9 papers
Capacity-Controlled Multi-View Stylization of 3D Gaussian Splatting
Zhihao Wen, Yixin Yang, Bojian Wu +4
While 3D Gaussian Splatting (3DGS) provides an efficient and explicit representation for novel view synthesis, enforcing stylistic coherence across viewpoints remains challenging.…
Augmented Radiance Field: A General Framework for Enhanced Gaussian Splatting
Yixin Yang, Bojian Wu, Yang Zhou +1
Due to the real-time rendering performance, 3D Gaussian Splatting (3DGS) has emerged as the leading method for radiance field reconstruction. However, its reliance on spherical har…
NoPe-NeRF++: Local-to-Global Optimization of NeRF with No Pose Prior
Dongbo Shi, Shen Cao, Bojian Wu +5
In this paper, we introduce NoPe-NeRF++, a novel local-to-global optimization algorithm for training Neural Radiance Fields (NeRF) without requiring pose priors. Existing methods,…
TrackGS: Optimizing COLMAP-Free 3D Gaussian Splatting with Global Track Constraints
Dongbo Shi, Shen Cao, Lubin Fan +4
We present TrackGS, a novel method to integrate global feature tracks with 3D Gaussian Splatting (3DGS) for COLMAP-free novel view synthesis. While 3DGS delivers impressive renderi…
Learning Compact Latent Space for Representing Neural Signed Distance Functions with High-fidelity Geometry Details
Qiang Bai, Bojian Wu, Xi Yang +1
Neural signed distance functions (SDFs) have been a vital representation to represent 3D shapes or scenes with neural networks. An SDF is an implicit function that can query signed…
Glossy Object Reconstruction with Cost-effective Polarized Acquisition
Bojian Wu, Yifan Peng, Ruizhen Hu +1
The challenge of image-based 3D reconstruction for glossy objects lies in separating diffuse and specular components on glossy surfaces from captured images, a task complicated by…