collaborators

11 papers

cs.CV2026

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…

cs.CV2026

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…

cs.GR2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…