10 papers
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…
BioVITA: Biological Dataset, Model, and Benchmark for Visual-Textual-Acoustic Alignment
Risa Shinoda, Kaede Shiohara, Nakamasa Inoue +3
Understanding animal species from multimodal data poses an emerging challenge at the intersection of computer vision and ecology. While recent biological models, such as BioCLIP, h…
AnimalCLAP: Taxonomy-Aware Language-Audio Pretraining for Species Recognition and Trait Inference
Risa Shinoda, Kaede Shiohara, Nakamasa Inoue +2
Animal vocalizations provide crucial insights for wildlife assessment, particularly in complex environments such as forests, aiding species identification and ecological monitoring…
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…