Abstract: Recent open-world representation learning approaches have leveraged CLIP to enable zero-shot 3D object recognition. However, performance on real point clouds with occlusions still falls ...
This is the official code for the ECCV 2024 paper "Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models". The format of the dataset is as ...
Abstract: Text-based image segmentation is the task of segmenting specific objects in an image based on user-provided text prompts. To improve the performance of existing models, this paper emphasizes ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback