260 citations · 276 across the 37 of their papers we have counts for
23 papers · 1 filter
Spatial-Aware Reduction Framework: Towards Efficient and Faithful Visual State Space Models
Jindi Lv, Aoyu Li, Yuhao Zhou +6
Mamba demonstrates strong efficiency in modeling long visual sequences. However, when token reduction is applied to structurally enhanced Mamba variants, these models exhibit a sev…
ScoutVLA: UAV-Centric Active Perception via a Dual-Expert VLA Model for Open-World Embodied Question Answering
Wenhao Lu, Zhengqiu Zhu, Xiaofeng Wang +7
Aerial Embodied Question Answering (EQA) requires Unmanned Aerial Vehicles (UAVs) to actively perceive the environment and answer natural language questions. Existing outdoor EQA s…
ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignment
Mingyu Dong, Chong Xia, Mingyuan Jia +4
Humans exhibit an innate capacity to rapidly perceive and segment objects from video observations, and even mentally assemble them into structured 3D scenes. Replicating such capab…
ReconPhys: Reconstruct Appearance and Physical Attributes from Single Video
Boyuan Wang, Xiaofeng Wang, Yongkang Li +9
Reconstructing non-rigid objects with physical plausibility remains a significant challenge. Existing approaches leverage differentiable rendering for per-scene optimization, recov…
FlashSign: Pose-Free Guidance for Efficient Sign Language Video Generation
Liuzhou Zhang, Zeyu Zhang, Biao Wu +10
Sign language plays a crucial role in bridging communication gaps between the deaf and hard-of-hearing communities. However, existing sign language video generation models often re…
UniDriveDreamer: A Single-Stage Multimodal World Model for Autonomous Driving
Guosheng Zhao, Yaozeng Wang, Xiaofeng Wang +10
World models have demonstrated significant promise for data synthesis in autonomous driving. However, existing methods predominantly concentrate on single-modality generation, typi…
ReconDreamer-RL: Enhancing Reinforcement Learning via Diffusion-based Scene Reconstruction
Chaojun Ni, Guosheng Zhao, Xiaofeng Wang +6
Reinforcement learning for training end-to-end autonomous driving models in closed-loop simulations is gaining growing attention. However, most simulation environments differ signi…
GigaVideo-1: Advancing Video Generation via Automatic Feedback with 4 GPU-Hours Fine-Tuning
Xiaoyi Bao, Jindi Lv, Xiaofeng Wang +6
Recent progress in diffusion models has greatly enhanced video generation quality, yet these models still require fine-tuning to improve specific dimensions like instance preservat…
Motion-R1: Enhancing Motion Generation with Decomposed Chain-of-Thought and RL Binding
Runqi Ouyang, Haoyun Li, Zhenyuan Zhang +6
Text-to-Motion generation has become a fundamental task in human-machine interaction, enabling the synthesis of realistic human motions from natural language descriptions. Although…
RoboTransfer: Controllable Geometry-Consistent Video Diffusion for Manipulation Policy Transfer
Liu Liu, Xiaofeng Wang, Guosheng Zhao +7
The goal of general-purpose robotics is to create agents that can seamlessly adapt to and operate in diverse, unstructured human environments. Imitation learning has become a key p…
WonderTurbo: Generating Interactive 3D World in 0.72 Seconds
Chaojun Ni, Xiaofeng Wang, Zheng Zhu +7
Interactive 3D generation is gaining momentum and capturing extensive attention for its potential to create immersive virtual experiences. However, a critical challenge in current…
HumanDreamer-X: Photorealistic Single-image Human Avatars Reconstruction via Gaussian Restoration
Boyuan Wang, Runqi Ouyang, Xiaofeng Wang +8
Single-image human reconstruction is vital for digital human modeling applications but remains an extremely challenging task. Current approaches rely on generative models to synthe…
HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation
Boyuan Wang, Xiaofeng Wang, Chaojun Ni +9
Human-motion video generation has been a challenging task, primarily due to the difficulty inherent in learning human body movements. While some approaches have attempted to drive…
ReconDreamer++: Harmonizing Generative and Reconstructive Models for Driving Scene Representation
Guosheng Zhao, Xiaofeng Wang, Chaojun Ni +4
Combining reconstruction models with generative models has emerged as a promising paradigm for closed-loop simulation in autonomous driving. For example, ReconDreamer has demonstra…
ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration
Chaojun Ni, Guosheng Zhao, Xiaofeng Wang +13
Closed-loop simulation is crucial for end-to-end autonomous driving. Existing sensor simulation methods (e.g., NeRF and 3DGS) reconstruct driving scenes based on conditions that cl…
DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation
Guosheng Zhao, Chaojun Ni, Xiaofeng Wang +9
Closed-loop simulation is essential for advancing end-to-end autonomous driving systems. Contemporary sensor simulation methods, such as NeRF and 3DGS, rely predominantly on condit…
DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation
Guosheng Zhao, Xiaofeng Wang, Zheng Zhu +4
World models have demonstrated superiority in autonomous driving, particularly in the generation of multi-view driving videos. However, significant challenges still exist in genera…
WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens
Xiaofeng Wang, Zheng Zhu, Guan Huang +3
World models play a crucial role in understanding and predicting the dynamics of the world, which is essential for video generation. However, existing world models are confined to…
CompletionFormer: Depth Completion with Convolutions and Vision Transformers
Zhang Youmin, Guo Xianda, Poggi Matteo +3
Given sparse depths and the corresponding RGB images, depth completion aims at spatially propagating the sparse measurements throughout the whole image to get a dense depth predict…
Detachable Novel Views Synthesis of Dynamic Scenes Using Distribution-Driven Neural Radiance Fields
Boyu Zhang, Wenbo Xu, Zheng Zhu +1
Representing and synthesizing novel views in real-world dynamic scenes from casual monocular videos is a long-standing problem. Existing solutions typically approach dynamic scenes…
Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark
Xiaofeng Wang, Zheng Zhu, Yunpeng Zhang +5
In recent years, vision-centric perception has flourished in various autonomous driving tasks, including 3D detection, semantic map construction, motion forecasting, and depth esti…
Crafting Monocular Cues and Velocity Guidance for Self-Supervised Multi-Frame Depth Learning
Xiaofeng Wang, Zheng Zhu, Guan Huang +4
Self-supervised monocular methods can efficiently learn depth information of weakly textured surfaces or reflective objects. However, the depth accuracy is limited due to the inher…
MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer
Chaoqiang Zhao, Youmin Zhang, Matteo Poggi +6
Self-supervised monocular depth estimation is an attractive solution that does not require hard-to-source depth labels for training. Convolutional neural networks (CNNs) have recen…