PEVA-Net: Prompt-Enhanced View Aggregation Network for Zero/Few-Shot Multi-View 3D Shape Recognition

arXiv:2404.19168v1 Announce Type: new
Abstract: Large vision-language models have impressively promote the performance of 2D visual recognition under zero/few-shot scenarios. In this paper, we focus on exploiting the large vision-language model, i.e., CLIP, to address zero/few-shot 3D shape recognition based on multi-view representations. The key challenge for both tasks is to generate a discriminative descriptor of the 3D shape represented by multiple view images under the scenarios of either without explicit training (zero-shot 3D shape recognition) or training with a …

abstract aggregation arxiv challenge clip cs.cv few-shot focus key language language model language models network paper performance promote prompt recognition tasks the key type view vision vision-language vision-language models visual