6 papers
AerialMetric: Benchmarking and Adapting UAV Monocular Metric Depth Estimation in the Real World
Zhongqiang Song, Guanying Chen, Yuqi Zhang +6
This paper addresses the problem of monocular metric depth estimation in aerial UAV imagery. Although recent data-driven methods have achieved remarkable progress in ground-level s…
Smart-Insertion-V: Photorealistic Video Insertion via a Closed-Loop Feedback Dual-Stream Framework
Xiao Cao, Yansong Qu, Xiangzhen +7
Mask-free video object insertion has emerged as a challenging task, requiring harmonious integration of reference objects into source videos. However, existing methods struggle whe…
GlowGS: Generative Semantic Feature Learning for 3D Gaussian Splatting in Nighttime Glow Scenes
Beibei Lin, Xiao Cao, Jingyuan Guo +1
Existing 3DGS methods effectively render high-quality novel views in clear-day scenes. However, they struggle with night scenes, particularly in glow regions, due to the lack of st…
GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction
Xiao Cao, Yuze Li, Youmin Zhang +4
3D Gaussian Splatting (3DGS) has emerged as a prominent paradigm for 3D reconstruction and novel view synthesis. However, it remains vulnerable to severe artifacts when trained und…
RobustSplat++: Decoupling Densification, Dynamics, and Illumination for In-the-Wild 3DGS
Chuanyu Fu, Guanying Chen, Yuqi Zhang +6
3D Gaussian Splatting (3DGS) has gained significant attention for its real-time, photo-realistic rendering in novel-view synthesis and 3D modeling. However, existing methods strugg…
RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGS
Chuanyu Fu, Yuqi Zhang, Kunbin Yao +5
3D Gaussian Splatting (3DGS) has gained significant attention for its real-time, photo-realistic rendering in novel-view synthesis and 3D modeling. However, existing methods strugg…