15 papers
FreeLit: Paired-Free Indoor Relighting via Physics-Guided Diffusion
Chi-En Yen, Duy-Khanh Ngo, Wen-Wei Tang +3
Image-based indoor scene relighting remains challenging due to the complex interplay between cluttered geometry and local illumination, requiring precise modeling of light position…
A Cross-Framework Study of Temporal Information Buffering Strategies for Learned Video Compression
Kuan-Wei Ho, Yi-Hsin Chen, Martin Benjak +2
Recent advances in learned video codecs have demonstrated remarkable compression efficiency. Two fundamental design aspects are critical: the choice of inter-frame coding framework…
MH-LVC: Multi-Hypothesis Temporal Prediction for Learned Conditional Residual Video Coding
Huu-Tai Phung, Zong-Lin Gao, Yi-Chen Yao +5
This work, termed MH-LVC, presents a multi-hypothesis temporal prediction scheme that employs long- and short-term reference frames in a conditional residual video coding framework…
Application Space and the Rate-Distortion-Complexity Analysis of Neural Video CODECs
Ricardo L. de Queiroz, Diogo C. Garcia, Yi-Hsin Chen +3
We study the decision-making process for choosing video compression systems through a rate-distortion-complexity (RDC) analysis. We discuss the 2D Bjontegaard delta (BD) metric and…
Exploring Autoregressive Vision Foundation Models for Image Compression
Huu-Tai Phung, Yu-Hsiang Lin, Yen-Kuan Ho +1
This work presents the first attempt to repurpose vision foundation models (VFMs) as image codecs, aiming to explore their generation capability for low-rate image compression. VFM…
HyTIP: Hybrid Temporal Information Propagation for Masked Conditional Residual Video Coding
Yi-Hsin Chen, Yi-Chen Yao, Kuan-Wei Ho +5
Most frame-based learned video codecs can be interpreted as recurrent neural networks (RNNs) propagating reference information along the temporal dimension. This work revisits the…
Conditional Residual Coding with Explicit-Implicit Temporal Buffering for Learned Video Compression
Yi-Hsin Chen, Kuan-Wei Ho, Martin Benjak +2
This work proposes a hybrid, explicit-implicit temporal buffering scheme for conditional residual video coding. Recent conditional coding methods propagate implicit temporal inform…
Huawei Cloud Model-as-a-Service on the CloudMatrix384 SuperPod
Ao Xiao, Bangzheng He, Baoquan Zhang +125
Scaled-out MoE LLMs and scaled-up SuperPods create new systems challenges for production Model-as-a-Service (MaaS), requiring disaggregation, low-latency communication, and decentr…
Learning Optimal Linear Block Transform by Rate Distortion Minimization
Alessandro Gnutti, Chia-Hao Kao, Wen-Hsiao Peng +1
Linear block transform coding remains a fundamental component of image and video compression. Although the Discrete Cosine Transform (DCT) is widely employed in all current compres…
On the Rate-Distortion-Complexity Trade-offs of Neural Video Coding
Yi-Hsin Chen, Kuan-Wei Ho, Martin Benjak +2
This paper aims to delve into the rate-distortion-complexity trade-offs of modern neural video coding. Recent years have witnessed much research effort being focused on exploring t…
Bridging Compressed Image Latents and Multimodal Large Language Models
Chia-Hao Kao, Cheng Chien, Yu-Jen Tseng +5
This paper presents the first-ever study of adapting compressed image latents to suit the needs of downstream vision tasks that adopt Multimodal Large Language Models (MLLMs). MLLM…
Transformer-based Learned Image Compression for Joint Decoding and Denoising
Yi-Hsin Chen, Kuan-Wei Ho, Shiau-Rung Tsai +4
This work introduces a Transformer-based image compression system. It has the flexibility to switch between the standard image reconstruction and the denoising reconstruction from…
LiDAR Depth Map Guided Image Compression Model
Alessandro Gnutti, Stefano Della Fiore, Mattia Savardi +3
The incorporation of LiDAR technology into some high-end smartphones has unlocked numerous possibilities across various applications, including photography, image restoration, augm…
MaskCRT: Masked Conditional Residual Transformer for Learned Video Compression
Yi-Hsin Chen, Hong-Sheng Xie, Cheng-Wei Chen +4
Conditional coding has lately emerged as the mainstream approach to learned video compression. However, a recent study shows that it may perform worse than residual coding when the…
Transformer-based Image Compression with Variable Image Quality Objectives
Chia-Hao Kao, Yi-Hsin Chen, Cheng Chien +2
This paper presents a Transformer-based image compression system that allows for a variable image quality objective according to the user's preference. Optimizing a learned codec f…