5 papers
Hadamard-Domain Model Quantization for Learned Image Coding
Junqi Shi, Chongzhi Wang, Yiwen He +2
Uniform INT8 quantization is attractive for deploying learned image coding (LIC), but its rate--distortion (R--D) performance is often limited by heavy-tailed tensors and large int…
DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression
Junqi Shi, Ming Lu, Xingchen Li +3
Diffusion-based image compression has recently shown outstanding perceptual fidelity, yet its practicality is hindered by prohibitive sampling overhead and high memory usage. Most…
Reinforced Rate Control for Neural Video Compression via Inter-Frame Rate-Distortion Awareness
Wuyang Cong, Junqi Shi, Lizhong Wang +4
Neural video compression (NVC) has demonstrated superior compression efficiency, yet effective rate control remains a significant challenge due to complex temporal dependencies. Ex…
YODA: Yet Another One-step Diffusion-based Video Compressor
Xingchen Li, Junzhe Zhang, Junqi Shi +2
While one-step diffusion models have recently excelled in perceptual image compression, their application to video remains limited. Prior efforts typically rely on pretrained 2D au…
On Quantizing Neural Representation for Variable-Rate Video Coding
Junqi Shi, Zhujia Chen, Hanfei Li +4
This work introduces NeuroQuant, a novel post-training quantization (PTQ) approach tailored to non-generalized Implicit Neural Representations for variable-rate Video Coding (INR-V…