Qing Ran
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Qing Ran has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Edward Yang
Department of Computer Science and Engineering, University of California, La Jolla, CA, USA
1 shared publication - Guangyuan Wang
Tongyi Lab, Alibaba, Hangzhou, China
1 shared publication - Hao Su
University of California San Diego, San Diego, USA
1 shared publication - Isabella Liu
University of California San Diego, La Jolla, USA
1 shared publication - Jianyu Tao
Department of Computer Science and Engineering, University of California, La Jolla, CA, USA
1 shared publication - Jieqing Feng
State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China
1 shared publication
Latest Publications
- Open Access
- 21 August 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 42 (5) , 1-15
High-Resolution Volumetric Reconstruction for Clothed Humans
We present a novel method for reconstructing clothed humans from a sparse set of, e.g., 1–6 RGB images. Despite impressive results from recent works employing deep implicit representation, we revisit the volumetric approach and demonstrate that better performance can be achieved with proper system design. The volumetric representation offers significant advantages in leveraging 3D spatial context through 3D convolutions, and the notorious quantization error is largely negligible with a reasonably large yet affordable volume resolution, e.g., 512. To handle memory and computation costs, we propose a sophisticated coarse-to-fine strategy with voxel culling and subspace sparse convolution. Our method starts with a discretized visual hull to compute a coarse shape and then focuses on a narrow band nearby the coarse shape for refinement. Once the shape is reconstructed, we adopt an image-based rendering approach, which computes the colors of surface points by blending input images with learned weights. Extensive experimental results show that our method significantly reduces the mean point-to-surface (P2S) precision of state-of-the-art methods by more than 50% to achieve approximately 2mm accuracy with a 512 volume resolution. Additionally, images rendered from our textured model achieve a higher peak signal-to-noise ratio (PSNR) compared to state-of-the-art methods.
- 21 August 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 42 (5) , 1-15
Open AccessHigh-Resolution Volumetric Reconstruction for Clothed Humans
We present a novel method for reconstructing clothed humans from a sparse set of, e.g., 1–6 RGB images. Despite impressive results from recent works employing deep implicit representation, we revisit the volumetric approach and demonstrate that better performance can be achieved with proper system design. The volumetric representation offers significant advantages in leveraging 3D spatial context through 3D convolutions, and the notorious quantization error is largely negligible with a reasonably large yet affordable volume resolution, e.g., 512. To handle memory and computation costs, we propose a sophisticated coarse-to-fine strategy with voxel culling and subspace sparse convolution. Our method starts with a discretized visual hull to compute a coarse shape and then focuses on a narrow band nearby the coarse shape for refinement. Once the shape is reconstructed, we adopt an image-based rendering approach, which computes the colors of surface points by blending input images with learned weights. Extensive experimental results show that our method significantly reduces the mean point-to-surface (P2S) precision of state-of-the-art methods by more than 50% to achieve approximately 2mm accuracy with a 512 volume resolution. Additionally, images rendered from our textured model achieve a higher peak signal-to-noise ratio (PSNR) compared to state-of-the-art methods.
- 15 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (12) , 14098-14113
ActiveZero++: Mixed Domain Learning Stereo and Confidence-Based Depth Completion With Zero Annotation
Learning-based stereo methods usually require a large scale dataset with depth, however obtaining accurate depth in the real domain is difficult, but groundtruth depth is readily available in the simulation domain. In this article we propose a new framework, ActiveZero++, which is a mixed domain learning solution for active stereovision systems that requires no real world depth annotation. In the simulation domain, we use a combination of supervised disparity loss and self-supervised loss on a shape primitives dataset. By contrast, in the real domain, we only use self-supervised loss on a dataset that is out-of-distribution from either training simulation data or test real data. To improve the robustness and accuracy of our reprojection loss in hard-to-perceive regions, our method introduces a novel self-supervised loss called temporal IR reprojection. Further, we propose the confidence-based depth completion module, which uses the confidence from the stereo network to identify and improve erroneous areas in depth prediction through depth-normal consistency. Extensive qualitative and quantitative evaluations on real-world data demonstrate state-of-the-art results that can even outperform a commercial depth sensor. Furthermore, our method can significantly narrow the Sim2Real domain gap of depth maps for state-of-the-art learning based 6D pose estimation algorithms.
- 15 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (12) , 14098-14113
ActiveZero++: Mixed Domain Learning Stereo and Confidence-Based Depth Completion With Zero Annotation
Learning-based stereo methods usually require a large scale dataset with depth, however obtaining accurate depth in the real domain is difficult, but groundtruth depth is readily available in the simulation domain. In this article we propose a new framework, ActiveZero++, which is a mixed domain learning solution for active stereovision systems that requires no real world depth annotation. In the simulation domain, we use a combination of supervised disparity loss and self-supervised loss on a shape primitives dataset. By contrast, in the real domain, we only use self-supervised loss on a dataset that is out-of-distribution from either training simulation data or test real data. To improve the robustness and accuracy of our reprojection loss in hard-to-perceive regions, our method introduces a novel self-supervised loss called temporal IR reprojection. Further, we propose the confidence-based depth completion module, which uses the confidence from the stereo network to identify and improve erroneous areas in depth prediction through depth-normal consistency. Extensive qualitative and quantitative evaluations on real-world data demonstrate state-of-the-art results that can even outperform a commercial depth sensor. Furthermore, our method can significantly narrow the Sim2Real domain gap of depth maps for state-of-the-art learning based 6D pose estimation algorithms.
- 1 August 2019
- Published by Elsevier in Computers & Graphics
- Vol. 82, 22-31
Intrinsic color correction for stereo matching
- 1 August 2019
- Published by Elsevier in Computers & Graphics
- Vol. 82, 22-31
Intrinsic color correction for stereo matching