3 papers
cs.GR2026
EDGS: Eliminating Densification for Efficient Convergence of 3DGS
Dmytro Kotovenko, Olga Grebenkova, Björn Ommer
3D Gaussian Splatting reconstructs scenes by starting from a sparse Structure-from-Motion initialization and refining under-reconstructed regions. This process is slow, as it requi…
cs.CV2024
DepthFM: Fast Monocular Depth Estimation with Flow Matching
Ming Gui, Johannes Schusterbauer, Ulrich Prestel +6
Current discriminative depth estimation methods often produce blurry artifacts, while generative approaches suffer from slow sampling due to curvatures in the noise-to-depth transp…
cs.CV2024
ZigMa: A DiT-style Zigzag Mamba Diffusion Model
Vincent Tao Hu, Stefan Andreas Baumann, Ming Gui +4
The diffusion model has long been plagued by scalability and quadratic complexity issues, especially within transformer-based structures. In this study, we aim to leverage the long…