← Search

Runling Liu

4 accepted papers

2025

ADC-GS: Pose-Free 3D Gaussian Splatting with Adaptive Depth Consistency

ICASSP 2025accepted

Recently proposed 3D Gaussian Splatting (3DGS) has achieved state-of-the-art results in the fields of novel view synthesis, but it heavily relies on pre-computed camera poses. Although recent methods mitigate by leveraging explicit representations achieve novel view synthesis without requiring camer…

Cited by 0SourceScholar
2025

HDA-GS: Hierarchical Density-Controlled for Anisotropic 3D Gaussian Splatting

ICASSP 2025accepted

Recently, 3D Gaussian Splatting (3D-GS) has demonstrated impressive results in novel view synthesis, achieving outstanding rendering quality and speed. However, 3D-GS heavily relies on the quality of the initial point cloud, and its original Adaptive Density Control (ADC) module has difficulty handl…

Cited by 0SourceScholar
2025

LocalDyGS: Multi-view Global Dynamic Scene Modeling via Adaptive Local Implicit Feature Decoupling

ICCV 2025poster

Due to the complex and highly dynamic motions in the real world, synthesizing dynamic videos from multi-view inputs for arbitrary viewpoints is challenging. Previous works based on neural radiance field or 3D Gaussian splatting are limited to modeling fine-scale motion, greatly restricting their app…

Cited by 0SourcePDFScholar
2025

Multi-View Image Enhancement Inconsistency Decoupling Guided 3D Gaussian Splatting

ICASSP 2025accepted

3D Gaussian Splatting (3DGS) has recently made breakthrough progress in radiance field reconstruction but struggles with multi-view inconsistency. Modern cameras often apply tailored enhancements to each view when capturing multi-view images. While this improves individual image quality, it inevitab…

Cited by 0SourceScholar