From the 3 of 5 linked papers with an AI index.
5 papers
View-Adaptive Renderer for View-Consistent 2D-to-3D Generation
U-Chae Jun, Jaeeun Ko, Jiwoo Kang
Reconstructing 3D shapes from a single image remains a fundamental yet challenging problem in computer vision. Traditional monocular 3D generation pipelines typically synthesize mu…
Convolutional Neural Shading for High-Quality 3D Reconstruction from Multi-View Images
Juheon Hwang, Taewan Kim, Heeseok Oh +1
The paper introduces Convolutional Neural Shading (CNS), a pipeline that uses a convolutional neural shader and a fine-detail displacement network to improve the accuracy of 3D sha…
Collaborative Feature Aggregation for Face Super-Resolution and Robust Re-Identification
Juheon Hwang, Taewan Kim, Jiwoo Kang
The paper introduces a transformer‑based collaborative feature aggregation method that jointly performs face super‑resolution and robust person re‑identification by unifying identi…
Face and Voice Cross-modal Association with Learning Convex Feature Embedding
Taewan Kim, Jiwoo Kang
The paper introduces a method that embeds face images and voice recordings into a shared convex feature space, using cross‑modal attention to reduce mismatches and improve verifica…
GeoAvatar: Adaptive Geometrical Gaussian Splatting for 3D Head Avatar
SeungJun Moon, Hah Min Lew, Seungeun Lee +2
Despite recent progress in 3D head avatar generation, balancing identity preservation, i.e., reconstruction, with novel poses and expressions, i.e., animation, remains a challenge.…