135 citations · 408 across the 38 of their papers we have counts for
22 papers · 1 filter
CineWeaver: Training-Free Reference-Controllable Multi-Shot Long Video Generation for Cinematic Storytelling
Yuyang Huang, Yabo Chen, Wenrui Dai +6
Cinematic video generation is challenging for text-to-video diffusion models due to concurrent requirements on multi-shot generation, fine-grained controllability over characters a…
Towards Holistic Modeling for Video Frame Interpolation with Auto-regressive Diffusion Transformers
Xinyu Peng, Han Li, Yuyang Huang +7
Existing video frame interpolation (VFI) methods often adopt a frame-centric approach, processing videos as independent short segments (e.g., triplets), which leads to temporal inc…
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).…
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…
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…
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,…
Point Cloud Denoising With Fine-Granularity Dynamic Graph Convolutional Networks
Wenqiang Xu, Wenrui Dai, Duoduo Xue +4
Due to limitations in acquisition equipment, noise perturbations often corrupt 3-D point clouds, hindering down-stream tasks such as surface reconstruction, rendering, and further…
Point Cloud Resampling with Learnable Heat Diffusion
Wenqiang Xu, Wenrui Dai, Duoduo Xue +4
Generative diffusion models have shown empirical successes in point cloud resampling, generating a denser and more uniform distribution of points from sparse or noisy 3D point clou…
Image Compression for Machine and Human Vision with Spatial-Frequency Adaptation
Han Li, Shaohui Li, Shuangrui Ding +5
Image compression for machine and human vision (ICMH) has gained increasing attention in recent years. Existing ICMH methods are limited by high training and storage overheads due…
Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariance
Xinyu Peng, Ziyang Zheng, Wenrui Dai +4
Recent diffusion models provide a promising zero-shot solution to noisy linear inverse problems without retraining for specific inverse problems. In this paper, we reveal that rece…
UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding
Bowen Shi, Peisen Zhao, Zichen Wang +8
Vision-language foundation models, represented by Contrastive Language-Image Pre-training (CLIP), have gained increasing attention for jointly understanding both vision and textual…
Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners
Bowen Shi, Xiaopeng Zhang, Yaoming Wang +5
Representation learning has been evolving from traditional supervised training to Contrastive Learning (CL) and Masked Image Modeling (MIM). Previous works have demonstrated their…
Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation
Han Li, Bowen Shi, Wenrui Dai +7
There has been a recent surge of interest in introducing transformers to 3D human pose estimation (HPE) due to their powerful capabilities in modeling long-term dependencies. Howev…
Hierarchical Spherical CNNs with Lifting-based Adaptive Wavelets for Pooling and Unpooling
Mingxing Xu, Chenglin Li, Wenrui Dai +4
Pooling and unpooling are two essential operations in constructing hierarchical spherical convolutional neural networks (HS-CNNs) for comprehensive feature learning in the spherica…
Hybrid ISTA: Unfolding ISTA With Convergence Guarantees Using Free-Form Deep Neural Networks
Ziyang Zheng, Wenrui Dai, Duoduo Xue +3
It is promising to solve linear inverse problems by unfolding iterative algorithms (e.g., iterative shrinkage thresholding algorithm (ISTA)) as deep neural networks (DNNs) with lea…
Hierarchical Graph Networks for 3D Human Pose Estimation
Han Li, Bowen Shi, Wenrui Dai +7
Recent 2D-to-3D human pose estimation works tend to utilize the graph structure formed by the topology of the human skeleton. However, we argue that this skeletal topology is too s…
Multi-dataset Pretraining: A Unified Model for Semantic Segmentation
Bowen Shi, Xiaopeng Zhang, Haohang Xu +4
Collecting annotated data for semantic segmentation is time-consuming and hard to scale up. In this paper, we for the first time propose a unified framework, termed as Multi-Datase…
AP-Loss for Accurate One-Stage Object Detection
Kean Chen, Weiyao Lin, Jianguo Li +3
One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background cla…
Group Re-Identification with Multi-grained Matching and Integration
Weiyao Lin, Yuxi Li, Hao Xiao +5
The task of re-identifying groups of people underdifferent camera views is an important yet less-studied problem.Group re-identification (Re-ID) is a very challenging task sinceit…
Towards Accurate One-Stage Object Detection with AP-Loss
Kean Chen, Jianguo Li, Weiyao Lin +6
One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background cla…