3 papers
cs.CV2026
RIGOR: Rig-Informed Geometry for Omnidirectional Reconstruction
Tingjun Huang, Dmitry Rudshin, Mathieu Meyer +3
Recent developments in feed-forward 3D reconstruction resulted in models which can recover dense scene representations and camera motion solely from an image stream. However, such…
cs.CV2024
3D scene generation from scene graphs and self-attention
Pietro Bonazzi, Mengqi Wang, Diego Martin Arroyo +4
Synthesizing realistic and diverse indoor 3D scene layouts in a controllable fashion opens up applications in simulated navigation and virtual reality. As concise and robust repres…
cs.CV2024
Few-shot point cloud reconstruction and denoising via learned Guassian splats renderings and fine-tuned diffusion features
Pietro Bonazzi, Marie-Julie Rakatosaona, Marco Cannici +2
Existing deep learning methods for the reconstruction and denoising of point clouds rely on small datasets of 3D shapes. We circumvent the problem by leveraging deep learning metho…