TSP3D: Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding

This repo contains the models for paper Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding. Code is available at: https://github.com/GWxuan/TSP3D

Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding
Wenxuan Guo*, Xiuwei Xu*, Ziwei Wang, Jianjiang Feng†, Jie Zhou, Jiwen Lu

* Equal contribution † Corresponding author

In this work, we propose an efficient multi-level convolution architecture for 3D visual grounding. TSP3D achieves superior performance compared to previous approaches in both inference speed and accuracy.

Main Results

• We provide the checkpoints for quick reproduction of the results reported in the paper.

  Benchmark	Pipeline	[email protected]	[email protected]	Inference Speed (FPS)	Downloads
  ScanRefer	Single-stage	56.45	46.71	12.43	model

  Benchmark	Pipeline	[email protected]	[email protected]	Downloads
  Nr3d	Single-stage	48.7	37.0	model
  Sr3d	Single-stage	57.1	44.1	model

• Comparison of 3DVG methods on ScanRefer dataset: