269 citations · 361 across the 46 of their papers we have counts for
11 papers · 1 filter
Error-Propagation-Free Learned Video Compression With Dual-Domain Progressive Temporal Alignment
Han Li, Shaohui Li, Wenrui Dai +5
Existing frameworks for learned video compression suffer from a dilemma between inaccurate temporal alignment and error propagation for motion estimation and compensation (ME/MC).…
EV-NVC: Efficient Variable bitrate Neural Video Compression
Yongcun Hu, Yingzhen Zhai, Jixiang Luo +4
Training neural video codec (NVC) with variable rate is a highly challenging task due to its complex training strategies and model structure. In this paper, we train an efficient v…
Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation
Yuyang Huang, Yabo Chen, Junyu Zhou +5
Source-free domain adaptation (SFDA) is a challenging task that tackles domain shifts using only a pre-trained source model and unlabeled target data. Existing SFDA methods are res…
GranViT: A Fine-Grained Vision Model With Autoregressive Perception For MLLMs
Guanghao Zheng, Bowen Shi, Mingxing Xu +8
Vision encoders are indispensable for allowing impressive performance of Multi-modal Large Language Models (MLLMs) in vision language tasks such as visual question answering and re…
OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation
Han Li, Xinyu Peng, Yaoming Wang +7
We introduce OneCAT, a unified multimodal model that seamlessly integrates understanding, generation, and editing within a novel, pure decoder-only transformer architecture. Our fr…
3DGabSplat: 3D Gabor Splatting for Frequency-adaptive Radiance Field Rendering
Junyu Zhou, Yuyang Huang, Wenrui Dai +5
Recent prominence in 3D Gaussian Splatting (3DGS) has enabled real-time rendering while maintaining high-fidelity novel view synthesis. However, 3DGS resorts to the Gaussian functi…
METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models
Yuchen Liu, Yaoming Wang, Bowen Shi +5
Vision encoders serve as the cornerstone of multimodal understanding. Single-encoder architectures like CLIP exhibit inherent constraints in generalizing across diverse multimodal…
ABC: Adaptive BayesNet Structure Learning for Computational Scalable Multi-task Image Compression
Yufeng Zhang, Wenrui Dai, Hang Yu +4
Neural Image Compression (NIC) has revolutionized image compression with its superior rate-distortion performance and multi-task capabilities, supporting both human visual percepti…
Noise Conditional Variational Score Distillation
Xinyu Peng, Ziyang Zheng, Yaoming Wang +6
We propose Noise Conditional Variational Score Distillation (NCVSD), a novel method for distilling pretrained diffusion models into generative denoisers. We achieve this by reveali…
HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimation
Hongwei Zheng, Han Li, Wenrui Dai +4
Existing 2D-to-3D human pose estimation (HPE) methods struggle with the occlusion issue by enriching information like temporal and visual cues in the lifting stage. In this paper,…
On Disentangled Training for Nonlinear Transform in Learned Image Compression
Han Li, Shaohui Li, Wenrui Dai +5
Learned image compression (LIC) has demonstrated superior rate-distortion (R-D) performance compared to traditional codecs, but is challenged by training inefficiency that could in…