Paper-Conference

TD-BFR: Truncated Diffusion Model for Efficient Blind Face Restoration
Diffusion-based methodologies have shown significant potential in blind face restoration (BFR), leveraging their robust generative …
Cite Source Document
TD-BFR: Truncated Diffusion Model for Efficient Blind Face Restoration
4DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Video
3D Gaussian Splatting (3DGS) has substantial potential for enabling photorealistic Free-Viewpoint Video (FVV) experiences. However, the …
Cite Code Project Source Document
4DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Video
CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration
Source Document
F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration
Source Document
FineVQ: Fine-Grained User Generated Content Video Quality Assessment (Highlight)
Code Source Document
Semantic versus Identity: A Divide-and-Conquer Approach towards Adjustable Medical Image De-Identification
Source Document
Serial Low-rank Adaptation of Vision Transformer
Fine-tuning large pre-trained vision foundation models in a parameter-efficient manner is critical for downstream vision tasks, …
Cite Source Document
Serial Low-rank Adaptation of Vision Transformer
VRVVC: Variable-Rate NeRF-Based Volumetric Video Compression
Neural Radiance Field (NeRF)-based volumetric video has revolutionized visual media by delivering photorealistic Free-Viewpoint Video …
Cite Source Document
VRVVC: Variable-Rate NeRF-Based Volumetric Video Compression
Preprocessing Enhanced Image Compression for Machine Vision
Source Document
VARFVV: View-Adaptive Real-Time Interactive Free-View Video Streaming with Edge Computing
Code Source Document