4 papers · 1 filter
3DTV: A Feedforward Interpolation Network for Real-Time View Synthesis
Stefan Schulz, Fernando Edelstein, Hannah Dröge +2
Real-time free-viewpoint rendering requires balancing multi-camera redundancy with the latency constraints of interactive applications. We address this challenge by combining light…
Neu-PiG: Neural Preconditioned Grids for Fast Dynamic Surface Reconstruction on Long Sequences
Julian Kaltheuner, Hannah Dröge, Markus Plack +2
Temporally consistent surface reconstruction of dynamic 3D objects from unstructured point cloud data remains challenging, especially for very long sequences. Existing methods eith…
Transformer-Based Inpainting for Real-Time 3D Streaming in Sparse Multi-Camera Setups
Leif Van Holland, Domenic Zingsheim, Mana Takhsha +4
High-quality 3D streaming from multiple cameras is crucial for immersive experiences in many AR/VR applications. The limited number of views - often due to real-time constraints -…
Yesnt: Are Diffusion Relighting Models Ready for Capture Stage Compositing? A Hybrid Alternative to Bridge the Gap
Elisabeth Jüttner, Janelle Pfeifer, Leona Krath +4
Volumetric video relighting is essential for bringing captured performances into virtual worlds, but current approaches struggle to deliver temporally stable, production-ready resu…