20 February 2025 in IEEE MultiMedia
3D Gaussian Splatting (3DGS) has become a pivotal technology for 3D scene representation. However, its application to large-scale, high-resolution scenes (exceeding 4k×4k pixels) is hindered by the excessive computational and storage requirements for managing a large number of Gaussians. To address these challenges, we propose ’EfficientGS’, an advanced approach that optimizes 3DGS for high-resolution, large-scale scenes. First, we design a more selective densification to reduce the overproliferation of Gaussians. Second, we develop a pruning mechanism to remove redundant Gaussians that only serve as auxiliaries to adjacent ones. Finally, we introduce a sparse order increment strategy for Spherical Harmonics to reduce unnecessary storage. Our empirical evaluations on various datasets, including extensive 4K+ aerial images, demonstrate that ’EfficientGS’ can achieve high rendering fidelity with less computational and storage cost. Our code is available at https://github.com/wenkaier/EfficientGS.
19 July 2022 in IEEE Transactions on Circuits and Systems for Video Technology
Learning-based face reconstruction methods have recently shown promising performance in recovering face geometry from a single image. However, the lack of training data with 3D annotations severely limits the performance. To tackle this problem, we proposed a novel end-to-end 3D face reconstruction network consisting of a conditional GAN (cGAN) for cross-domain face synthesis and a novel mesh transformer for face reconstruction. Our method first uses cGAN to translate the realistic face images to the specific rendered style, with a 2D facial edge consistency loss function. The domain-transferred images are then fed into face reconstruction network which uses a novel mesh transformer to output 3D mesh vertices. To exploit the domain-transferred in-the-wild images, we further propose a reprojection consistency loss to restrict face reconstruction network in a self-supervised way. Our approach can be trained with annotated dataset, synthetic dataset and in-the-wild images to learn a unified face model. Extensive experiments have demonstrated the effectiveness of our method.
30 June 2022 in KSII Transactions on Internet and Information Systems
KSII Transactions on Internet and Information Systems TIIS Paper Details
17 October 2025 in Pattern Recognition
29 July 2022 in IEEE MultiMedia
Monocular face reconstruction is a significant task in many multimedia applications. However, learning-based methods unequivocally suffer from the lack of large datasets annotated with 3D ground-truth. To tackle this problem, we proposed a novel end-to-end 3D face reconstruction network consisting of a domain-transfer conditional GAN (cGAN) and a face reconstruction network. Our method first uses cGAN to translate the realistic face images to the specific rendered style, with a novel 2D facial edge consistency loss function to exploit in-the-wild images. The domain-transferred images are then fed into 3D face reconstruction network. We further propose a novel reprojection consistency loss to restrict 3D face reconstruction network in a self-supervised way. Our approach can be trained with annotated dataset, synthetic dataset and in-the-wild images to learn a unified face model. Extensive experiments have demonstrated the effectiveness of our method.
1 October 2025 in IEEE MultiMedia