IPDN: Image-enhanced Prompt Decoding Network for 3D Referring Expression Segmentation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916558496858112 |
|---|---|
| author | Chen, Qi Wu, Changli Ji, Jiayi Ma, Yiwei Yang, Danni Sun, Xiaoshuai |
| author_facet | Chen, Qi Wu, Changli Ji, Jiayi Ma, Yiwei Yang, Danni Sun, Xiaoshuai |
| contents | 3D Referring Expression Segmentation (3D-RES) aims to segment point cloud scenes based on a given expression. However, existing 3D-RES approaches face two major challenges: feature ambiguity and intent ambiguity. Feature ambiguity arises from information loss or distortion during point cloud acquisition due to limitations such as lighting and viewpoint. Intent ambiguity refers to the model's equal treatment of all queries during the decoding process, lacking top-down task-specific guidance. In this paper, we introduce an Image enhanced Prompt Decoding Network (IPDN), which leverages multi-view images and task-driven information to enhance the model's reasoning capabilities. To address feature ambiguity, we propose the Multi-view Semantic Embedding (MSE) module, which injects multi-view 2D image information into the 3D scene and compensates for potential spatial information loss. To tackle intent ambiguity, we designed a Prompt-Aware Decoder (PAD) that guides the decoding process by deriving task-driven signals from the interaction between the expression and visual features. Comprehensive experiments demonstrate that IPDN outperforms the state-ofthe-art by 1.9 and 4.2 points in mIoU metrics on the 3D-RES and 3D-GRES tasks, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_04995 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | IPDN: Image-enhanced Prompt Decoding Network for 3D Referring Expression Segmentation Chen, Qi Wu, Changli Ji, Jiayi Ma, Yiwei Yang, Danni Sun, Xiaoshuai Computer Vision and Pattern Recognition Artificial Intelligence 3D Referring Expression Segmentation (3D-RES) aims to segment point cloud scenes based on a given expression. However, existing 3D-RES approaches face two major challenges: feature ambiguity and intent ambiguity. Feature ambiguity arises from information loss or distortion during point cloud acquisition due to limitations such as lighting and viewpoint. Intent ambiguity refers to the model's equal treatment of all queries during the decoding process, lacking top-down task-specific guidance. In this paper, we introduce an Image enhanced Prompt Decoding Network (IPDN), which leverages multi-view images and task-driven information to enhance the model's reasoning capabilities. To address feature ambiguity, we propose the Multi-view Semantic Embedding (MSE) module, which injects multi-view 2D image information into the 3D scene and compensates for potential spatial information loss. To tackle intent ambiguity, we designed a Prompt-Aware Decoder (PAD) that guides the decoding process by deriving task-driven signals from the interaction between the expression and visual features. Comprehensive experiments demonstrate that IPDN outperforms the state-ofthe-art by 1.9 and 4.2 points in mIoU metrics on the 3D-RES and 3D-GRES tasks, respectively. |
| title | IPDN: Image-enhanced Prompt Decoding Network for 3D Referring Expression Segmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2501.04995 |