Search papers, labs, and topics across Lattice.
2
0
4
CoMA-DiT is proposed, a bidirectional cross-modal Diffusion Transformer for latent augmentation that treats paired modalities as sources of mutual generative supervision rather than merely as inputs to be fused.
Adverse weather conditions can significantly degrade image quality, but our mask-guided MMIF method achieves superior feature restoration and interaction, setting a new benchmark in the field.
