6 papers · 1 filter
SeeClear: Reliable Transparent Object Depth Estimation via Generative Opacification
Xiaoying Wang, Yumeng He, Jingkai Shi +4
Monocular depth estimation remains challenging for transparent objects, where refraction and transmission are difficult to model and break the appearance assumptions used by depth…
DressWild: Feed-Forward Pose-Agnostic Garment Sewing Pattern Generation from In-the-Wild Images
Zeng Tao, Ying Jiang, Yunuo Chen +7
Recent advances in garment pattern generation have shown promising progress. However, existing feed-forward methods struggle with diverse poses and viewpoints, while optimization-b…
SPARK: Sim-ready Part-level Articulated Reconstruction with VLM Knowledge
Yumeng He, Ying Jiang, Jiayin Lu +2
Articulated 3D objects are critical for embodied AI, robotics, and interactive scene understanding, yet creating simulation-ready assets remains labor-intensive and requires expert…
Birth of a Painting: Differentiable Brushstroke Reconstruction
Ying Jiang, Jiayin Lu, Yunuo Chen +4
Painting embodies a unique form of visual storytelling, where the creation process is as significant as the final artwork. Although recent advances in generative models have enable…
Dress-1-to-3: Single Image to Simulation-Ready 3D Outfit with Diffusion Prior and Differentiable Physics
Xuan Li, Chang Yu, Wenxin Du +5
Recent advances in large models have significantly advanced image-to-3D reconstruction. However, the generated models are often fused into a single piece, limiting their applicabil…
PhysMotion: Physics-Grounded Dynamics From a Single Image
Xiyang Tan, Ying Jiang, Xuan Li +4
We introduce PhysMotion, a novel framework that leverages principled physics-based simulations to guide intermediate 3D representations generated from a single image and input cond…