← Search

Akshobhya Sharma

1 accepted papers

2026

Learning 3D Shape Fidelity Metric from Real-world Distortions

CVPR 2026

3D generation and reconstruction have become essential in many computer vision applications, where the reconstructed or generated 3D shapes need to appear realistic to human perception. However, traditional metrics like Chamfer Distance to compare two 3D shapes focus primarily on matching accuracy o

Cited by 0SourceScholar