no code implementations • 22 Apr 2024 • Guibiao Liao, Jiankun Li, Zhenyu Bao, Xiaoqing Ye, Jingdong Wang, Qing Li, Kanglin Liu
Additionally, to address the semantic ambiguity, caused by utilizing view-inconsistent 2D CLIP semantics to supervise Gaussians, we introduce a 3D Coherent Self-training (3DCS) strategy, resorting to the multi-view consistency originated from the 3D model.
no code implementations • 7 Feb 2024 • Guibiao Liao, Kaichen Zhou, Zhenyu Bao, Kanglin Liu, Qing Li
First, from the single-view perspective, we introduce Region Semantic Ranking (RSR) regularization by leveraging 2D mask proposals derived from SAM to rectify the noisy semantics of each training view, facilitating accurate semantic field learning.
1 code implementation • 26 Jan 2024 • Zhenyu Bao, Guibiao Liao, Zhongyuan Zhao, Kanglin Liu, Qing Li, Guoping Qiu
One of the innovative features of Du-NeRF is that it decouples a view-independent component from the density field and uses it as a label to supervise the learning process of the SDF field.
1 code implementation • 23 Jan 2024 • Zhongyuan Zhao, Zhenyu Bao, Qing Li, Guoping Qiu, Kanglin Liu
In this paper, we introduce PSAvatar, a novel framework for animatable head avatar creation that utilizes discrete geometric primitive to create a parametric morphable shape model and employs 3D Gaussian for fine detail representation and high fidelity rendering.
1 code implementation • 29 Sep 2023 • Cheng Guo, Leidong Fan, Qian Zhang, Hanyuan Liu, Kanglin Liu, Xiuhua Jiang
The latter requires more efficiency, thus the pre-calculated LUT (look-up table) has become a popular solution.
no code implementations • 27 Sep 2023 • Xujie Kang, Kanglin Liu, Jiang Duan, Yuanhao Gong, Guoping Qiu
Given a new $6DoF$ camera pose in an indoor environment, we study the challenging problem of predicting the view from that pose based on a set of reference RGBD views.
no code implementations • 16 Jul 2021 • Kanglin Liu, Gaofeng Cao, Jiang Duan, Guoping Qiu
Single-image HDR reconstruction or inverse tone mapping (iTM) is a challenging task.
1 code implementation • 5 Nov 2020 • Kanglin Liu, Gaofeng Cao, Fei Zhou, Bozhi Liu, Jiang Duan, Guoping Qiu
In this paper, we present a new technique termed Structure-Texture Independent Architecture with Weight Decomposition and Orthogonal Regularization (STIA-WO) to disentangle the latent space for unsupervised semantic face editing.
no code implementations • 23 Jun 2020 • Kanglin Liu, Qing Li, Guoping Qiu
We present PoseGANs, a conditional generative adversarial networks (cGANs) based framework for the implementation of pose-to-image translation.
2 code implementations • ICCV 2019 • Kanglin Liu, Wenming Tang, Fei Zhou, Guoping Qiu
Theoretical analysis shows that the optimal solution to the discriminator has a strong relationship to the spectral distributions of the weight matrix. Therefore, we monitor the spectral distribution in the discriminator of spectral normalized GANs (SN-GANs), and discover a phenomenon which we refer to as spectral collapse, where a large number of singular values of the weight matrices drop dramatically when mode collapse occurs.
no code implementations • 16 Mar 2018 • Kanglin Liu, Guoping Qiu
In this paper, we introduce the boundedness and continuity ($BC$) conditions to enforce the Lipschitz constraint on the discriminator functions of GANs.