Abstract: Text-driven 3D editing is an emerging task that focuses on modifying scenes based on text prompts. Current methods often adapt pre-trained 2D image editors to multi-view observations, using ...

Abstract: Large-scale scientific simulations require significant resources to generate high-resolution time-varying data (TVD). While super-resolution is an efficient post-processing strategy to ...

This is a fixed and working version of the SPAR3D (Stable Point-Aware Reconstruction of 3D Objects) project. I took the original codebase, identified and corrected errors, and now use it for 3D mesh ...

3D face recognition is a powerful biometric modality that captures detailed facial geometry, enabling robustness to variations in lighting, pose, occlusion, and presentation attacks. Despite these ...