#Latent Diffusion Models

11개의 포스트

[논문리뷰] Making Reconstruction FID Predictive of Diffusion Generation FID

Haotian Zhang이 arXiv에 게시한 'Making Reconstruction FID Predictive of Diffusion Generation FID' 논문에 대한 자세한 리뷰입니다.

#Review #Latent Diffusion Models #VAE #FID #Generative Models #Evaluation Metrics #Image Generation #Reconstruction-Generation Dilemma #Interpolation

2026년 3월 8일

[논문리뷰] Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models

arXiv에 게시된 'Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models' 논문에 대한 자세한 리뷰입니다.

#Review #2D Strokes #3D Model Generation #Rigged Meshes #Latent Diffusion Models #Skeleton Generation #Text-to-3D #Graph Neural Networks #Preference Optimization

2026년 2월 11일

[논문리뷰] Boosting Latent Diffusion Models via Disentangled Representation Alignment

arXiv에 게시된 'Boosting Latent Diffusion Models via Disentangled Representation Alignment' 논문에 대한 자세한 리뷰입니다.

#Review #Latent Diffusion Models #Variational Autoencoders #Disentangled Representations #Vision Foundation Models #Representation Alignment #Image Generation #Semantic Disentanglement

2026년 1월 12일

[논문리뷰] Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing

arXiv에 게시된 'Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Image Generation #Image Editing #Representation Encoders #Latent Diffusion Models #Variational Autoencoder (VAE)#Semantic Reconstruction #Off-manifold Latents #DINOv2

2025년 12월 21일

[논문리뷰] REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion

Giorgos Sfikas이 arXiv에 게시한 'REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion' 논문에 대한 자세한 리뷰입니다.

#Review #Latent Diffusion Models #Vision Foundation Models #Semantic Compression #Global-Local Semantics #Image Generation #Representation Entanglement #Transformer Architecture

2025년 12월 18일

[논문리뷰] Towards Scalable Pre-training of Visual Tokenizers for Generation

arXiv에 게시된 'Towards Scalable Pre-training of Visual Tokenizers for Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Visual Tokenizers #Pre-training #Latent Diffusion Models #Generative Models #Vision Transformer #Contrastive Learning #Self-Supervised Learning #Scaling Laws

2025년 12월 15일

[논문리뷰] Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion

arXiv에 게시된 'Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion' 논문에 대한 자세한 리뷰입니다.

#Review #Latent Diffusion Models #Asynchronous Denoising #Semantic Modeling #Texture Modeling #Image Generation #Vision Transformer #VAE #Fast Convergence

2025년 12월 4일

[논문리뷰] GaussianBlender: Instant Stylization of 3D Gaussians with Disentangled Latent Spaces

Sezer Karaoglu이 arXiv에 게시한 'GaussianBlender: Instant Stylization of 3D Gaussians with Disentangled Latent Spaces' 논문에 대한 자세한 리뷰입니다.

#Review #3D Gaussian Splatting #Text-to-3D Stylization #Latent Diffusion Models #Disentangled Latent Spaces #Feed-forward Editing #Geometry Preservation #Multi-view Consistency

2025년 12월 4일

[논문리뷰] One Small Step in Latent, One Giant Leap for Pixels: Fast Latent Upscale Adapter for Your Diffusion Models

Ilya Makarov이 arXiv에 게시한 'One Small Step in Latent, One Giant Leap for Pixels: Fast Latent Upscale Adapter for Your Diffusion Models' 논문에 대한 자세한 리뷰입니다.

#Review #Latent Diffusion Models #Super-Resolution #Upscaling Adapter #Image Generation #Latent Space #Multi-scale Learning #Cross-VAE

2025년 11월 13일

[논문리뷰] VIST3A: Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator

Federico Tombari이 arXiv에 게시한 'VIST3A: Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-3D #Model Stitching #Multi-view Reconstruction #Video Generation #Latent Diffusion Models #Gaussian Splats #Pointmaps #Reward Finetuning

2025년 10월 17일

[논문리뷰] UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution

arXiv에 게시된 'UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution' 논문에 대한 자세한 리뷰입니다.

#Review #Video Super-Resolution #Multi-Modal Generation #Latent Diffusion Models #Cascaded Framework #Condition Injection #Text-to-Video #Video Editing #4K Video

2025년 10월 10일