Pith. sign in

IPDN: Image-enhanced Prompt Decoding Network for 3D Referring Expression Segmentation

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

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.

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

3DResT: A Strong Baseline for Semi-Supervised 3D Referring Expression Segmentation

cs.CV · 2025-04-17 · conditional · novelty 6.0

3DResT applies teacher-student semi-supervised learning to 3D referring expression segmentation, promoting high-agreement pseudo-labels into the labeled set and dynamically weighting low-agreement ones, and reports a +8.34 mIoU gain over fully supervised training at 1% labels on ScanRefer.

citing papers explorer

Showing 1 of 1 citing paper.

  • 3DResT: A Strong Baseline for Semi-Supervised 3D Referring Expression Segmentation cs.CV · 2025-04-17 · conditional · none · ref 9 · internal anchor

    3DResT applies teacher-student semi-supervised learning to 3D referring expression segmentation, promoting high-agreement pseudo-labels into the labeled set and dynamically weighting low-agreement ones, and reports a +8.34 mIoU gain over fully supervised training at 1% labels on ScanRefer.