6 papers
TTT3R: 3D Reconstruction as Test-Time Training
Xingyu Chen, Yue Chen, Yuliang Xiu +2
Modern Recurrent Neural Networks have become a competitive architecture for 3D reconstruction due to their linear-time complexity. However, their performance degrades significantly…
ConeGS: Error-Guided Densification Using Pixel Cones for Improved Reconstruction With Fewer Primitives
BartÅomiej Baranowski, Stefano Esposito, Patricia GschoÃmann +2
3D Gaussian Splatting (3DGS) achieves state-of-the-art image quality and real-time performance in novel view synthesis but often suffers from a suboptimal spatial distribution of p…
Easi3R: Estimating Disentangled Motion from DUSt3R Without Training
Xingyu Chen, Yue Chen, Yuliang Xiu +2
Recent advances in DUSt3R have enabled robust estimation of dense point clouds and camera parameters of static scenes, leveraging Transformer network architectures and direct super…
GenFusion: Closing the Loop between Reconstruction and Generation via Videos
Sibo Wu, Congrong Xu, Binbin Huang +2
Recently, 3D reconstruction and generation have demonstrated impressive novel view synthesis results, achieving high fidelity and efficiency. However, a notable conditioning gap ca…
Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes
Stefano Esposito, Anpei Chen, Christian Reiser +7
High-quality view synthesis relies on volume rendering, splatting, or surface rendering. While surface rendering is typically the fastest, it struggles to accurately model fuzzy ge…
sshELF: Single-Shot Hierarchical Extrapolation of Latent Features for 3D Reconstruction from Sparse-Views
Eyvaz Najafli, Marius Kästingschäfer, Sebastian Bernhard +2
Reconstructing unbounded outdoor scenes from sparse outward-facing views poses significant challenges due to minimal view overlap. Previous methods often lack cross-scene understan…