collaborators

7 papers

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2025

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…