technique

Diffusion-Aligned Structured Latents

techniqueactiveprovisionaldiffusion-aligned-structured-latents-9563da51·1 events·first seen 16h ago

Aliases: Diffusion-Aligned Structured Latents

Co-occurring entities

Sparse-structure Multimodal Diffusion Transformer FLUX3D Modal-Aware Rotary Positional Embedding

More like this (12)

Diffusion Language Models latent diffusion Latent Profile Analysis latent diffusion model Latent Context Language Models Latent Space Representation-Conditioned Diffusion Models Sparse-structure Multimodal Diffusion Transformer LALS (Latent Association Leaning Score)Interleaved Speech Language Models Latently Work In Text Self-Augmenting Retrieval for Diffusion Language Models Ambient Diffusion Policy

Recent events (1)

5arXiv · cs.AI·16h ago·source ↗

FLUX3D: Diffusion-aligned sparse representation for high-fidelity image-to-3D Gaussian Splatting

Researchers introduce FLUX3D, an image-to-3D Gaussian Splatting framework that addresses two structural bottlenecks in sparse voxel-based 3D generation: a representation bottleneck from discriminative 2D features and a cross-modal correspondence bottleneck in diffusion transformers. The system introduces Diffusion-Aligned Structured Latents (DA-SLAT) and a Sparse-structure Multimodal Diffusion Transformer (SMDiT) with Modal-Aware Rotary Positional Embedding (MARoPE) to improve 2D-3D alignment. Benchmark results claim substantial improvements in appearance fidelity over all current state-of-the-art methods for 3DGS asset generation.

Multimodal Progress Sparse-structure Multimodal Diffusion Transformer FLUX3D Diffusion-Aligned Structured Latents +1 more