7 papers
Progressive Pose-Guided 4D Animal Reconstruction from Monocular Video
Siyuan Li, Weiying Chen, Yilin Wang +3
Reconstructing 4D animals from monocular videos is challenging due to large inter-species variation, complex articulations, and the lack of reliable templates. Existing approaches…
PICS: Pairwise Image Compositing with Spatial Interactions
Hang Zhou, Xinxin Zuo, Sen Wang +1
Despite strong single-turn performance, diffusion-based image compositing often struggles to preserve coherent spatial relations in pairwise or sequential edits, where subsequent i…
Highly Efficient 3D Human Pose Tracking from Events with Spiking Spatiotemporal Transformer
Shihao Zou, Yuxuan Mu, Wei Ji +5
Event camera, as an asynchronous vision sensor capturing scene dynamics, presents new opportunities for highly efficient 3D human pose tracking. Existing approaches typically adopt…
MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer
Yilin Wang, Chuan Guo, Yuxuan Mu +5
Generative masked transformers have demonstrated remarkable success across various content generation tasks, primarily due to their ability to effectively model large-scale dataset…
BOOTPLACE: Bootstrapped Object Placement with Detection Transformers
Hang Zhou, Xinxin Zuo, Rui Ma +1
In this paper, we tackle the copy-paste image-to-image composition problem with a focus on object placement learning. Prior methods have leveraged generative models to reduce the r…
Lifelong Learning with Task-Specific Adaptation: Addressing the Stability-Plasticity Dilemma
Ruiyu Wang, Sen Wang, Xinxin Zuo +1
Lifelong learning (LL) aims to continuously acquire new knowledge while retaining previously learned knowledge. A central challenge in LL is the stability-plasticity dilemma, which…