13 papers
Rate-Distortion Adaptive Primitive Selection for Omnidirectional Gaussian Splatting
Yulong Cheng, Youneng Bao, Junfeng Zhou +2
Learned image codecs (LICs) achieve high reconstruction quality, but their decoding speed is often insufficient for immersive virtual reality (VR). Gaussian splatting (GS) codecs r…
DA-Lion: Efficient Neural Video Representation via Direction-Aware Optimization
Qingyu Mao, Jiacong Chen, Shuai Liu +2
Implicit neural video representation (NVR) encodes a video as the parameters of an overfitted neural network, where training and testing data are identical and the objective is ins…
Quality Assessment of 3D Gaussian Splatting: Distortions, Benchmarks, and Open Challenges
Shuai Liu, Binqiang Liu, Qingyu Mao +3
3D Gaussian Splatting (3DGS) has become a practical scene representation for real-time novel-view rendering, compression, and immersive content delivery. However, its quality asses…
Locality-Aware Density Control for Efficient Gaussian-based Image Representation
Jiacong Chen, Qingyu Mao, Xiandong Meng +5
2D Gaussian Splatting is an attractive direction for image representation due to its explicit formulation, fast rasterization, and favorable decoding efficiency. The representation…
DynaQuant: Dynamic Mixed-Precision Quantization for Learned Image Compression
Youneng Bao, Yulong Cheng, Yiping Liu +4
Prevailing quantization techniques in Learned Image Compression (LIC) typically employ a static, uniform bit-width across all layers, failing to adapt to the highly diverse data di…
Dataset Distillation as Data Compression: A Rate-Utility Perspective
Youneng Bao, Yiping Liu, Zhuo Chen +3
Driven by the ``scale-is-everything'' paradigm, modern machine learning increasingly demands ever-larger datasets and models, yielding prohibitive computational and storage require…
Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video Reconstruction
Jiacong Chen, Qingyu Mao, Youneng Bao +4
3D Gaussian Splatting (3DGS) has emerged as a high-fidelity and efficient paradigm for online free-viewpoint video (FVV) reconstruction, offering viewers rapid responsiveness and i…
ShiftLIC: Lightweight Learned Image Compression with Spatial-Channel Shift Operations
Youneng Bao, Wen Tan, Chuanmin Jia +3
Learned Image Compression (LIC) has attracted considerable attention due to their outstanding rate-distortion (R-D) performance and flexibility. However, the substantial computatio…
Enhancing Adversarial Training with Prior Knowledge Distillation for Robust Image Compression
Zhi Cao, Youneng Bao, Fanyang Meng +4
Deep neural network-based image compression (NIC) has achieved excellent performance, but NIC method models have been shown to be susceptible to backdoor attacks. Adversarial train…
Universal Learned Image Compression With Low Computational Cost
Bowen Li, Yao Xin, Youneng Bao +3
Recently, learned image compression methods have developed rapidly and exhibited excellent rate-distortion performance when compared to traditional standards, such as JPEG, JPEG200…
Exploring Structural Sparsity in Neural Image Compression
Shanzhi Yin, Chao Li, Wen Tan +3
Neural image compression have reached or out-performed traditional methods (such as JPEG, BPG, WebP). However,their sophisticated network structures with cascaded convolution layer…
Transformations in Learned Image Compression from a Modulation Perspective
Youneng Bao, Fangyang Meng, Wen Tan +3
In this paper, a unified transformation method in learned image compression(LIC) is proposed from the perspective of modulation. Firstly, the quantization in LIC is considered as a…
Universal Efficient Variable-rate Neural Image Compression
Shanzhi Yin, Chao Li, Youneng Bao +1
Recently, Learning-based image compression has reached comparable performance with traditional image codecs(such as JPEG, BPG, WebP). However, computational complexity and rate fle…