3 papers
cs.CV2026
PhGS: Post-Hoc Pruning and Refinement of Single-View Feed-Forward 3D Gaussian Reconstructions
Rinto Yagawa, Han Cheng, Dieter Schmalstieg +2
Recent single-view feed-forward 3D Gaussian Splatting (3DGS) generation predicts a fixed number of Gaussians per camera ray, introducing severe spatial redundancy. Most existing co…
cs.CV2025
IntelliCap: Intelligent Guidance for Consistent View Sampling
Ayaka Yasunaga, Hideo Saito, Dieter Schmalstieg +1
Novel view synthesis from images, for example, with 3D Gaussian splatting, has made great progress. Rendering fidelity and speed are now ready even for demanding virtual reality ap…
cs.CV2025
User-in-the-Loop View Sampling with Error Peaking Visualization
Ayaka Yasunaga, Hideo Saito, Shohei Mori
Augmented reality (AR) provides ways to visualize missing view samples for novel view synthesis. Existing approaches present 3D annotations for new view samples and task users with…