paper-with-me

홈 › Papers

PEGASUS: Physically Enhanced Gaussian Splatting Simulation System for 6DoF Object Pose Dataset Generation

2024-01-04 · Lukas Meyer, Floris Erich, Yusuke Yoshiyasu, Marc Stamminger, Noriaki Ando, Yukiyasu Domae

We introduce Physically Enhanced Gaussian Splatting Simulation System (PEGASUS) for 6DOF object pose dataset generation, a versatile dataset generator based on 3D Gaussian Splatting. Environment and object representations can be easily obtained using commodity cameras to reconstruct with Gaussian Splatting. <i>PEGASUS</i> allows the composition of new scenes by merging the respective underlying Gaussian Splatting point cloud of an environment with one or multiple objects. Leveraging a physics engine enables the simulation of natural object placement within a scene through interaction between meshes extracted for the objects and the environment. Consequently, an extensive amount of new scenes - static or dynamic - can be created by combining different environments and objects. By rendering scenes from various perspectives, diverse data points such as RGB images, depth maps, semantic masks, and 6DoF object poses can be extracted. Our study demonstrates that training on data generated by PEGASUS enables pose estimation networks to successfully transfer from synthetic data to real-world data. Moreover, we introduce the Ramen dataset, comprising 30 Japanese cup noodle items. This dataset includes spherical scans that captures images from both object hemisphere and the Gaussian Splatting reconstruction, making them compatible with PEGASUS.

📄 PDF Abstract BibTeX arXiv:2401.02281

Code (1)

meyerls/pegasus 공식 구현 pytorch

Tasks

Dataset GenerationObjectPose Estimation

Methods 이 논문이 사용한 방법론

PEGASUS PEGASUS proposes a transformer-based model for abstractive summarization. It uses a special self-supervised pre-training objective called gap-sentences generation (GSG) that's…

Similar Papers 제목 키워드 기반

PhyCAGE: Physically Plausible Compositional 3D Asset Generation from a Single Image

2024-11-27 · Han Yan, Mingrui Zhang, Yang Li, Chao Ma 외

We present PhyCAGE, the first approach for physically plausible compositional 3D asset generation from a single image. Given an input image, we first generate consistent multi-view images for components of the assets. Th…

GaussTwin: Unified Simulation and Correction with Gaussian Splatting for Robotic Digital Twins

2026-03-05 · Yichen Cai, Paul Jansonnie, Cristiana de Farias, Oleg Arenz 외 arxiv

Digital twins promise to enhance robotic manipulation by maintaining a consistent link between real-world perception and simulation. However, most existing systems struggle with the lack of a unified model, complex dynam…

GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation

2025-05-21 · Yuchen Li, Chaoran Feng, Zhenyu Tang, Kaiyuan Deng 외

We introduce GS2E (Gaussian Splatting to Event), a large-scale synthetic event dataset for high-fidelity event vision tasks, captured from real-world sparse multi-view RGB images. Existing event datasets are often synthe…

3D ReconstructionDiversity

PG-3DGS: Optimizing 3D Gaussian Splatting to Satisfy Physics Objectives

2026-05-11 · Zachary Lee, Maxwell Jacobson, Yexiang Xue arxiv

Recent advances in Gaussian Splatting have enabled fast, high-fidelity 3D scene generation, yet these methods remain purely visual and lack an understanding of how shapes behave in the physical world. We introduce Physic…

Scene Generation

6DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric Rendering

2024-10-07 · Zhongpai Gao, Benjamin Planche, Meng Zheng, Anwesa Choudhuri 외

Novel view synthesis has advanced significantly with the development of neural radiance fields (NeRF) and 3D Gaussian splatting (3DGS). However, achieving high quality without compromising real-time rendering remains cha…

3DGSNeRFNovel View Synthesis