A Comparative Evaluation of Geometric Accuracy in NeRF and Gaussian Splatting
Mikolaj Zielinski, Eryk Vykysaly, Bartlomiej Biesiada, Jan Baturo, Mateusz Capala + 1 more
TLDR
This paper introduces a pipeline and benchmark to evaluate the geometric accuracy of neural rendering methods like NeRF and Gaussian Splatting.
Key contributions
- Evaluates geometric accuracy of neural rendering (NeRF, Gaussian Splatting).
- Introduces a new evaluation pipeline for surface and shape fidelity.
- Provides a benchmark dataset with 19 diverse 3D scenes.
- Highlights importance for robotics tasks like grasping and manipulation.
Why it matters
Standard metrics for neural rendering overlook crucial geometric fidelity. This paper addresses this by providing a dedicated pipeline and benchmark to assess surface and shape accuracy. This is vital for robotics, where precise geometry enables effective grasping and manipulation.
Original Abstract
Recent advances in neural rendering have introduced numerous 3D scene representations. Although standard computer vision metrics evaluate the visual quality of generated images, they often overlook the fidelity of surface geometry. This limitation is particularly critical in robotics, where accurate geometry is essential for tasks such as grasping and object manipulation. In this paper, we present an evaluation pipeline for neural rendering methods that focuses on geometric accuracy, along with a benchmark comprising 19 diverse scenes. Our approach enables a systematic assessment of reconstruction methods in terms of surface and shape fidelity, complementing traditional visual metrics.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.