paper-with-me

홈 › Papers

Large Language Models Can Understanding Depth from Monocular Images

2024-09-02 · Zhongyi Xia, Tianzhao Wu

Monocular depth estimation is a critical function in computer vision applications. This paper shows that large language models (LLMs) can effectively interpret depth with minimal supervision, using efficient resource utilization and a consistent neural network architecture. We introduce LLM-MDE, a multimodal framework that deciphers depth through language comprehension. Specifically, LLM-MDE employs two main strategies to enhance the pretrained LLM's capability for depth estimation: cross-modal reprogramming and an adaptive prompt estimation module. These strategies align vision representations with text prototypes and automatically generate prompts based on monocular images, respectively. Comprehensive experiments on real-world MDE datasets confirm the effectiveness and superiority of LLM-MDE, which excels in few-/zero-shot tasks while minimizing resource use. The source code is available.

📄 PDF Abstract BibTeX arXiv:2409.01133

Code (0)

등록된 구현이 없습니다.

Tasks

Depth EstimationMonocular Depth Estimation

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Center3D: Center-based Monocular 3D Object Detection with Joint Depth Understanding

2020-05-27 · Yunlei Tang, Sebastian Dorn, Chiragkumar Savani

Localizing objects in 3D space and understanding their associated 3D properties is challenging given only monocular RGB images. The situation is compounded by the loss of depth information during perspective projection. …

3D Object DetectionDepth EstimationGeneral ClassificationMonocular 3D Object Detection+3

SynDeMo: Synergistic Deep Feature Alignment for Joint Learning of Depth and Ego-Motion

2019-10-01 · ICCV 2019 10 · Behzad Bozorgtabar, Mohammad Saeed Rad, Dwarikanath Mahapatra, Jean-Philippe Thiran

Despite well-established baselines, learning of scene depth and ego-motion from monocular video remains an ongoing challenge, specifically when handling scaling ambiguity issues and depth inconsistencies in image sequenc…

Depth EstimationMotion Estimation

MGNet: Monocular Geometric Scene Understanding for Autonomous Driving

2022-06-27 · ICCV 2021 10 · Markus Schön, Michael Buchholz, Klaus Dietmayer

We introduce MGNet, a multi-task framework for monocular geometric scene understanding. We define monocular geometric scene understanding as the combination of two known tasks: Panoptic segmentation and self-supervised m…

Autonomous DrivingDepth EstimationGPUMonocular Depth Estimation+2

Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

2023-12-04 · CVPR 2024 1 · Bingxin Ke, Anton Obukhov, Shengyu Huang, Nando Metzger 외

Monocular depth estimation is a fundamental computer vision task. Recovering 3D depth from a single image is geometrically ill-posed and requires scene understanding, so it is not surprising that the rise of deep learnin…

Depth EstimationGPUMonocular Depth EstimationScene Understanding+1

DGOcc: Depth-aware Global Query-based Network for Monocular 3D Occupancy Prediction

2025-04-10 · Xu Zhao, Pengju Zhang, Bo Liu, Yihong Wu

Monocular 3D occupancy prediction, aiming to predict the occupancy and semantics within interesting regions of 3D scenes from only 2D images, has garnered increasing attention recently for its vital role in 3D scene unde…

GPUPredictionScene Understanding