• Home
  • Search
  • A Two-Streamed Network for Estimating Fine-Scaled Depth Maps from Single RGB Images
  • Open Access IconOpen Access
  • Cite Icon320
  • https://doi.org/10.1109/iccv.2017.365Copy DOI Icon

A Two-Streamed Network for Estimating Fine-Scaled Depth Maps from Single RGB Images

  • Oct 1, 2017
  • Jun Li +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Estimating depth from a single RGB image is an ill-posed and inherently ambiguous problem. State-of-the-art deep learning methods can now estimate accurate 2D depth maps, but when the maps are projected into 3D, they lack local detail and are often highly distorted. We propose a fast-to-train two-streamed CNN that predicts depth and depth gradients, which are then fused together into an accurate and detailed depth map. We also define a novel set loss over multiple images; by regularizing the estimation between a common set of images, the network is less prone to overfitting and achieves better accuracy than competing methods. Experiments on the NYU Depth v2 dataset shows that our depth predictions are competitive with state-of-the-art and lead to faithful 3D projections.

Similar Papers
  • Conference Article
  • Citations2

Non-essentiality of correlation between image and depth map in free viewpoint image coding: Accurate depth map case

  • Jul 01, 2014
  • Tomohiko Inoue +2
  • Research Article

EDRNet: Edge-Enhanced Dynamic Routing Adaptive for Depth Completion

  • Mar 13, 2025
  • Mathematics
  • Fuyun Sun +2
  • Research Article
  • Citations8

Learning to Reconstruct and Understand Indoor Scenes From Sparse Views.

  • Jan 01, 2020
  • IEEE Transactions on Image Processing
  • Jingyu Yang +7
  • Book Chapter

CNN Approach for Monocular Depth Estimation: Ear Case Study

  • Dec 01, 2021
  • Roberto Magherini +5
  • PDF
  • Research Article
  • Citations8

Encoder-Decoder Structure With the Feature Pyramid for Depth Estimation From a Single Image

  • Jan 01, 2021
  • IEEE Access
  • Mengxia Tang +3
  • Research Article
  • Citations13

Multi-stage cascaded deconvolution for depth map and surface normal prediction from single image

  • Jul 06, 2018
  • Pattern Recognition Letters
  • Ram Prasad Padhy +4
  • Conference Article
  • Citations9

An iterative, non-local approach for restoring depth maps in RGB-D images

  • Feb 01, 2015
  • Akash Bapat +2
  • Conference Article
  • Citations5

Real-time stereo matching for depth estimation using GPU

  • Aug 01, 2015
  • Fang-Hsuan Cheng +1
  • Research Article
  • Citations44

Generation of high-quality depth maps using hybrid camera system for 3-D video

  • Oct 25, 2010
  • Journal of Visual Communication and Image Representation
  • Eun-Kyung Lee +1
  • PDF
  • Research Article
  • Citations7

Lightweight and Energy-Aware Monocular Depth Estimation Models for IoT Embedded Devices: Challenges and Performances in Terrestrial and Underwater Scenarios †

  • Feb 16, 2023
  • Sensors (Basel, Switzerland)
  • Lorenzo Papa +4
  • Conference Article

Self-Supervised Monocular Depth Estimation Based on Dual-Branch DepthNet and Multi-Attention Fusion

  • Jan 01, 2025
  • Yuanyuan Wang
  • Conference Article
  • Citations4

MonoSOD: Monocular Salient Object Detection based on Predicted Depth

  • May 30, 2021
  • George Dimas +2
  • PDF
  • Research Article
  • Citations46

Deep Architecture With Cross Guidance Between Single Image and Sparse LiDAR Data for Depth Completion

  • Jan 01, 2020
  • IEEE Access
  • Sihaeng Lee +3
  • Conference Article
  • Citations8

Hole correction in estimated depth map from single image using color uniformity principle

  • Aug 01, 2017
  • Himanshu Kumar +2
  • Research Article
  • Citations28

Monocular depth estimation with guidance of surface normal map

  • Nov 24, 2017
  • Neurocomputing
  • Han Yan +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.