Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.09883 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908650155540480 |
|---|---|
| author | Zhang, Liheng Wang, Jin Li, Hui Zhang, Bingfeng Liu, Weifeng |
| author_facet | Zhang, Liheng Wang, Jin Li, Hui Zhang, Bingfeng Liu, Weifeng |
| contents | 3D understanding has drawn significant attention recently, leveraging Vision-Language Models (VLMs) to enable multi-modal reasoning between point cloud and text data. Current 3D-VLMs directly embed the 3D point clouds into 3D tokens, following large 2D-VLMs with powerful reasoning capabilities. However, this framework has a great computational cost limiting its application, where we identify that the bottleneck lies in processing all 3D tokens in the Large Language Model (LLM) part. This raises the question: how can we reduce the computational overhead introduced by 3D tokens while preserving the integrity of their essential information? To address this question, we introduce Hierarchical Compensatory Compression (HCC-3D) to efficiently compress 3D tokens while maintaining critical detail retention. Specifically, we first propose a global structure compression (GSC), in which we design global queries to compress all 3D tokens into a few key tokens while keeping overall structural information. Then, to compensate for the information loss in GSC, we further propose an adaptive detail mining (ADM) module that selectively recompresses salient but under-attended features through complementary scoring. Extensive experiments demonstrate that HCC-3D not only achieves extreme compression ratios (approximately 98%) compared to previous 3D-VLMs, but also achieves new state-of-the-art performance, showing the great improvements on both efficiency and performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_09883 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HCC-3D: Hierarchical Compensatory Compression for 98% 3D Token Reduction in Vision-Language Models Zhang, Liheng Wang, Jin Li, Hui Zhang, Bingfeng Liu, Weifeng Computer Vision and Pattern Recognition 3D understanding has drawn significant attention recently, leveraging Vision-Language Models (VLMs) to enable multi-modal reasoning between point cloud and text data. Current 3D-VLMs directly embed the 3D point clouds into 3D tokens, following large 2D-VLMs with powerful reasoning capabilities. However, this framework has a great computational cost limiting its application, where we identify that the bottleneck lies in processing all 3D tokens in the Large Language Model (LLM) part. This raises the question: how can we reduce the computational overhead introduced by 3D tokens while preserving the integrity of their essential information? To address this question, we introduce Hierarchical Compensatory Compression (HCC-3D) to efficiently compress 3D tokens while maintaining critical detail retention. Specifically, we first propose a global structure compression (GSC), in which we design global queries to compress all 3D tokens into a few key tokens while keeping overall structural information. Then, to compensate for the information loss in GSC, we further propose an adaptive detail mining (ADM) module that selectively recompresses salient but under-attended features through complementary scoring. Extensive experiments demonstrate that HCC-3D not only achieves extreme compression ratios (approximately 98%) compared to previous 3D-VLMs, but also achieves new state-of-the-art performance, showing the great improvements on both efficiency and performance. |
| title | HCC-3D: Hierarchical Compensatory Compression for 98% 3D Token Reduction in Vision-Language Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.09883 |