Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Trajectory-Guided Diffusion for Foreground-Preserving Background Generation in Multi-Layer Documents
Taewon Kang
We present a diffusion-based framework for document-centric background generation that achieves foreground preservation and multi-page stylistic consistency through latent-space de…
cs.CV2025
HART: Human Aligned Reconstruction Transformer
Xiyi Chen, Shaofei Wang, Marko Mihajlovic +3
We introduce HART, a unified framework for sparse-view human reconstruction. Given a small set of uncalibrated RGB images of a person as input, it outputs a watertight clothed mesh…