Search Results for author:
Found 2 papers, 0 papers with code
2L3: Lifting Imperfect Generated 2D Images into Accurate 3D
Specifically, we first leverage to decouple the shading information from the generated images to reduce the impact of inconsistent lighting; then, we introduce mono prior with view-dependent transient encoding to enhance the reconstructed normal; and finally, we design a view augmentation fusion strategy that minimizes pixel-level loss in generated sparse views and semantic loss in augmented random views, resulting in view-consistent geometry and detailed textures.
Retrieval-Enhanced Visual Prompt Learning for Few-shot Classification
Prompt learning has become a popular approach for adapting large vision-language models, such as CLIP, to downstream tasks.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
