Make-A-Shape: a Ten-Million-scale 3D Shape Model

no code implementations • 20 Jan 2024 • Ka-Hei Hui, Aditya Sanghi, Arianna Rampini, Kamal Rahimi Malekshan, Zhengzhe Liu, Hooman Shayani, Chi-Wing Fu

We then make the representation generatable by a diffusion model by devising the subband coefficients packing scheme to layout the representation in a low-resolution grid.

Generalizable Pose Estimation Using Implicit Scene Representations

no code implementations • 26 May 2023 • Vaibhav Saxena, Kamal Rahimi Malekshan, Linh Tran, Yotto Koga

Most widely used methods learn to infer the object pose in a discriminative setup where the model filters useful information to infer the exact pose of the object.

Density Estimation Object +1

Reconstructing editable prismatic CAD from rounded voxel models

no code implementations • 2 Sep 2022 • Joseph G. Lambourne, Karl D. D. Willis, Pradeep Kumar Jayaraman, Longfei Zhang, Aditya Sanghi, Kamal Rahimi Malekshan

Reverse Engineering a CAD shape from other representations is an important geometric processing step for many downstream applications.

CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation

1 code implementation • CVPR 2022 • Aditya Sanghi, Hang Chu, Joseph G. Lambourne, Ye Wang, Chin-Yi Cheng, Marco Fumero, Kamal Rahimi Malekshan

Generating shapes using natural language can enable new ways of imagining and creating the things around us.

Text-to-Image Generation Text-to-Shape Generation +1