← Search

Kaiqiang Zhou

2 accepted papers

2025

Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction

ICLR 2025poster

Leveraging the visual priors of pre-trained text-to-image diffusion models offers a promising solution to enhance zero-shot generalization in dense prediction tasks. However, existing methods often uncritically use the original diffusion formulation, which may not be optimal due to the fundamental d…

Cited by 33SourcePDFScholar
2024

DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception

CVPR 2024poster

Current perceptive models heavily depend on resource-intensive datasets prompting the need for innovative solutions. Leveraging recent advances in diffusion models synthetic data by constructing image inputs from various annotations proves beneficial for downstream tasks. While prior methods have se…

Cited by 26SourcePDFScholar