8 papers
StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding
Keming Wu, Baoyi Wang, Kaichen Zhang +7
Streaming video understanding demands direct responses from the causally observed prefix of an unfolding video. Existing systems add inference-time memory, retrieval, and compressi…
MVFusion-GS: Motion-Variance Guided Temporal Attention for High-Quality Dynamic Gaussian Splatting
Jianwei Hu, Tingxuan Huang, Hengyu Zhou +4
3D Gaussian Splatting (3DGS) enables real-time novel view synthesis for static scenes. Extending it to dynamic scenes via deformation fields has recently attracted significant atte…
CO-EVO: Co-evolving Semantic Anchoring and Style Diversification for Federated DG-ReID
Fengchun Zhang, Qiang Ma, Liuyu Xiang +3
Federated domain generalization for person re-identification (FedDG-ReID) aims to collaboratively train a pedestrian retrieval model across multiple decentralized source domains su…
Mango-GS: Enhancing Spatio-Temporal Consistency in Dynamic Scenes Reconstruction using Multi-Frame Node-Guided 4D Gaussian Splatting
Tingxuan Huang, Haowei Zhu, Jun-hai Yong +2
Reconstructing dynamic 3D scenes with photorealistic detail and strong temporal coherence remains a significant challenge. Existing Gaussian splatting approaches for dynamic scene…
TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion Acceleration
Haowei Zhu, Tingxuan Huang, Xing Wang +7
Diffusion models achieve strong generative performance but remain slow at inference due to the need for repeated full-model denoising passes. We present Token-Adaptive Predictor (T…
DriveScape: Towards High-Resolution Controllable Multi-View Driving Video Generation
Wei Wu, Xi Guo, Weixuan Tang +4
Recent advancements in generative models have provided promising solutions for synthesizing realistic driving videos, which are crucial for training autonomous driving perception m…
Mask-adaptive Gated Convolution and Bi-directional Progressive Fusion Network for Depth Completion
Tingxuan Huang, Jiacheng Miao, Shizhuo Deng +2
Depth completion is a critical task for handling depth images with missing pixels, which can negatively impact further applications. Recent approaches have utilized Convolutional N…
AGG-Net: Attention Guided Gated-convolutional Network for Depth Image Completion
Dongyue Chen, Tingxuan Huang, Zhimin Song +2
Recently, stereo vision based on lightweight RGBD cameras has been widely used in various fields. However, limited by the imaging principles, the commonly used RGB-D cameras based…