A Comparative Evaluation of Geometric Accuracy in NeRF and Gaussian Splatting
For robotics practitioners, this work provides a benchmark and evaluation pipeline to assess geometric fidelity of neural rendering methods, addressing a gap in standard metrics.
The paper evaluates geometric accuracy of NeRF and Gaussian Splatting methods, finding that Gaussian Splatting achieves higher surface fidelity (e.g., 15% better Chamfer distance) while NeRF excels in visual quality, highlighting a trade-off critical for robotics applications.
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.