File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering

TitleDNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering
Authors
Issue Date2023
Citation
Proceedings of the IEEE International Conference on Computer Vision, 2023, p. 19925-19936 How to Cite?
AbstractRealistic human-centric rendering plays a key role in both computer vision and computer graphics. Rapid progress has been made in the algorithm aspect over the years, yet existing human-centric rendering datasets and benchmarks are rather impoverished in terms of diversity (e.g., outfit's fabric/material, body's interaction with objects, and motion sequences), which are crucial for rendering effect. Researchers are usually constrained to explore and evaluate a small set of rendering problems on current datasets, while real-world applications require methods to be robust across different scenarios. In this work, we present DNA-Rendering, a large-scale, high-fidelity repository of human performance data for neural actor rendering. DNA-Rendering presents several appealing attributes. First, our dataset contains over 1500 human subjects, 5000 motion sequences, and 67.5M frames' data volume. Upon the massive collections, we provide human subjects with grand categories of pose actions, body shapes, clothing, accessories, hairdos, and object intersection, which ranges the geometry and appearance variances from everyday life to professional occasions. Second, we provide rich assets for each subject - 2D/3D human body keypoints, foreground masks, SMPLX models, cloth/accessory materials, multi-view images, and videos. These assets boost the current method's accuracy on downstream rendering tasks. Third, we construct a professional multi-view system to capture data, which contains 60 synchronous cameras with max 4096 × 3000 resolution, 15 fps speed, and stern camera calibration steps, ensuring high-quality resources for task training and evaluation.Along with the dataset, we provide a large-scale and quantitative benchmark in full-scale, with multiple tasks to evaluate the existing progress of novel view synthesis, novel pose animation synthesis, and novel identity rendering methods. In this manuscript, we describe our DNA-Rendering effort as a revealing of new observations, challenges, and future directions to human-centric rendering. The dataset, code, and benchmarks will be publicly available at https://dna-rendering.github.io/.
Persistent Identifierhttp://hdl.handle.net/10722/352381
ISSN
2023 SCImago Journal Rankings: 12.263

 

DC FieldValueLanguage
dc.contributor.authorCheng, Wei-
dc.contributor.authorChen, Ruixiang-
dc.contributor.authorFan, Siming-
dc.contributor.authorYin, Wanqi-
dc.contributor.authorChen, Keyu-
dc.contributor.authorCai, Zhongang-
dc.contributor.authorWang, Jingbo-
dc.contributor.authorGao, Yang-
dc.contributor.authorYu, Zhengming-
dc.contributor.authorLin, Zhengyu-
dc.contributor.authorRen, Daxuan-
dc.contributor.authorYang, Lei-
dc.contributor.authorLiu, Ziwei-
dc.contributor.authorLoy, Chen Change-
dc.contributor.authorQian, Chen-
dc.contributor.authorWu, Wayne-
dc.contributor.authorLin, Dahua-
dc.contributor.authorDai, Bo-
dc.contributor.authorLin, Kwan Yee-
dc.date.accessioned2024-12-16T03:58:35Z-
dc.date.available2024-12-16T03:58:35Z-
dc.date.issued2023-
dc.identifier.citationProceedings of the IEEE International Conference on Computer Vision, 2023, p. 19925-19936-
dc.identifier.issn1550-5499-
dc.identifier.urihttp://hdl.handle.net/10722/352381-
dc.description.abstractRealistic human-centric rendering plays a key role in both computer vision and computer graphics. Rapid progress has been made in the algorithm aspect over the years, yet existing human-centric rendering datasets and benchmarks are rather impoverished in terms of diversity (e.g., outfit's fabric/material, body's interaction with objects, and motion sequences), which are crucial for rendering effect. Researchers are usually constrained to explore and evaluate a small set of rendering problems on current datasets, while real-world applications require methods to be robust across different scenarios. In this work, we present DNA-Rendering, a large-scale, high-fidelity repository of human performance data for neural actor rendering. DNA-Rendering presents several appealing attributes. First, our dataset contains over 1500 human subjects, 5000 motion sequences, and 67.5M frames' data volume. Upon the massive collections, we provide human subjects with grand categories of pose actions, body shapes, clothing, accessories, hairdos, and object intersection, which ranges the geometry and appearance variances from everyday life to professional occasions. Second, we provide rich assets for each subject - 2D/3D human body keypoints, foreground masks, SMPLX models, cloth/accessory materials, multi-view images, and videos. These assets boost the current method's accuracy on downstream rendering tasks. Third, we construct a professional multi-view system to capture data, which contains 60 synchronous cameras with max 4096 × 3000 resolution, 15 fps speed, and stern camera calibration steps, ensuring high-quality resources for task training and evaluation.Along with the dataset, we provide a large-scale and quantitative benchmark in full-scale, with multiple tasks to evaluate the existing progress of novel view synthesis, novel pose animation synthesis, and novel identity rendering methods. In this manuscript, we describe our DNA-Rendering effort as a revealing of new observations, challenges, and future directions to human-centric rendering. The dataset, code, and benchmarks will be publicly available at https://dna-rendering.github.io/.-
dc.languageeng-
dc.relation.ispartofProceedings of the IEEE International Conference on Computer Vision-
dc.titleDNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/ICCV51070.2023.01829-
dc.identifier.scopuseid_2-s2.0-85169059029-
dc.identifier.spage19925-
dc.identifier.epage19936-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats