11 papers
Confidence matters: Leveraging Multi-view Geometric Priors for GS-based Reconstruction
Hongyu Zhou, Zorah Lähner
3D Gaussian splatting (3DGS) has emerged as a widely-used tool for novel view synthesis, offering real-time rendering in a sparse representation. However, the method's reliance on…
GARDEN: Gravity-Aligned Reconstruction of Disentangled ENvironments from RGB images
Jiahao Sun, Dingkun Wei, Zehong Shen +3
Converting multi-view RGB observations into simulation-ready 3D environments remains challenging because current reconstruction pipelines produce monolithic scene representations w…
Geometry Gaussians: Decoupling Appearance and Geometry in Gaussian Splatting
Hongyu Zhou, Zorah Lähner
After the success of 3D Gaussian Splatting (3DGS) for novel view synthesis, many works have explored how to also use it for geometric surface representation. However, extracting ac…
The Constant Eye: Benchmarking and Bridging Appearance Robustness in Autonomous Driving
Jiabao Wang, Hongyu Zhou, Yuanbo Yang +2
Despite rapid progress, autonomous driving algorithms remain notoriously fragile under Out-of-Distribution (OOD) conditions. We identify a critical decoupling failure in current re…
ReRoPE: Repurposing RoPE for Relative Camera Control
Chunyang Li, Yuanbo Yang, Jiahao Shao +3
Video generation with controllable camera viewpoints is essential for applications such as interactive content creation, gaming, and simulation. Existing methods typically adapt pr…
FreeFix: Boosting 3D Gaussian Splatting via Fine-Tuning-Free Diffusion Models
Hongyu Zhou, Zisen Shao, Sheng Miao +4
Neural Radiance Fields and 3D Gaussian Splatting have advanced novel view synthesis, yet still rely on dense inputs and often degrade at extrapolated views. Recent approaches lever…