Publication
GLVD: Guided Learned Vertex Descent
Conference Article
Conference
Neural Information Processing Systems (NIPS)
Edition
2025
Doc link
https://openreview.net/forum?id=T7KZbdzAXB
File
Authors
Projects associated
Abstract
Existing 3D face modeling methods usually depend on 3D Morphable Models, which inherently constrain the representation capacity to fixed shape priors. Optimization-based approaches offer high-quality reconstructions but tend to be computationally expensive. In this work, we introduce GLVD, a hybrid method for 3D face reconstruction from few-shot images that extends Learned Vertex Descent (LVD) by integrating per-vertex neural field optimization with global structural guidance from dynamically predicted 3D keypoints. By incorporating relative spatial encoding, GLVD iteratively refines mesh vertices without requiring dense 3D supervision. This enables expressive and adaptable geometry reconstruction while maintaining computational efficiency. GLVD achieves state-of-the-art performance in single-view settings and remains highly competitive in multi-view scenarios, all while substantially reducing inference time.
Categories
pattern recognition.
Author keywords
Computer Vision, 3D Face Reconstruction, Neural Fields, Few-Shot 3D Reconstruction
Scientific reference
P. Caselles and F. Moreno-Noguer. GLVD: Guided Learned Vertex Descent, 2025 Neural Information Processing Systems, 2025, San Diego, USA.
Follow us!