Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision

Depth Map Super-Resolution

3260 papers • 126 benchmarks • 313 datasets

Depth map super-resolution is the task of upsampling depth images. ( Image credit: A Joint Intensity and Depth Co-Sparse Analysis Model for Depth Map Super-Resolution )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in depth-map-super-resolution

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find depth-map-super-resolution models and implementations

Datasets

Middlebury 2005

Middlebury 2005

RGB-D-D

Subtasks

No subtasks available.

Most implemented papers

Joint convolutional neural pyramid for depth map super-resolution

Yan Zheng, Yi Xiao, Xiang Cao, Xianyi Zhu, Renzhi Yang•Tue Jan 02 2018

Experimental results show that the joint convolutional neural pyramid model with large receptive fields for joint depth map super-resolution outperforms existing state-of-the-art algorithms not only on data pairs of RGB/depth images, but also on other data pairs like color/saliency and color-scribbles/colorized images.

13

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

0

Discrete Cosine Transform Network for Guided Depth Map Super-Resolution

Jiangshe Zhang, Chunxia Zhang, Junmin Liu, Shuang Xu, Zixiang Zhao•Tue Apr 13 2021

A novel Discrete Cosine Transform Network (DCTNet) is proposed, which outperforms previous state-of-the-art methods with a relatively small number of parameters, and employs an edge attention mechanism to highlight the contours informative for guided upsampling.

129 0

Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baseline

Runmin Cong, Lingzhi He, Hongguang Zhu, Feng Li, H. Bai, Chunjie Zhang, Chunyu Lin, Meiqin Liu, Yao Zhao•Mon Apr 12 2021

This work constructs a large-scale dataset named "RGB-D-D", in which the high-frequency component adaptively decomposed from RGB image to guide the depth map SR, and provides a fast depth map super-resolution (FDSR) baseline.

108 0

Inferring Super-Resolution Depth from a Moving Light-Source Enhanced RGB-D Sensor: A Variational Approach

D. Cremers, Lu Sang, Bjoern Haefner•Thu Dec 12 2019

A novel approach towards depth map super-resolution using multi-view uncalibrated photometric stereo with nonconvex variational approach such that no calibration on lighting or camera motion is required due to the formulation of an end-to-end joint optimization problem.

12 0

Unpaired Depth Super-Resolution in the Wild

Alexey Artemov, D. Zorin, E. Burnaev, Aleksandr Safin, M. Kan, Nikita Drobyshev, Oleg Voynov, Alexander N. Filippov•Mon May 24 2021

An unpaired learning method for depth super-resolution based on a learnable degradation model and including a dedicated enhancement component which integrates surface quality measures to produce more accurate depth images is proposed.

1 0

Learning Continuous Depth Representation via Geometric Spatial Aggregator

Bingbing Ni, Xuanhong Chen, Zhengyan Tong, Xiaohang Wang, Hang Wang•Tue Dec 06 2022

This work proposes a novel continuous depth representation for DSR, which exploits a distance field modulated by arbitrarily upsampled target gridding, through which the geometric information is explicitly introduced into feature aggregation and target generation.

13 0

Guided Depth Map Super-Resolution: A Survey

Xiangyang Ji, Debin Zhao, Junjun Jiang, Xianming Liu, Zhiwei Zhong•Thu Feb 16 2023

A comprehensive survey of recent progress in guided depth map super-resolution (GDSR), which aims to reconstruct a high-resolution depth map from a low-resolution observation with the help of a paired high- resolution color image, is presented.

54 0

Deformable Kernel Networks for Joint Image Filtering

J. Ponce, Bumsub Ham, Beomjun Kim•Wed Oct 16 2019

A CNN architecture and its efficient implementation, called the deformable kernel network (DKN), that outputs sets of neighbors and the corresponding weights adaptively for each pixel is proposed that outperforms the state of the art by a significant margin in all cases.

161 0

High-resolution Depth Maps Imaging via Attention-based Hierarchical Multi-modal Fusion

Xiangyang Ji, Junjun Jiang, Debin Zhao, Zhiwei Zhong, Xianming Liu, Zhiwen Chen•Sat Apr 03 2021

To effectively extract and combine relevant information from LR depth and HR guidance, a multi-modal attention based fusion (MMAF) strategy for hierarchical convolutional layers, including a feature enhancement block to select valuable features and a feature recalibration block to unify the similarity metrics of modalities with different appearance characteristics are proposed.

63 0

Deep Attentional Guided Image Filtering

Xiangyang Ji, Debin Zhao, Junjun Jiang, Zhiwei Zhong, Xianming Liu•Sun Dec 12 2021

This work proposes an attentional kernel learning module to generate dual sets of filter kernels from the guidance and the target and then adaptively combine them by modeling the pixelwise dependency between the two images.

47 0

Adding a benchmark result helps the community track progress.

Depth Map Super-Resolution | State-of-the-Art