First Workshop on Photorealistic Image and Environment Synthesis
for Computer Vision (PIES-CV)

To be held as a hybrid workshop in conjunction with IEEE/CVF WACV 2023.

Promoting the synthesis of photorealistic images and virtual environments for research purposes.

Mission of the project

The First Workshop on Photorealistic Image and Environment Synthesis for Computer Vision (PIES-CV) will engage experts and researchers on the synthesis of photorealistic images and virtual environments, particularly in the form of public datasets, software tools, and infrastructures, for computer vision (CV) research. Such public datasets, software tools, and infrastructures will enable researchers to better investigate how photorealism affects CV algorithms and approaches. Photorealistic image and environment synthesis can benefit multiple research areas in addition to CV, such as machine learning, robotics, human perception, multimedia systems, and mixed reality.

Schedule

Note: PIES-CV will be held as a hybrid workshop.

Organizers

Nicholas R. Gans, University of Texas at Arlington

Ryan P. McMahan, University of Central Florida

List of Invited Speakers

Keynote Speaker

  • Angel Chang - Creating Realistic and Interactive 3D Environments

Other Invited Speakers

  • William Beksi - Synthetic 3D Datasets for Indoor Robotic Applications

  • Stefan Leutenegger - Interiornet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset

  • Matthias Nießner - The Revolution of Neural Rendering

  • Hamid Rezatofighi - Jack Rabbot Dataset and Benchmark (JRDB)

  • Katja Schwartz - 3D-aware Image Synthesis: Learning to Generate 3D Content from Images

  • Yao Yao - BlendedMVS: A Low-cost Image and Depth Synthesis Pipeline for Multi-view Geometry Learning

  • Lap-Fai (Craig) Yu and Sai-Kit Yeung - Understanding Real Scenes for Mixed Reality Applications

Examples of PIES

Matterport3D

Chang, A., Dai, A., Funkhouser, T., Halber, M., Niessner, M., Savva, M., Song, S., Zeng, A. and Zhang, Y. 2017. Matterport3d: Learning from rgb-d data in indoor environments. arXiv preprint arXiv:1709.06158. (2017).

3D-FRONT

Fu, H., Cai, B., Gao, L., Zhang, L., Li, C., Xun, Z., Sun, C., Fei, Y., Zheng, Y. and Li, Y. 2020. 3D- FRONT: 3D Furnished Rooms with layOuts and semaNTics. arXiv preprint arXiv:2011.09127. (2020).


Replica Dataset

Straub, J., Whelan, T., Ma, L., Chen, Y., Wijmans, E., Green, S., Engel, J.J., Mur-Artal, R., Ren, C. and Verma, S. 2019. The Replica dataset: A digital replica of indoor spaces. arXiv preprint arXiv:1906.05797. (2019).


Structured3D

Zheng, J., Zhang, J., Li, J., Tang, R., Gao, S. and Zhou, Z. 2019. Structured3d: A large photo- realistic dataset for structured 3d modeling. arXiv preprint arXiv:1908.00222. 2, 7 (2019).


Questions?