AI Paper Atlas

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

NeurIPS 2023 · 3D vision › 3D generation · approach: Monocular 3D object reconstruction · 97 citations (OpenAlex)

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 changedWhereMeasuredEffect
finetune on the high-quality alignment subset (ablation)Zero123-XL · Google Scanned ObjectsPSNR: 18.225 -> 19.876Improved
finetune on the high-quality alignment subset (ablation)Zero123-XL · Google Scanned ObjectsSSIM: 0.877 -> 0.888Improved
finetune on the high-quality alignment subset (ablation)Zero123-XL · Google Scanned ObjectsLPIPS: 0.088 -> 0.075Improved
finetune on the high-quality alignment subset (ablation)Zero123-XL · Google Scanned ObjectsFID: 0.070 -> 0.056Improved
increase pretraining dataset sizeZero123 · Google Scanned Objectsrvisual similarity scoreImproved
increase pretraining dataset sizePixelNeRF · held-out Objaverse-XL objectsnovel view synthesis qualityImproved
pretrain on Objaverse-XL before fine-tuningPixelNeRF · DTU and ShapeNetPSNRImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy