Paper-Conference

Agentic Retoucher for Text-To-Image Generation
Code Source Document
One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolution
Code Source Document
LaTo: Landmark-tokenized Diffusion Transformer for Fine-grained Human Face Editing
Code Source Document
SMC++: Masked Learning of Unsupervised Video Semantic Compression
Source Document
BEAM: Bridging Physically-based Rendering and Gaussian Modeling for Relightable Volumetric Video
Source Document
MultiEgo: A Multi-View Egocentric Video Dataset for 4D Scene Reconstruction
Source Document
Cellular Aggregation Graph Convolutional Network for Point Cloud Quality Assessment
Source Document
AlignGS: Aligning Geometry and Semantics for Robust Indoor Reconstruction from Sparse Views
Source Document
Long-tailed Recognition with Model Rebalancing
Source Document
MoA-VR: A Mixture-of-Agents System Towards All-in-One Video Restoration
Source Document