11 papers
VC-Tooler: Learning Compositional and Adaptive Visual Tool Use
Yizheng Wu, Jiashen Hua, Bing Deng +1
Agentic multimodal reasoning extends passive image understanding by allowing VLMs to actively acquire and refine visual evidence through visual tool interactions. Effective visual…
Illuminating Visual Identity in Universal Multimodal Embeddings
Jiawei Cao, Junyi Feng, Jiashen Hua +5
Universal Multimodal Embeddings (UMEs) aim to unify various modalities and tasks into a shared representation space. In recent years, this field has witnessed substantial progress…
EchoStyle: Unlocking High-Fidelity Video Stylization with Reverse Data Synthesis
Huaqiu Li, Jiahao Wang, Sijia Cai +4
While image stylization has been studied extensively, video stylization remains a critical and largely unsolved challenge in the field of intelligent content creation. Existing met…
AnyID: Ultra-Fidelity Universal Identity-Preserving Video Generation from Any Visual References
Jiahao Wang, Hualian Sheng, Sijia Cai +5
Identity-preserving video generation offers powerful tools for creative expression, allowing users to customize videos featuring their beloved characters. However, prevailing metho…
Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMs
Zhiyu Pan, Yizheng Wu, Jiashen Hua +5
Reasoning has emerged as a key capability of large language models. In linguistic tasks, this capability can be enhanced by self-improving techniques that refine reasoning paths fo…
EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion Transformer
Yuxiao Yang, Hualian Sheng, Sijia Cai +6
Video generation models have advanced significantly, yet they still struggle to synthesize complex human movements due to the high degrees of freedom in human articulation. This li…
EchoShot: Multi-Shot Portrait Video Generation
Jiahao Wang, Hualian Sheng, Sijia Cai +5
Video diffusion models substantially boost the productivity of artistic workflows with high-quality portrait video generative capacity. However, prevailing pipelines are primarily…
Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactions
He Zhu, Quyu Kong, Kechun Xu +5
Grounding 3D object affordance is a task that locates objects in 3D space where they can be manipulated, which links perception and action for embodied intelligence. For example, f…
PerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Models
Jinhua Zhang, Hualian Sheng, Sijia Cai +6
Controllable generation is considered a potentially vital approach to address the challenge of annotating 3D data, and the precision of such controllable generation becomes particu…
CT3D++: Improving 3D Object Detection with Keypoint-induced Channel-wise Transformer
Hualian Sheng, Sijia Cai, Na Zhao +4
The field of 3D object detection from point clouds is rapidly advancing in computer vision, aiming to accurately and efficiently detect and localize objects in three-dimensional sp…
RoScenes: A Large-scale Multi-view 3D Dataset for Roadside Perception
Xiaosu Zhu, Hualian Sheng, Sijia Cai +7
We introduce RoScenes, the largest multi-view roadside perception dataset, which aims to shed light on the development of vision-centric Bird's Eye View (BEV) approaches for more c…