7 papers · 1 filter
Depth-Consistent 3D Gaussian Splatting via Physical Defocus Modeling and Multi-View Geometric Supervision
Yu Deng, Baozhu Zhao, Junyan Su +2
Three-dimensional reconstruction in scenes with extreme depth variations remains challenging due to inconsistent supervisory signals between near-field and far-field regions. Exist…
TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering
Xiaohan Zhang, Sitong Wang, Yushen Yan +3
High-quality novel view synthesis for large-scale scenes presents a challenging dilemma in 3D computer vision. Existing methods typically partition large scenes into multiple regio…
GarmentX: Autoregressive Parametric Representations for High-Fidelity 3D Garment Generation
Jingfeng Guo, Jinnan Chen, Weikai Chen +6
This work presents GarmentX, a novel framework for generating diverse, high-fidelity, and wearable 3D garments from a single input image. Traditional garment reconstruction methods…
Metamon-GS: Enhancing Representability with Variance-Guided Densification and Light Encoding
Junyan Su, Baozhu Zhao, Xiaohan Zhang +1
The introduction of 3D Gaussian Splatting (3DGS) has advanced novel view synthesis by utilizing Gaussians to represent scenes. Encoding Gaussian point features with anchor embeddin…
Toy-GS: Assembling Local Gaussians for Precisely Rendering Large-Scale Free Camera Trajectories
Xiaohan Zhang, Zhenyu Sun, Yukui Qiu +2
Currently, 3D rendering for large-scale free camera trajectories, namely, arbitrary input camera trajectories, poses significant challenges: 1) The distribution and observation ang…
Aerial-NeRF: Adaptive Spatial Partitioning and Sampling for Large-Scale Aerial Rendering
Xiaohan Zhang, Yukui Qiu, Zhenyu Sun +1
Recent progress in large-scale scene rendering has yielded Neural Radiance Fields (NeRF)-based models with an impressive ability to synthesize scenes across small objects and indoo…