4 papers
DiffusionLight-Turbo: Accelerated Light Probes for Free via Single-Pass Chrome Ball Inpainting
Worameth Chinchuthakun, Pakkapon Phongthawee, Amit Raj +3
We introduce a simple yet effective technique for estimating lighting from a single low-dynamic-range (LDR) image by reframing the task as a chrome ball inpainting problem. This ap…
LUSD: Localized Update Score Distillation for Text-Guided Image Editing
Worameth Chinchuthakun, Tossaporn Saengja, Nontawat Tritrong +3
While diffusion models show promising results in image editing given a target prompt, achieving both prompt fidelity and background preservation remains difficult. Recent works hav…
Distilling Two-Timed Flow Models by Separately Matching Initial and Terminal Velocities
Pramook Khungurn, Pratch Piyawongwisal, Sira Sriswasdi +1
A flow matching model learns a time-dependent vector field that generates a probability path that interpolates between a well-known noise dis…
Revisiting Diffusion Autoencoder Training for Image Reconstruction Quality
Pramook Khungurn, Sukit Seripanitkarn, Phonphrm Thawatdamrongkit +1
Diffusion autoencoders (DAEs) are typically formulated as a noise prediction model and trained with a linear- noise schedule that spends much of its sampling steps at high nois…