|
DreamFace: Progressive Generation of Animatable 3D Faces under Text Guidance
We present a progressive scheme to generate personalized 3D faces with text guidance, which can customize 3D facial assets with the desired shape and physically-based textures, as well as empowered animation capabilities.
ACM Transactions on Graphics (Proc. of SIGGRAPH), 2023.
[Paper]
[Project Page]
[Video]
[bibtex]
|
|
|
|
HACK: Learning a Parametric Head and Neck Model for High-fidelity Animation
We present a novel parametric model for constructing the cervical region of digital humans which tackles the full spectrum of neck and larynx motions to offer more personalized and anatomically-consistent controls
ACM Transactions on Graphics (Proc. of SIGGRAPH), 2023.
[Paper]
[Project Page]
[Video]
[bibtex]
|
|
|
|
Free-bloom: Zero-shot text-to-video generator with llm director and ldm animator
We propose a novel zero-shot and training-free text-to-video approach, which mainly focuses on improving the narrative of the progression of events by harnessing the knowledge from the pre-trained LLM and LDM.
Neural Information Processing Systems (NeurIPS), 2023.
[Paper]
[Project Page]
[Video]
|
|
|
|
StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset
We propose a novel scheme to encode and capture highly detailed 3D human-object spatial relations from single-view images using Human-Object Offset, with a Stacked Normalizing Flow to infer the posterior distribution.
International Joint Conferences on Artificial Intelligence Organization (IJCAI), 2023.
[Paper]
[Project Page]
[Video]
[bibtex]
|
|
|
|
NeReF: Neural Refractive Field for Fluid Surface Reconstruction and Rendering
We propose a neural scene representation for refractive fluid surfaces, which can render the refraction effect directly from the implicit representation.
International Conference on Computational Photography (ICCP), 2023.
[Paper]
[Project Page]
[Video]
[bibtex]
|
|
|
|
ReRF: Neural Residual Radiance Fields for Streamably Free-Viewpoint Videos
We present a novel neural modeling technique that we call the Residual Radiance Field or ReRF as a highly compact representation of dynamic scenes, enabling high-quality FVV streaming and rendering.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
[Paper]
[Project Page]
[Video]
[bibtex]
|
|
|
|
HumanGen: Generating Human Radiance Fields with Explicit Priors
We present a novel neural scheme to generate high-quality radiance fields for 3D humans, by explicitly utilizing richer priors from the top-tier 2D generation and 3D reconstruction schemes.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
[Paper]
[Project Page]
[Video]
[bibtex]
|
|
|
|
Instant-NVR: Instant Neural Volumetric Rendering for Human-object Interactions from RGBD Stream
We present an instant neural volumetric rendering system for human-object interacting scenes using a single RGBD camera, via on-the-fly generation of the radiance fields for both the rigid object and dynamic human.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
[Paper]
[Project Page]
[Video]
[bibtex]
|
|
|
|
NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions
We present a neural pipeline that takes multi-view dome capture as inputs and conducts accurate 3D modeling and photo-realistic rendering of complex human-object interaction.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
[Paper]
[Project Page]
[Video]
[bibtex]
|
|
|
|
Relightable Neural Human Assets from Multi-view Gradient Illuminations
We contribute a new 3D human dataset that contains more than 2,000 high-quality human assets captured under both multi-view and multi-illumination settings.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
[Paper]
[Project Page]
[Video]
[bibtex]
|
|
|
|
SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments
We present a novel scene-aware dataset collected in large urban environments to facilitate the research of global human pose estimation with human-scene interaction in the wild.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
[Paper]
[Project Page]
[Video]
[bibtex]
|
|
|
|
CIMI4D: A Large Multimodal Climbing Motion Dataset under Human-scene Interactions
We contribute a large rock climbing motion datasets, consiting of around 180,000 frames of inertial measurements, LiDAR point clouds, RGB videos, static point cloud scenes, and reconstructed scene meshes.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
[Paper]
[Project Page]
[Video]
[bibtex]
|
|
|
|
LiDAR-aid Inertial Poser: Large-scale Human Motion Capture by Sparse Inertial and LiDAR Sensors
We present a novel approach to capture challenging human motionsin large-scale scenarios accurately using a light-weight hardware setup with only single LiDAR and 4 IMUs.
IEEE Transactions on Visualization and Computer Graphics (Proc. IEEE VR), 2023.
[Paper]
[Project Page (Coming soon)]
[Video]
[bibtex]
|
|
|
|
HybridCap: Inertia-aid Monocular Capture of Challenging Human Motions
We present a high-quality inertia-aid monocular approach for capturing challenging human motions, using a light-weight hybrid setting with a single RGB camera and sparse IMUs.
Proceedings of the the Association for the Advance of Artificial Intelligence (AAAI), 2023.
[Paper]
[Project Page (Coming soon)]
[Video]
[bibtex]
|
|
|
|
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation
We propose an inverse kinematics optimization layer that leverages the strengths of both optimization and regression for end-to-end 3D human pose and shape estimation.
Proceedings of the the Association for the Advance of Artificial Intelligence (AAAI), 2023.
[Paper]
[Project Page]
[Video]
[bibtex]
|
|
|
|
Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes
we propose a monocular camera and single LiDAR-based method for 3D multi-person pose estimation in large-scale scenes, which is easy to deploy and insensitive to light.
Proceedings of the the Association for the Advance of Artificial Intelligence (AAAI), 2023.
[Paper]
[Project Page]
[Video (Coming soon)]
[bibtex]
|
|
|