5 papers
SurGe: Improved Surface Geometry in Point Maps
Karim Knaebel, Gonzalo Martin Garcia, Christian Schmidt +4
Recent feedforward 3D reconstruction methods predict point maps and estimate global 3D geometry remarkably well. However, their predictions still exhibit inaccurate local surface g…
Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers
Chung-Shien Brian Wang, Christian Schmidt, Jens Piekenbrinck +1
Efficient and accurate feed-forward multi-view reconstruction has long been an important task in computer vision. Recent transformer-based models like VGGT, and MapAnything…
OpenSplat3D: Open-Vocabulary 3D Instance Segmentation using Gaussian Splatting
Jens Piekenbrinck, Christian Schmidt, Alexander Hermans +3
3D Gaussian Splatting (3DGS) has emerged as a powerful representation for neural scene reconstruction, offering high-quality novel view synthesis while maintaining computational ef…
Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think
Gonzalo Martin Garcia, Karim Knaebel, Christian Schmidt +3
Recent work showed that large diffusion models can be reused as highly precise monocular depth estimators by casting depth estimation as an image-conditional image generation task.…
Look Gauss, No Pose: Novel View Synthesis using Gaussian Splatting without Accurate Pose Initialization
Christian Schmidt, Jens Piekenbrinck, Bastian Leibe
3D Gaussian Splatting has recently emerged as a powerful tool for fast and accurate novel-view synthesis from a set of posed input images. However, like most novel-view synthesis a…