CLIPSym: Delving into Symmetry Detection with CLIP

TL;DR

CLIPSym leverages CLIP's vision-language capabilities with a novel symmetry detection model and prompting technique, achieving state-of-the-art results in geometric symmetry detection tasks.

Contribution

The paper introduces CLIPSym, a symmetry detection method that combines CLIP's pre-trained encoders with a rotation-equivariant decoder and a new prompting technique, SAPG.

Findings

Outperforms state-of-the-art on three datasets

Benefits from CLIP's pre-training and semantic prompts

Effective rotation and reflection symmetry detection

Abstract

Symmetry is one of the most fundamental geometric cues in computer vision, and detecting it has been an ongoing challenge. With the recent advances in vision-language models,~i.e., CLIP, we investigate whether a pre-trained CLIP model can aid symmetry detection by leveraging the additional symmetry cues found in the natural image descriptions. We propose CLIPSym, which leverages CLIP's image and language encoders and a rotation-equivariant decoder based on a hybrid of Transformer and $G$-Convolution to detect rotation and reflection symmetries. To fully utilize CLIP's language encoder, we have developed a novel prompting technique called Semantic-Aware Prompt Grouping (SAPG), which aggregates a diverse set of frequent object-based prompts to better integrate the semantic cues for symmetry detection. Empirically, we show that CLIPSym outperforms the current state-of-the-art on three standard symmetry detection datasets (DENDI, SDRW, and LDRS). Finally, we conduct detailed ablations verifying the benefits of CLIP's pre-training, the proposed equivariant decoder, and the SAPG technique. The code is available at https://github.com/timyoung2333/CLIPSym.