[논문리뷰] PoseTraj: Pose-Aware Trajectory Control in Video Diffusion
PoseTraj 논문 리뷰 (CVPR 2025)
Recent posts
[논문리뷰] BlockDance: Reuse Structurally Similar Spatio-Temporal Features to Accelerate Diffusion Transformers
BlockDance 논문 리뷰 (CVPR 2025)
[논문리뷰] Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression
Random Conditioning 논문 리뷰 (CVPR 2025)
[논문리뷰] TransPixeler: Advancing Text-to-Video Generation with Transparency
TransPixeler 논문 리뷰 (CVPR 2025)
[논문리뷰] Progressive Compositionality In Text-to-Image Generative Models
EvoGen 논문 리뷰 (ICLR 2025 Spotlight)