5 papers
G2P: Gaussian-to-Point Attribute Alignment for Boundary-Aware 3D Segmentation
Hojun Song, Chae-yeong Song, Jeong-hun Hong +5
Point cloud segmentation is critical for 3D scene understanding. However, sparse and irregular point distributions provide limited appearance evidence, making geometry-only feature…
APC: Transferable and Efficient Adversarial Point Counterattack for Robust 3D Point Cloud Recognition
Geunyoung Jung, Soohong Kim, Inseok Kong +1
The advent of deep neural networks has led to remarkable progress in 3D point cloud recognition, but they remain vulnerable to adversarial attacks. Although various defense methods…
P3T: Prototypical Point-level Prompt Tuning with Enhanced Generalization for 3D Vision-Language Models
Geunyoung Jung, Soohong Kim, Kyungwoo Song +1
With the rise of pre-trained models in the 3D point cloud domain for a wide range of real-world applications, adapting them to downstream tasks has become increasingly important. H…
CatalogStitch: Dimension-Aware and Occlusion-Preserving Object Compositing for Catalog Image Generation
Sanyam Jain, Pragya Kandari, Manit Singhal +2
Generative object compositing methods have shown remarkable ability to seamlessly insert objects into scenes. However, when applied to real-world catalog image generation, these me…
CompSplat: Compression-aware 3D Gaussian Splatting for Real-world Video
Hojun Song, Heejung Choi, Aro Kim +5
High-quality novel view synthesis (NVS) from real-world videos is crucial for applications such as cultural heritage preservation, digital twins, and immersive media. However, real…