5 papers · 1 filter
Fillerbuster: Unified Generative Scene Completion Model for Casual Captures
Ethan Weber, Norman Müller, Yash Kant +4
We present Fillerbuster, a unified model that completes unknown regions of a 3D scene with a multi-view latent diffusion transformer. Casual captures are often sparse and miss surr…
FlowR: Flowing from Sparse to Dense 3D Reconstructions
Tobias Fischer, Samuel Rota Bulò, Yung-Hsu Yang +7
3D Gaussian splatting enables high-quality novel view synthesis (NVS) at real-time frame rates. However, its quality drops sharply as we depart from the training views. Thus, dense…
Multi-view Image Diffusion via Coordinate Noise and Fourier Attention
Justin Theiss, Norman Müller, Daeil Kim +1
Recently, text-to-image generation with diffusion models has made significant advancements in both higher fidelity and generalization capabilities compared to previous baselines. H…
ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models
Lukas Höllein, Aljaž BožiÄ, Norman Müller +5
3D asset generation is getting massive amounts of attention, inspired by the recent success of text-guided 2D content creation. Existing text-to-3D methods use pretrained text-to-i…
Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models
Zhengming Yu, Zhiyang Dou, Xiaoxiao Long +9
We present Surf-D, a novel method for generating high-quality 3D shapes as Surfaces with arbitrary topologies using Diffusion models. Previous methods explored shape generation wit…