3 papers
cs.CV2026
Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching
Junwan Kim, Jiho Park, Seonghu Jeon +1
Flow matching has recently emerged as a promising alternative to diffusion-based generative models, particularly for text-to-image generation. Despite its flexibility in allowing a…
cs.CV2026
Projected Representation Conditioning for High-fidelity Novel View Synthesis
Min-Seop Kwak, Minkyung Kwon, Jinhyeok Choi +2
We propose a novel framework for diffusion-based novel view synthesis in which we leverage external representations as conditions, harnessing their geometric and semantic correspon…
cs.CV2025
CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Models
Minkyung Kwon, Jinhyeok Choi, Jiho Park +6
Multi-view diffusion models have recently emerged as a powerful paradigm for novel view synthesis, yet the underlying mechanism that enables their view-consistency remains unclear.…