9 papers
Quartet of Diffusions: Structure-Aware Point Cloud Generation through Part and Symmetry Guidance
Chenliang Zhou, Fangcheng Zhong, Weihao Xia +3
We introduce the Quartet of Diffusions, a structure-aware point cloud generation framework that explicitly models part composition and symmetry. Unlike prior methods that treat sha…
Features Emerge as Discrete States: The First Application of SAEs to 3D Representations
Albert Miao, Chenliang Zhou, Jiawei Zhou +1
Sparse Autoencoders (SAEs) are a powerful dictionary learning technique for decomposing neural network activations, translating the hidden state into human ideas with high semantic…
Self-Supervised Implicit Attention Priors for Point Cloud Reconstruction
Kyle Fogarty, Chenyue Cai, Jing Yang +2
Recovering high-quality surfaces from irregular point cloud is ill-posed unless strong geometric priors are available. We introduce an implicit self-prior approach that distills a…
Twist and Compute: The Cost of Pose in 3D Generative Diffusion
Kyle Fogarty, Jack Foster, Boqiao Zhang +2
Despite their impressive results, large-scale image-to-3D generative models remain opaque in their inductive biases. We identify a significant limitation in image-conditioned 3D ge…
CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation
Chenliang Zhou, Fangcheng Zhong, Cengiz Oztireli
Recently introduced Contrastive Language-Image Pre-Training (CLIP) bridges images and text by embedding them into a joint latent space. This opens the door to ample literature that…
Best Foot Forward: Robust Foot Reconstruction in-the-wild
Kyle Fogarty, Jing Yang, Chayan Kumar Patodi +5
Accurate 3D foot reconstruction is crucial for personalized orthotics, digital healthcare, and virtual fittings. However, existing methods struggle with incomplete scans and anatom…