1 code implementation • 23 May 2023 • Taiki Miyanishi, Daichi Azuma, Shuhei Kurita, Motoki Kawanabe
We present a novel task for cross-dataset visual grounding in 3D scenes (Cross3DVG), which overcomes limitations of existing 3D visual grounding models, specifically their restricted 3D resources and consequent tendencies of overfitting a specific 3D dataset.