34 citations · 56 across the 11 of their papers we have counts for
15 papers
SearchWorld: Spatial Value-Grounded Imagination for UAV Object Search via World Models
Yatai Ji, Zhengqiu Zhu, Yong Zhao +5
Autonomous unmanned aerial vehicle (UAV) object search involves a closed loop of perception, decision-making, and action under partial observability. Urban environments pose severa…
S2Tok: Streaming 3D Gaussian Reconstruction with Persistent Spatial Tokens
Fang Li, Jiraphon Yenphraphai, Quentin Herau +5
Streaming 3D reconstruction requires more than a sequence of geometric predictions: it requires a persistent scene state that can incorporate new evidence and remain renderable as…
Building Rome from a Single Image
Jiraphon Yenphraphai, Fang Li, Tianshuo Xu +5
Single-image scene generation aims to produce a complete 3D scene mesh from a single image, including surfaces the camera did not observe. While pretrained 3D object generators enc…
LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation
Bo Jiang, Depu Meng, Yihan Hu +3
Modern video generators produce visually compelling clips but still struggle with physical and motion consistency, limiting their use as reliable world simulators. Existing remedie…
Teaching Video Generators to Remember: Eliciting Dynamic Memory for Out-of-Sight State Evolution
Tianshuo Xu, Yichen Xie, Depu Meng +5
Video world models should maintain evolving states when evidence is unobserved, yet current generators often freeze hidden states upon interruption. This is not simply a capacity p…
SpectralSplat: Appearance-Disentangled Feed-Forward Gaussian Splatting for Driving Scenes
Quentin Herau, Tianshuo Xu, Depu Meng +5
Feed-forward 3D Gaussian Splatting methods have achieved impressive reconstruction quality for autonomous driving scenes, yet they entangle scene geometry with transient appearance…
URoPE: Universal Relative Position Embedding across Geometric Spaces
Yichen Xie, Depu Meng, Chensheng Peng +4
Relative position embedding has become a standard mechanism for encoding positional information in Transformers. However, existing formulations are typically limited to a fixed geo…
Evaluating Roadside Perception for Autonomous Vehicles: Insights from Field Testing
Rusheng Zhang, Depu Meng, Shengyin Shen +4
Roadside perception systems are increasingly crucial in enhancing traffic safety and facilitating cooperative driving for autonomous vehicles. Despite rapid technological advanceme…
MSight: An Edge-Cloud Infrastructure-based Perception System for Connected Automated Vehicles
Rusheng Zhang, Depu Meng, Shengyin Shen +3
As vehicular communication and networking technologies continue to advance, infrastructure-based roadside perception emerges as a pivotal tool for connected automated vehicle (CAV)…
Robust Roadside Perception: an Automated Data Synthesis Pipeline Minimizing Human Annotation
Rusheng Zhang, Depu Meng, Lance Bassett +3
Recently, advancements in vehicle-to-infrastructure communication technologies have elevated the significance of infrastructure-based roadside perception systems for cooperative dr…
ROCO: A Roundabout Traffic Conflict Dataset
Depu Meng, Owen Sayer, Rusheng Zhang +3
Traffic conflicts have been studied by the transportation research community as a surrogate safety measure for decades. However, due to the rarity of traffic conflicts, collecting…
CORE: Consistent Representation Learning for Face Forgery Detection
Yunsheng Ni, Depu Meng, Changqian Yu +3
Face manipulation techniques develop rapidly and arouse widespread public concerns. Despite that vanilla convolutional neural networks achieve acceptable performance, they suffer f…
Conditional DETR for Fast Training Convergence
Depu Meng, Xiaokang Chen, Zejia Fan +5
The recently-developed DETR approach applies the transformer encoder and decoder architecture to object detection and achieves promising performance. In this paper, we handle the c…
Bottom-Up Human Pose Estimation by Ranking Heatmap-Guided Adaptive Keypoint Estimates
Ke Sun, Zigang Geng, Depu Meng +4
The typical bottom-up human pose estimation framework includes two stages, keypoint detection and grouping. Most existing works focus on developing grouping algorithms, e.g., assoc…
Deep Convolutional Neural Networks with Merge-and-Run Mappings
Liming Zhao, Jingdong Wang, Xi Li +2
A deep residual network, built by stacking a sequence of residual blocks, is easy to train, because identity mappings skip residual branches and thus improve information flow. To f…