Compressed Depth Map Super-Resolution and Restoration: AIM 2024 Challenge Results

Marcos V. Conde; Florin Alexandru Vasluianu; Jinhui Xiong; Wei Ye; Rakesh Ranjan; Radu Timofte; Huan Zheng; Wencheng Han; Tianyi Yan; Jianbing Shen; Pihai Sun; Yuanqi Yao; Kui Jiang; Wenbo Zhao; Xianming Liu; Evgeny Burnaev; Junjun Jiang; Woojae Han; Kyeonghyun Lee; Seongmin Hong; Se Young Chun; Jinseong Kim; Dohyeong Kim; Jeahwan Kim; Yubo Wang; Chi Zhang; Huizhen Luo; Yansai Wu; Mengcheng Huang; Chengji Liu; Chongli Yve; Jianhang Sun; Cheng Guo; Yingcai Du; Huang Jianhao; Liu Shuai; Li Chenghua

doi:10.1007/978-3-031-91856-8_17

Compressed Depth Map Super-Resolution and Restoration: AIM 2024 Challenge Results

Marcos V. Conde^*
, Florin Alexandru Vasluianu
, Jinhui Xiong
, Wei Ye
, Rakesh Ranjan
, Radu Timofte
, Huan Zheng
, Wencheng Han
, Tianyi Yan
, Jianbing Shen
, Pihai Sun
, Yuanqi Yao
, Kui Jiang
, Wenbo Zhao
, Xianming Liu
, Evgeny Burnaev
, Junjun Jiang
, Woojae Han
, Kyeonghyun Lee
, Seongmin Hong

Se Young Chun, Jinseong Kim, Dohyeong Kim, Jeahwan Kim, Yubo Wang, Chi Zhang, Huizhen Luo, Yansai Wu, Mengcheng Huang, Chengji Liu, Chongli Yve, Jianhang Sun, Cheng Guo, Yingcai Du, Huang Jianhao, Liu Shuai, Li Chenghua

^*Corresponding author for this work

University of Würzburg
Sony PlayStation
Meta Reality Labs

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The increasing demand for augmented reality (AR) and virtual reality (VR) applications highlights the need for efficient depth information processing. Depth maps, essential for rendering realistic scenes and supporting advanced functionalities, are typically large and challenging to stream efficiently due to their size. This challenge introduces a focus on developing innovative depth upsampling techniques to reconstruct high-quality depth maps from compressed data. These techniques are crucial for overcoming the limitations posed by depth compression, which often degrades quality, loses scene details and introduces artifacts. By enhancing depth upsampling methods, this challenge aims to improve the efficiency and quality of depth map reconstruction. Our goal is to advance the state-of-the-art in depth processing technologies, thereby enhancing the overall user experience in AR and VR applications.

Original language	English
Title of host publication	Computer Vision – ECCV 2024 Workshops, Proceedings
Editors	Alessio Del Bue, Cristian Canton, Jordi Pont-Tuset, Tatiana Tommasi
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	287-303
Number of pages	17
ISBN (Print)	9783031918551
DOIs	https://doi.org/10.1007/978-3-031-91856-8_17
State	Published - 2025
Externally published	Yes
Event	Workshops that were held in conjunction with the 18th European Conference on Computer Vision, ECCV 2024 - Milan, Italy Duration: 29 Sep 2024 → 4 Oct 2024

Publication series

Name	Lecture Notes in Computer Science
Volume	15632 LNCS
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	Workshops that were held in conjunction with the 18th European Conference on Computer Vision, ECCV 2024
Country/Territory	Italy
City	Milan
Period	29/09/24 → 4/10/24

Access to Document

10.1007/978-3-031-91856-8_17

Cite this

Conde, M. V., Vasluianu, F. A., Xiong, J., Ye, W., Ranjan, R., Timofte, R., Zheng, H., Han, W., Yan, T., Shen, J., Sun, P., Yao, Y., Jiang, K., Zhao, W., Liu, X., Burnaev, E., Jiang, J., Han, W., Lee, K., ... Chenghua, L. (2025). Compressed Depth Map Super-Resolution and Restoration: AIM 2024 Challenge Results. In A. Del Bue, C. Canton, J. Pont-Tuset, & T. Tommasi (Eds.), Computer Vision – ECCV 2024 Workshops, Proceedings (pp. 287-303). (Lecture Notes in Computer Science; Vol. 15632 LNCS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-91856-8_17

Conde, Marcos V. ; Vasluianu, Florin Alexandru ; Xiong, Jinhui et al. / Compressed Depth Map Super-Resolution and Restoration : AIM 2024 Challenge Results. Computer Vision – ECCV 2024 Workshops, Proceedings. editor / Alessio Del Bue ; Cristian Canton ; Jordi Pont-Tuset ; Tatiana Tommasi. Springer Science and Business Media Deutschland GmbH, 2025. pp. 287-303 (Lecture Notes in Computer Science).

@inproceedings{b472124ae99940f09ff44e85f783bac1,

title = "Compressed Depth Map Super-Resolution and Restoration: AIM 2024 Challenge Results",

abstract = "The increasing demand for augmented reality (AR) and virtual reality (VR) applications highlights the need for efficient depth information processing. Depth maps, essential for rendering realistic scenes and supporting advanced functionalities, are typically large and challenging to stream efficiently due to their size. This challenge introduces a focus on developing innovative depth upsampling techniques to reconstruct high-quality depth maps from compressed data. These techniques are crucial for overcoming the limitations posed by depth compression, which often degrades quality, loses scene details and introduces artifacts. By enhancing depth upsampling methods, this challenge aims to improve the efficiency and quality of depth map reconstruction. Our goal is to advance the state-of-the-art in depth processing technologies, thereby enhancing the overall user experience in AR and VR applications.",

author = "Conde, \{Marcos V.\} and Vasluianu, \{Florin Alexandru\} and Jinhui Xiong and Wei Ye and Rakesh Ranjan and Radu Timofte and Huan Zheng and Wencheng Han and Tianyi Yan and Jianbing Shen and Pihai Sun and Yuanqi Yao and Kui Jiang and Wenbo Zhao and Xianming Liu and Evgeny Burnaev and Junjun Jiang and Woojae Han and Kyeonghyun Lee and Seongmin Hong and Chun, \{Se Young\} and Jinseong Kim and Dohyeong Kim and Jeahwan Kim and Yubo Wang and Chi Zhang and Huizhen Luo and Yansai Wu and Mengcheng Huang and Chengji Liu and Chongli Yve and Jianhang Sun and Cheng Guo and Yingcai Du and Huang Jianhao and Liu Shuai and Li Chenghua",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.; Workshops that were held in conjunction with the 18th European Conference on Computer Vision, ECCV 2024 ; Conference date: 29-09-2024 Through 04-10-2024",

year = "2025",

doi = "10.1007/978-3-031-91856-8\_17",

language = "英语",

isbn = "9783031918551",

series = "Lecture Notes in Computer Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "287--303",

editor = "\{Del Bue\}, Alessio and Cristian Canton and Jordi Pont-Tuset and Tatiana Tommasi",

booktitle = "Computer Vision – ECCV 2024 Workshops, Proceedings",

address = "德国",

}

Conde, MV, Vasluianu, FA, Xiong, J, Ye, W, Ranjan, R, Timofte, R, Zheng, H, Han, W, Yan, T, Shen, J, Sun, P, Yao, Y, Jiang, K , Zhao, W, Liu, X, Burnaev, E, Jiang, J, Han, W, Lee, K, Hong, S, Chun, SY, Kim, J, Kim, D, Kim, J, Wang, Y, Zhang, C, Luo, H, Wu, Y, Huang, M, Liu, C, Yve, C, Sun, J, Guo, C, Du, Y, Jianhao, H, Shuai, L & Chenghua, L 2025, Compressed Depth Map Super-Resolution and Restoration: AIM 2024 Challenge Results. in A Del Bue, C Canton, J Pont-Tuset & T Tommasi (eds), Computer Vision – ECCV 2024 Workshops, Proceedings. Lecture Notes in Computer Science, vol. 15632 LNCS, Springer Science and Business Media Deutschland GmbH, pp. 287-303, Workshops that were held in conjunction with the 18th European Conference on Computer Vision, ECCV 2024, Milan, Italy, 29/09/24. https://doi.org/10.1007/978-3-031-91856-8_17

Compressed Depth Map Super-Resolution and Restoration: AIM 2024 Challenge Results. / Conde, Marcos V.; Vasluianu, Florin Alexandru; Xiong, Jinhui et al.
Computer Vision – ECCV 2024 Workshops, Proceedings. ed. / Alessio Del Bue; Cristian Canton; Jordi Pont-Tuset; Tatiana Tommasi. Springer Science and Business Media Deutschland GmbH, 2025. p. 287-303 (Lecture Notes in Computer Science; Vol. 15632 LNCS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Compressed Depth Map Super-Resolution and Restoration

T2 - Workshops that were held in conjunction with the 18th European Conference on Computer Vision, ECCV 2024

AU - Conde, Marcos V.

AU - Vasluianu, Florin Alexandru

AU - Xiong, Jinhui

AU - Ye, Wei

AU - Ranjan, Rakesh

AU - Timofte, Radu

AU - Zheng, Huan

AU - Han, Wencheng

AU - Yan, Tianyi

AU - Shen, Jianbing

AU - Sun, Pihai

AU - Yao, Yuanqi

AU - Jiang, Kui

AU - Zhao, Wenbo

AU - Liu, Xianming

AU - Burnaev, Evgeny

AU - Jiang, Junjun

AU - Han, Woojae

AU - Lee, Kyeonghyun

AU - Hong, Seongmin

AU - Chun, Se Young

AU - Kim, Jinseong

AU - Kim, Dohyeong

AU - Kim, Jeahwan

AU - Wang, Yubo

AU - Zhang, Chi

AU - Luo, Huizhen

AU - Wu, Yansai

AU - Huang, Mengcheng

AU - Liu, Chengji

AU - Yve, Chongli

AU - Sun, Jianhang

AU - Guo, Cheng

AU - Du, Yingcai

AU - Jianhao, Huang

AU - Shuai, Liu

AU - Chenghua, Li

PY - 2025

Y1 - 2025

N2 - The increasing demand for augmented reality (AR) and virtual reality (VR) applications highlights the need for efficient depth information processing. Depth maps, essential for rendering realistic scenes and supporting advanced functionalities, are typically large and challenging to stream efficiently due to their size. This challenge introduces a focus on developing innovative depth upsampling techniques to reconstruct high-quality depth maps from compressed data. These techniques are crucial for overcoming the limitations posed by depth compression, which often degrades quality, loses scene details and introduces artifacts. By enhancing depth upsampling methods, this challenge aims to improve the efficiency and quality of depth map reconstruction. Our goal is to advance the state-of-the-art in depth processing technologies, thereby enhancing the overall user experience in AR and VR applications.

AB - The increasing demand for augmented reality (AR) and virtual reality (VR) applications highlights the need for efficient depth information processing. Depth maps, essential for rendering realistic scenes and supporting advanced functionalities, are typically large and challenging to stream efficiently due to their size. This challenge introduces a focus on developing innovative depth upsampling techniques to reconstruct high-quality depth maps from compressed data. These techniques are crucial for overcoming the limitations posed by depth compression, which often degrades quality, loses scene details and introduces artifacts. By enhancing depth upsampling methods, this challenge aims to improve the efficiency and quality of depth map reconstruction. Our goal is to advance the state-of-the-art in depth processing technologies, thereby enhancing the overall user experience in AR and VR applications.

UR - https://www.scopus.com/pages/publications/105006923480

U2 - 10.1007/978-3-031-91856-8_17

DO - 10.1007/978-3-031-91856-8_17

M3 - 会议稿件

AN - SCOPUS:105006923480

SN - 9783031918551

T3 - Lecture Notes in Computer Science

SP - 287

EP - 303

BT - Computer Vision – ECCV 2024 Workshops, Proceedings

A2 - Del Bue, Alessio

A2 - Canton, Cristian

A2 - Pont-Tuset, Jordi

A2 - Tommasi, Tatiana

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 29 September 2024 through 4 October 2024

ER -

Conde MV, Vasluianu FA, Xiong J, Ye W, Ranjan R, Timofte R et al. Compressed Depth Map Super-Resolution and Restoration: AIM 2024 Challenge Results. In Del Bue A, Canton C, Pont-Tuset J, Tommasi T, editors, Computer Vision – ECCV 2024 Workshops, Proceedings. Springer Science and Business Media Deutschland GmbH. 2025. p. 287-303. (Lecture Notes in Computer Science). doi: 10.1007/978-3-031-91856-8_17