Xiaolong Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Xiaolong Wu has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Ang Li
Pacific Northwest National Laboratory
1 shared publication - Aravind Machiry
Purdue University, West Lafayette, USA
1 shared publication - Dave (Jing) Tian
Purdue University
1 shared publication - Heather Yu
Futurewei Technologies Stony Futurewei Technologies Futurewei Technologies Futurewei Technologies Futurewei Technologies Futurewei Technologies Stony Futurewei Technologies Futurewei Technologies Futurewei Technologies Technologies Stony Brook University Brook University Purdue University University of Southern California Purdue University George Mason University Brook University Stony Brook University
1 shared publication - Jiajia Li
North Carolina State University, Raleigh, USA
1 shared publication - Jiazhi Li
Futurewei Technologies Stony Futurewei Technologies Futurewei Technologies Futurewei Technologies Futurewei Technologies Futurewei Technologies Stony Futurewei Technologies Futurewei Technologies Futurewei Technologies Technologies Stony Brook University Brook University Purdue University University of Southern California Purdue University George Mason University Brook University Stony Brook University
1 shared publication
Latest Publications
- Open Access
Inverse Rendering for High-Genus Surface Meshes from Multi-View Images
We present a topology-informed inverse rendering approach for reconstructing high-genus surface meshes from multi-view images. Compared to 3D representations like voxels and point clouds, mesh-based representations are preferred as they enable the application of differential geometry theory and are optimized for modern graphics pipelines. However, existing inverse rendering methods often fail catastrophically on high-genus surfaces, leading to the loss of key topological features, and tend to oversmooth low-genus surfaces, resulting in the loss of surface details. This failure stems from their overreliance on Adam-based optimizers, which can lead to vanishing and exploding gradients. To overcome these challenges, we introduce an adaptive V-cycle remeshing scheme in conjunction with a re-parametrized Adam optimizer to enhance topological and geometric awareness. By periodically coarsening and refining the deforming mesh, our method informs mesh vertices of their current topology and geometry before optimization, mitigating gradient issues while preserving essential topological features. Additionally, we enforce topological consistency by constructing topological primitives with genus numbers that match those of ground truth using Gauss-Bonnet theorem. Experimental results demonstrate that our inverse rendering approach outperforms the current state-of-the-art method, achieving significant improvements in Chamfer Distance and Volume IoU, particularly for high-genus surfaces, while also enhancing surface details for low-genus surfaces.
Open AccessInverse Rendering for High-Genus Surface Meshes from Multi-View Images
We present a topology-informed inverse rendering approach for reconstructing high-genus surface meshes from multi-view images. Compared to 3D representations like voxels and point clouds, mesh-based representations are preferred as they enable the application of differential geometry theory and are optimized for modern graphics pipelines. However, existing inverse rendering methods often fail catastrophically on high-genus surfaces, leading to the loss of key topological features, and tend to oversmooth low-genus surfaces, resulting in the loss of surface details. This failure stems from their overreliance on Adam-based optimizers, which can lead to vanishing and exploding gradients. To overcome these challenges, we introduce an adaptive V-cycle remeshing scheme in conjunction with a re-parametrized Adam optimizer to enhance topological and geometric awareness. By periodically coarsening and refining the deforming mesh, our method informs mesh vertices of their current topology and geometry before optimization, mitigating gradient issues while preserving essential topological features. Additionally, we enforce topological consistency by constructing topological primitives with genus numbers that match those of ground truth using Gauss-Bonnet theorem. Experimental results demonstrate that our inverse rendering approach outperforms the current state-of-the-art method, achieving significant improvements in Chamfer Distance and Volume IoU, particularly for high-genus surfaces, while also enhancing surface details for low-genus surfaces.
- 10 July 2025
- Published by Springer Nature
- p. 65-85
FlexGE: Towards Secure and Flexible Model Partition for Deep Neural Networks
- 10 July 2025
- Published by Springer Nature
- p. 65-85
FlexGE: Towards Secure and Flexible Model Partition for Deep Neural Networks
- 5 August 2019
- Published by Springer Nature in CCF Transactions on High Performance Computing
- Vol. 1 (2) , 111-130
PASTA: a parallel sparse tensor algorithm benchmark suite
- 5 August 2019
- Published by Springer Nature in CCF Transactions on High Performance Computing
- Vol. 1 (2) , 111-130
PASTA: a parallel sparse tensor algorithm benchmark suite