5 papers
Towards Highly-Constrained Human Motion Generation with Retrieval-Guided Diffusion Noise Optimization
Hanchao Liu, Fang-Lue Zhang, Shining Zhang +2
Generating human motion that satisfies customized zero-shot goal functions, enabling applications such as controllable character animation and behavior synthesis for virtual agents…
Beyond Inpainting: Unleash 3D Understanding for Precise Camera-Controlled Video Generation
Dong-Yu Chen, Yixin Guo, Shuojin Yang +2
Camera control has been extensively studied in conditioned video generation; however, performing precisely altering the camera trajectories while faithfully preserving the video co…
NeuralSSD: A Neural Solver for Signed Distance Surface Reconstruction
Zi-Chen Xi, Jiahui Huang, Hao-Xiang Chen +4
We proposed a generalized method, NeuralSSD, for reconstructing a 3D implicit surface from the widely-available point cloud data. NeuralSSD is a solver-based on the neural Galerkin…
Recovering Complete Actions for Cross-dataset Skeleton Action Recognition
Hanchao Liu, Yujiang Li, Tai-Jiang Mu +1
Despite huge progress in skeleton-based action recognition, its generalizability to different domains remains a challenging issue. In this paper, to solve the skeleton action gener…
Theoretically Achieving Continuous Representation of Oriented Bounding Boxes
Zi-Kai Xiao, Guo-Ye Yang, Xue Yang +3
Considerable efforts have been devoted to Oriented Object Detection (OOD). However, one lasting issue regarding the discontinuity in Oriented Bounding Box (OBB) representation rema…