English
Related papers

Related papers: DoubleTake: Geometry Guided Depth Estimation

200 papers

The dual-pixel (DP) hardware works by splitting each pixel in half and creating an image pair in a single snapshot. Several works estimate depth/inverse depth by treating the DP pair as a stereo pair. However, dual-pixel disparity only…

Computer Vision and Pattern Recognition · Computer Science 2020-12-02 Liyuan Pan , Shah Chowdhury , Richard Hartley , Miaomiao Liu , Hongguang Zhang , Hongdong Li

Despite significant progress made in the past few years, challenges remain for depth estimation using a single monocular image. First, it is nontrivial to train a metric-depth prediction model that can generalize well to diverse scenes…

Computer Vision and Pattern Recognition · Computer Science 2022-09-07 Wei Yin , Jianming Zhang , Oliver Wang , Simon Niklaus , Simon Chen , Yifan Liu , Chunhua Shen

3D reconstruction from a single RGB image is a challenging problem in computer vision. Previous methods are usually solely data-driven, which lead to inaccurate 3D shape recovery and limited generalization capability. In this work, we focus…

Computer Vision and Pattern Recognition · Computer Science 2020-06-18 Yichao Zhou , Shichen Liu , Yi Ma

We explore 3D human pose estimation from a single RGB image. While many approaches try to directly predict 3D pose from image measurements, we explore a simple architecture that reasons through intermediate 2D pose predictions. Our approach…

Computer Vision and Pattern Recognition · Computer Science 2017-04-12 Ching-Hang Chen , Deva Ramanan

We present 3DMV, a novel method for 3D semantic scene segmentation of RGB-D scans in indoor environments using a joint 3D-multi-view prediction network. In contrast to existing methods that either use geometry or RGB data as input for this…

Computer Vision and Pattern Recognition · Computer Science 2018-03-29 Angela Dai , Matthias Nießner

Computational stereo has reached a high level of accuracy, but degrades in the presence of occlusions, repeated textures, and correspondence errors along edges. We present a novel approach based on neural networks for depth estimation that…

Computer Vision and Pattern Recognition · Computer Science 2020-04-01 Yinda Zhang , Neal Wadhwa , Sergio Orts-Escolano , Christian Häne , Sean Fanello , Rahul Garg

Depth ambiguity is a fundamental challenge in spatial scene understanding, especially in transparent scenes where single-depth estimates fail to capture full 3D structure. Existing models, limited to deterministic predictions, overlook…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Xiaohao Xu , Feng Xue , Xiang Li , Haowei Li , Shusheng Yang , Tianyi Zhang , Matthew Johnson-Roberson , Xiaonan Huang

We present a new learning-based method for multi-frame depth estimation from a color video, which is a fundamental problem in scene understanding, robot navigation or handheld 3D reconstruction. While recent learning-based methods estimate…

Computer Vision and Pattern Recognition · Computer Science 2021-07-13 Xiaoxiao Long , Lingjie Liu , Christian Theobalt , Wenping Wang

We propose a method at the intersection of Computer Vision and Computer Graphics fields, which automatically generates RGBD images using neural networks, based on previously seen and synchronized video, depth and pose signals. Since the…

Computer Vision and Pattern Recognition · Computer Science 2020-07-15 Mihai Cristian Pîrvu

Inferring a meaningful geometric scene representation from a single image is a fundamental problem in computer vision. Approaches based on traditional depth map prediction can only reason about areas that are visible in the image.…

Computer Vision and Pattern Recognition · Computer Science 2023-04-20 Felix Wimbauer , Nan Yang , Christian Rupprecht , Daniel Cremers

Language-guided grasping has emerged as a promising paradigm for enabling robots to identify and manipulate target objects through natural language instructions, yet it remains highly challenging in cluttered or occluded scenes. Existing…

Robotics · Computer Science 2026-02-05 Rui Tang , Guankun Wang , Long Bai , Huxin Gao , Jiewen Lai , Chi Kit Ng , Jiazheng Wang , Fan Zhang , Hongliang Ren

Self-supervised deep learning methods have leveraged stereo images for training monocular depth estimation. Although these methods show strong results on outdoor datasets such as KITTI, they do not match performance of supervised methods on…

Computer Vision and Pattern Recognition · Computer Science 2021-06-28 Benjamin Keltjens , Tom van Dijk , Guido de Croon

RGB-D scene parsing methods effectively capture both semantic and geometric features of the environment, demonstrating great potential under challenging conditions such as extreme weather and low lighting. However, existing RGB-D scene…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Jianxin Huang , Jiahang Li , Sergey Vityazev , Alexander Dvorkovich , Rui Fan

Multimodal Large Language Models (MLLMs) demonstrate exceptional semantic reasoning but struggle with 3D spatial perception when restricted to pure RGB inputs. Despite leveraging implicit geometric priors from 3D reconstruction models,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Jiaxin Zhang , Junjun Jiang , Haijie Li , Youyu Chen , Kui Jiang , Dave Zhenyu Chen

Monocular Metric Depth Estimation (MMDE) is essential for physically intelligent systems, yet accurate depth estimation for underrepresented classes in complex scenes remains a persistent challenge. To address this, we propose RAD, a…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Michael Baltaxe , Dan Levi , Sagie Benaim

Existing deep learning-based image inpainting methods typically rely on convolutional networks with RGB images to reconstruct images. However, relying exclusively on RGB images may neglect important depth information, which plays a critical…

Image and Video Processing · Electrical Eng. & Systems 2025-05-09 Jin Hyun Park , Harine Choi , Praewa Pitiphat

Leveraging 3D information within Multimodal Large Language Models (MLLMs) has recently shown significant advantages for indoor scene understanding. However, existing methods, including those using explicit ground-truth 3D positional…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Chushan Zhang , Ruihan Lu , Jinguang Tong , Yikai Wang , Hongdong Li

Human pose estimation (i.e., locating the body parts / joints of a person) is a fundamental problem in human-computer interaction and multimedia applications. Significant progress has been made based on the development of depth sensors,…

Computer Vision and Pattern Recognition · Computer Science 2016-08-16 Keze Wang , Shengfu Zhai , Hui Cheng , Xiaodan Liang , Liang Lin

Modern scene reconstruction methods are able to accurately recover 3D surfaces that are visible in one or more images. However, this leads to incomplete reconstructions, missing all occluded surfaces. While much progress has been made on…

Computer Vision and Pattern Recognition · Computer Science 2025-11-07 Sam Bahrami , Dylan Campbell

This paper studies unsupervised monocular depth prediction problem. Most of existing unsupervised depth prediction algorithms are developed for outdoor scenarios, while the depth prediction work in the indoor environment is still very…

Computer Vision and Pattern Recognition · Computer Science 2019-11-21 Yinglong Feng , Shuncheng Wu , Okan Köpüklü , Xueyang Kang , Federico Tombari