29 citations · 43 across the 9 of their papers we have counts for
8 papers · 1 filter
ERGO: Excess-Risk-Guided Optimization for High-Fidelity Monocular 3D Gaussian Splatting
Zehua Ma, Hanhui Li, Zhenyu Xie +4
Generating 3D content from a single image remains a fundamentally challenging and ill-posed problem due to the inherent absence of geometric and textural information in occluded re…
Exploring Talking Head Models With Adjacent Frame Prior for Speech-Preserving Facial Expression Manipulation
Zhenxuan Lu, Zhihua Xu, Zhijing Yang +4
Speech-Preserving Facial Expression Manipulation (SPFEM) is an innovative technique aimed at altering facial expressions in images and videos while retaining the original mouth mov…
DCA-LUT: Deep Chromatic Alignment with 5D LUT for Purple Fringing Removal
Jialang Lu, Shuning Sun, Pu Wang +6
Purple fringing, a persistent artifact caused by Longitudinal Chromatic Aberration (LCA) in camera lenses, has long degraded the clarity and realism of digital imaging. Traditional…
Zero-Shot Visual Grounding in 3D Gaussians via View Retrieval
Liwei Liao, Xufeng Li, Xiaoyun Zheng +3
3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on text prompts, which is essential for applications such as robotics. However, existing 3DVG methods encounter…
CL-MVSNet: Unsupervised Multi-view Stereo with Dual-level Contrastive Learning
Kaiqiang Xiong, Rui Peng, Zhe Zhang +4
Unsupervised Multi-View Stereo (MVS) methods have achieved promising progress recently. However, previous methods primarily depend on the photometric consistency assumption, which…
OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarking
Xuanyu Zhang, Zecheng Tang, Zhipei Xu +5
With the rapid growth of generative AI and its widespread application in image editing, new risks have emerged regarding the authenticity and integrity of digital content. Existing…
PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling
Xiaoyun Zheng, Liwei Liao, Xufeng Li +5
High-quality human reconstruction and photo-realistic rendering of a dynamic scene is a long-standing problem in computer vision and graphics. Despite considerable efforts invested…
LLIC: Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compression
Wei Jiang, Peirong Ning, Jiayu Yang +3
The effective receptive field (ERF) plays an important role in transform coding, which determines how much redundancy can be removed during transform and how many spatial priors ca…