Search

Bernard Ghanem

AToM: Amortized Text-to-Mesh using 2D Diffusion
Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud Understanding
Exploring Open-Vocabulary Semantic Segmentation from CLIP Vision Encoder Distillation Only
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies
Rethinking Learning-based Demosaicing, Denoising, and Super-Resolution Pipeline
ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learning
DeepGCNs: Making GCNs Go as Deep as CNNs
PU-GCN: Point Cloud Upsampling using Graph Convolutional Networks
SGAS: Sequential Greedy Architecture Search