse-XL objects | novel view synthesis quality | Improved |
| pretrain on Objaverse-XL before fine-tuning | PixelNeRF · DTU and ShapeNet | PSNR | Improved |
Closest papers by meaning
- From an Image to a Scene: Learning to Imagine the World from a Million 360° Videos (NeurIPS 2024 · similarity 0.87)
- ImageNet3D: Towards General-Purpose Object-Level 3D Understanding (NeurIPS 2024 · similarity 0.87)
- Towards 3D Objectness Learning in an Open World (NeurIPS 2025 · similarity 0.87)
- EA3D: Online Open-World 3D Object Extraction from Streaming Videos (NeurIPS 2025 · similarity 0.86)
- DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision (CVPR 2024 · similarity 0.86)
- Uni3D: Exploring Unified 3D Representation at Scale (ICLR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
