Your browser does not support the video tag.
Geometry in Style: 3D Stylization via Surface Normal Deformation
Nam Anh Dinh ,
Itai Lang ,
Hyunwoo Kim ,
Oded Stein ,
Rana Hanocka
CVPR 2025
project page
/
paper
/
code
Geometry in Style produces an identity-preserving stylization of mesh geonetry deforming the surface normals of the input shape.
Your browser does not support the video tag.
iSeg: Interactive 3D Segmentation via Interactive Attention
Itai Lang ,
Fei Xu ,
Dale Decatur ,
Sudarshan Babu ,
Rana Hanocka
SIGGRAPH Asia 2024
project page
/
arXiv
/
code
We propose an interactive segmentation technique for 3D shapes that produces fine-grained customized segmentations based on user clicks.
Your browser does not support the video tag.
3D Paintbrush: Local Stylization of 3D Shapes with Cascaded Score Distillation
Dale Decatur ,
Itai Lang ,
Kfir Aberman ,
Rana Hanocka
CVPR 2024
project page
/
arXiv
/
video
/
code
We generate precise localizations and highly detailed local textures on 3D shapes using text guidance.
Your browser does not support the video tag.
SAGA: Spectral Geometric Adversarial Attack on 3D Meshes
Tomer Stolik* ,
Itai Lang* ,
Shai Avidan
(*Equal contribution)
ICCV 2023
project page
/
arXiv
/
code
We apply a low frequency perturbation in the spectral shape domain to alter the reconstruction by a victim mesh autoencoder to a desired output geometry.
Your browser does not support the video tag.
SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flow
Itai Lang ,
Dror Aiger ,
Forrester Cole ,
Shai Avidan ,
Michael Rubinstein
CVPR 2023
project page
/
arXiv
/
video
/
code
We use pure correspondence learning and direct refinement optimization to predict a highly accurate scene flow while using a fraction of the training data.
Your browser does not support the video tag.
3D Highlighter: Localizing Regions on 3D Shapes via Text Descriptions
Dale Decatur ,
Itai Lang ,
Rana Hanocka
CVPR 2023 (Highlight Presentation)
project page
/
arXiv
/
video
/
code
We synthesize colors over a 3D shape and use CLIP supervision to localize semantic regions using open vocabulary text prompts.
Your browser does not support the video tag.
DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction
Itai Lang* ,
Dvir Ginzburg* ,
Shai Avidan ,
Dan Raviv
(*Equal contribution)
3DV 2021
arXiv
/
video
/
code
We use latent similarity and the point coordinates themselves to construct one point cloud by the other and achive an accurate dense matching with a small training data amount and without any correspondence supervision.
Your browser does not support the video tag.
Geometric Adversarial Attacks and Defenses on 3D Point Clouds
Itai Lang ,
Uriel Kotlicki ,
Shai Avidan
3DV 2021
arXiv
/
video
/
code
We perturb an input point cloud to attack an autoencoder model and change the reconstructed geometry to a different selected target shape.
Your browser does not support the video tag.
SampleNet: Differentiable Point Cloud Sampling
Itai Lang ,
Asaf Manor ,
Shai Avidan
CVPR 2020 (Oral Presentation)
arXiv
/
video
/
code
We propose a differentiable relaxation to the sampling operation that enables learning a task-oriented sampling model in an end-to-end manner.
Your browser does not support the video tag.
Learning to Sample
Oren Dovrat* ,
Itai Lang* ,
Shai Avidan
(*Equal contribution)
CVPR 2019
arXiv
/
code
We propose a data-driven sampling approach for 3D point clouds that selects the most suitable subset of points for a downstream task.