paper-with-me

홈 › Papers

Not Your Stereo-Typical Estimator: Combining Vision and Language for Volume Perception

2026-04-10 · Gautham Vinod, Bruce Coburn, Siddeshwar Raghavan, Fengqing Zhu arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.09886

Code (0)

등록된 구현이 없습니다.

Tasks

3D Reconstruction

Similar Papers 제목 키워드 기반

Rectification-specific Supervision and Constrained Estimator for Online Stereo Rectification

2025-01-01 · CVPR 2025 1 · Rui Gong, Kim-Hui Yap, Weide Liu, Xulei Yang 외

Online stereo rectification is critical for autonomous vehicles and robots in dynamic environments, where factors such as vibration, temperature fluctuations, and mechanical stress can affect rectification accuracy a…

Autonomous VehiclesDepth EstimationOptical Flow EstimationStereo Depth Estimation

Real-Time Model-Based Rigid Object Pose Estimation and Tracking Combining Dense and Sparse Visual Cues

2013-06-01 · CVPR 2013 6 · Karl Pauwels, Leonardo Rubio, Javier Diaz, Eduardo Ros

We propose a novel model-based method for estimating and tracking the six-degrees-of-freedom (6DOF) pose of rigid objects of arbitrary shapes in real-time. By combining dense motion and stereo cues with sparse keypoint c…

Pose Estimation

Extending 6D Object Pose Estimators for Stereo Vision

2024-02-08 · Thomas Pöllabauer, Jan Emrich, Volker Knauthe, Arjan Kuijper

Estimating the 6D pose of objects accurately, quickly, and robustly remains a difficult task. However, recent methods for directly regressing poses from RGB images using dense features have achieved state-of-the-art resu…

6D Pose Estimation6D Pose Estimation using RGBObjectPose Estimation

Self-Supervised Monocular Depth Hints

2019-09-19 · ICCV 2019 10 · Jamie Watson, Michael Firman, Gabriel J. Brostow, Daniyar Turmukhambetov

Monocular depth estimators can be trained with various forms of self-supervision from binocular-stereo data to circumvent the need for high-quality laser scans or other ground-truth data. The disadvantage, however, is th…

Depth EstimationDepth PredictionMonocular Depth EstimationSelf-Supervised Learning

The Role of Cyclopean-Eye in Stereo Vision

2025-06-26 · Sherlon Almeida da Silva, Davi Geiger, Luiz Velho, Moacir Antonelli Ponti

This work investigates the geometric foundations of modern stereo vision systems, with a focus on how 3D structure and human-inspired perception contribute to accurate depth reconstruction. We revisit the Cyclopean Eye m…