3D Shape Augmentation with Content-Aware Shape Resizing
This addresses the data scarcity issue for 3D model training in computer vision, though it appears incremental as it adapts seam carving to 3D.
The paper tackles the problem of limited training data for 3D deep learning by introducing Efficient 3D Seam Carving (E3SC), a 3D model augmentation method that deforms parts of models while preserving semantics, resulting in diverse and high-quality augmented shapes that improve subsequent 3D generation algorithms.
Recent advancements in deep learning for 3D models have propelled breakthroughs in generation, detection, and scene understanding. However, the effectiveness of these algorithms hinges on large training datasets. We address the challenge by introducing Efficient 3D Seam Carving (E3SC), a novel 3D model augmentation method based on seam carving, which progressively deforms only part of the input model while ensuring the overall semantics are unchanged. Experiments show that our approach is capable of producing diverse and high-quality augmented 3D shapes across various types and styles of input models, achieving considerable improvements over previous methods. Quantitative evaluations demonstrate that our method effectively enhances the novelty and quality of shapes generated by other subsequent 3D generation algorithms.