Not Your Stereo-Typical Estimator: Combining Vision and Language for Volume Perception
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917400173084672 |
|---|---|
| author | Vinod, Gautham Coburn, Bruce Raghavan, Siddeshwar Zhu, Fengqing |
| author_facet | Vinod, Gautham Coburn, Bruce Raghavan, Siddeshwar Zhu, Fengqing |
| contents | Accurate volume estimation of objects from visual data is a long-standing challenge in computer vision with significant applications in robotics, logistics, and smart health. Existing methods often rely on complex 3D reconstruction pipelines or struggle with the ambiguity inherent in single-view images. To address these limitations, we introduce a new method that fuses implicit 3D cues from stereo vision with explicit prior knowledge from natural language text. Our approach extracts deep features from a stereo image pair and a descriptive text prompt that contains the object's class and an approximate volume, then integrates them using a simple yet effective projection layer into a unified, multi-modal representation for regression. We conduct extensive experiments on public datasets demonstrating that our text-guided approach significantly outperforms vision-only baselines. Our findings show that leveraging even simple textual priors can effectively guide the volume estimation task, paving the way for more context-aware visual measurement systems. Code: https://gitlab.com/viper-purdue/stereo-typical-estimator. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09886 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Not Your Stereo-Typical Estimator: Combining Vision and Language for Volume Perception Vinod, Gautham Coburn, Bruce Raghavan, Siddeshwar Zhu, Fengqing Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Multimedia Image and Video Processing Accurate volume estimation of objects from visual data is a long-standing challenge in computer vision with significant applications in robotics, logistics, and smart health. Existing methods often rely on complex 3D reconstruction pipelines or struggle with the ambiguity inherent in single-view images. To address these limitations, we introduce a new method that fuses implicit 3D cues from stereo vision with explicit prior knowledge from natural language text. Our approach extracts deep features from a stereo image pair and a descriptive text prompt that contains the object's class and an approximate volume, then integrates them using a simple yet effective projection layer into a unified, multi-modal representation for regression. We conduct extensive experiments on public datasets demonstrating that our text-guided approach significantly outperforms vision-only baselines. Our findings show that leveraging even simple textual priors can effectively guide the volume estimation task, paving the way for more context-aware visual measurement systems. Code: https://gitlab.com/viper-purdue/stereo-typical-estimator. |
| title | Not Your Stereo-Typical Estimator: Combining Vision and Language for Volume Perception |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Multimedia Image and Video Processing |
| url | https://arxiv.org/abs/2604.09886 |