Object-Centric Domain Randomization for 3D Shape Reconstruction in the Wild
| Autor: | Cho, Junhyeong, Youwang, Kim, Yang, Hunmin, Oh, Tae-Hyun |
|---|---|
| Rok vydání: | 2024 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | One of the biggest challenges in single-view 3D shape reconstruction in the wild is the scarcity of <3D shape, 2D image>-paired data from real-world environments. Inspired by remarkable achievements via domain randomization, we propose ObjectDR which synthesizes such paired data via a random simulation of visual variations in object appearances and backgrounds. Our data synthesis framework exploits a conditional generative model (e.g., ControlNet) to generate images conforming to spatial conditions such as 2.5D sketches, which are obtainable through a rendering process of 3D shapes from object collections (e.g., Objaverse-XL). To simulate diverse variations while preserving object silhouettes embedded in spatial conditions, we also introduce a disentangled framework which leverages an initial object guidance. After synthesizing a wide range of data, we pre-train a model on them so that it learns to capture a domain-invariant geometry prior which is consistent across various domains. We validate its effectiveness by substantially improving 3D shape reconstruction models on a real-world benchmark. In a scale-up evaluation, our pre-training achieves 23.6% superior results compared with the pre-training on high-quality computer graphics renderings. Comment: Project Page: https://ObjectDR.github.io |
| Databáze: | arXiv |
| Externí odkaz: |
|