(CVPR 2023) PLA: Language-Driven Open-Vocabulary 3D Scene Understanding & (CVPR2024) RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding
Hi, thanks for your interesting work!
I can only find the captions and the corresponding point indices, but I can't find the corresponding 2D rendering images. How could I get them?
Thanks a lot!!
Hi, we use real-world images from ScanNet dataset instead of rendering images. You can obtain the image (scannet_frames_25k) downloading link from ScanNet's official website.
Hi, thanks for your interesting work! I can only find the captions and the corresponding point indices, but I can't find the corresponding 2D rendering images. How could I get them? Thanks a lot!!