7 papers
FillGS: Filling Observation Gaps in 4D Gaussian Splatting via Viewpoint-Time Selection and Generative Refinement
Takashi Otonari, Toshihiko Yamasaki
4D Gaussian Splatting (4DGS) can render dynamic scenes photorealistically. However, with limited viewpoint coverage, some spatiotemporal regions remain sparsely observed, leading t…
GUSH3R: Everyone Everywhere All at Once as Gaussians
Keito Abe, Kaede Shiohara, Takashi Otonari +1
Reconstructing dynamic human-scene environments from monocular videos is a challenging problem that requires jointly modeling scene geometry, camera motion, and non-rigid human dyn…
Wild3R: Feed-Forward 3D Gaussian Splatting from Unconstrained Sparse Photo Collection
Yuto Furutani, Takashi Otonari, Kaede Shiohara +1
Feed-forward 3D Gaussian Splatting (3DGS) removes the need for time-consuming per-scene optimization required by traditional 3DGS. However, existing feed-forward approaches struggl…
Unified Vector Floorplan Generation via Markup Representation
Kaede Shiohara, Toshihiko Yamasaki
Automatic residential floorplan generation has long been a central challenge bridging architecture and computer graphics, aiming to make spatial design more efficient and accessibl…
ExposeAnyone: Personalized Audio-to-Expression Diffusion Models Are Robust Zero-Shot Face Forgery Detectors
Kaede Shiohara, Toshihiko Yamasaki, Vladislav Golyanik
Detecting unknown deepfake manipulations remains one of the most challenging problems in face forgery detection. Current state-of-the-art approaches fail to generalize to unseen ma…
ControlVP: Interactive Geometric Refinement of AI-Generated Images with Consistent Vanishing Points
Ryota Okumura, Kaede Shiohara, Toshihiko Yamasaki
Recent text-to-image models, such as Stable Diffusion, have achieved impressive visual quality, yet they often suffer from geometric inconsistencies that undermine the structural r…