1 citations · 1 across the 13 of their papers we have counts for
13 papers
Pose-Free Omnidirectional Gaussian Splatting for 360-Degree Videos with Consistent Depth Priors
Chuanqing Zhuang, Xin Lu, Zehui Deng +4
Omnidirectional 3D Gaussian Splatting with panoramas is a key technique for 3D scene representation, and existing methods typically rely on slow SfM to provide camera poses and spa…
Landmark Guided 4D Facial Expression Generation
Xin Lu, Zhengda Lu, Yiqun Wang +1
In this paper, we proposed a generative model that learns to synthesize the 4D facial expression with the neutral landmark. Existing works mainly focus on the generation of sequenc…
FC-4DFS: Frequency-controlled Flexible 4D Facial Expression Synthesizing
Xin Lu, Chuanqing Zhuang. Zhengda Lu, Yiqun Wang +1
4D facial expression synthesizing is a critical problem in the fields of computer vision and graphics. Current methods lack flexibility and smoothness when simulating the inter-fra…
Memory-Guided View Refinement for Dynamic Human-in-the-loop EQA
Xin Lu, Rui Li, Xun Huang +6
Embodied Question Answering (EQA) has traditionally been evaluated in temporally stable environments where visual evidence can be accumulated reliably. However, in dynamic, human-p…
LSF-Animation: Label-Free Speech-Driven Facial Animation via Implicit Feature Representation
Xin Lu, Chuanqing Zhuang, Chenxi Jin +4
Speech-driven 3D facial animation has attracted increasing interest since its potential to generate expressive and temporally synchronized digital humans. While recent works have b…
Empowering Vector Graphics with Consistently Arbitrary Viewing and View-dependent Visibility
Yidi Li, Jun Xiao, Zhengda Lu +2
This work presents a novel text-to-vector graphics generation approach, Dream3DVG, allowing for arbitrary viewpoint viewing, progressive detail optimization, and view-dependent occ…
DehazeGS: Seeing Through Fog with 3D Gaussian Splatting
Jinze Yu, Yiqun Wang, Aiheng Jiang +5
Current novel view synthesis methods are typically designed for high-quality and clean input images. However, in foggy scenes, scattering and attenuation can significantly degrade…
SpikeGS: Learning 3D Gaussian Fields from Continuous Spike Stream
Jinze Yu, Xin Peng, Zhengda Lu +2
A spike camera is a specialized high-speed visual sensor that offers advantages such as high temporal resolution and high dynamic range compared to conventional frame cameras. Thes…
Improved Neural Radiance Fields Using Pseudo-depth and Fusion
Jingliang Li, Qiang Zhou, Chaohui Yu +4
Since the advent of Neural Radiance Fields, novel view synthesis has received tremendous attention. The existing approach for the generalization of radiance field reconstruction pr…
SDFReg: Learning Signed Distance Functions for Point Cloud Registration
Leida Zhang, Zhengda Lu, Kai Liu +1
Learning-based point cloud registration methods can handle clean point clouds well, while it is still challenging to generalize to noisy, partial, and density-varying point clouds.…
DS-MVSNet: Unsupervised Multi-view Stereo via Depth Synthesis
Jingliang Li, Zhengda Lu, Yiqun Wang +2
In recent years, supervised or unsupervised learning-based MVS methods achieved excellent performance compared with traditional methods. However, these methods only use the probabi…
DepthGAN: GAN-based Depth Generation of Indoor Scenes from Semantic Layouts
Yidi Li, Yiqun Wang, Zhengda Lu +1
Limited by the computational efficiency and accuracy, generating complex 3D scenes remains a challenging problem for existing generation networks. In this work, we propose DepthGAN…
ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation
Chuanqing Zhuang, Zhengda Lu, Yiqun Wang +2
Depth estimation is a crucial step for 3D reconstruction with panorama images in recent years. Panorama images maintain the complete spatial information but introduce distortion wi…