Search Results for author:
Found 11 papers, 6 papers with code
PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models
Current benchmarks for evaluating the reasoning capabilities of Large Language Models (LLMs) face significant limitations: task oversimplification, data contamination, and flawed evaluation items.
ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness
We propose Equivariant Tightness Fitting for Clothed Humans, or ETCH, a novel pipeline that estimates cloth-to-body surface mapping through locally approximate SE(3) equivariance, encoding tightness as displacement vectors from the cloth surface to the underlying body.
Deformable Gaussian Splatting for Efficient and High-Fidelity Reconstruction of Surgical Scenes
To address these challenges, we introduce EH-SurGS, an efficient and high-fidelity reconstruction algorithm for deformable surgical scenes.
StrandHead: Text to Strand-Disentangled 3D Head Avatars Using Hair Geometric Priors
We propose StrandHead, a novel text to 3D head avatar generation method capable of generating disentangled 3D hair with strand representation.
DreamMapping: High-Fidelity Text-to-3D Generation via Variational Distribution Mapping
Score Distillation Sampling (SDS) has emerged as a prevalent technique for text-to-3D generation, enabling 3D content creation by distilling view-dependent information from text-to-2D guidance.
DEGAS: Detailed Expressions on Full-Body Gaussian Avatars
We also propose an audio-driven extension of our method with the help of 2D talking faces, opening new possibilities for interactive AI agents.
HeadEvolver: Text to Head Avatars via Expressive and Attribute-Preserving Mesh Deformation
Extensive experiments demonstrate that our framework can generate diverse and expressive head avatars with high-quality meshes that artists can easily manipulate in graphics software, facilitating downstream applications such as efficient asset creation and animation with preserved attributes.
MagicScroll: Nontypical Aspect-Ratio Image Generation for Visual Storytelling via Multi-Layered Semantic-Aware Denoising
Visual storytelling often uses nontypical aspect-ratio images like scroll paintings, comic strips, and panoramas to create an expressive and compelling narrative.
MLP-AMDC: An MLP Architecture for Adaptive-Mask-based Dual-Camera snapshot hyperspectral imaging
In order to improve the inference speed of the reconstruction network, this paper proposes An MLP Architecture for Adaptive-Mask-based Dual-Camera (MLP-AMDC) to replace the transformer structure of the network.
DMDC: Dynamic-mask-based dual camera design for snapshot Hyperspectral Imaging
First, the system learns the spatial feature distribution of the scene based on the RGB images, then instructs the SLM to encode each scene, and finally sends both RGB and CASSI images to the network for reconstruction.
SST-ReversibleNet: Reversible-prior-based Spectral-Spatial Transformer for Efficient Hyperspectral Image Reconstruction
The reconstruction subnet in the network then learns the mapping of the residuals to the true values to improve reconstruction accuracy.
