DAMA uses body-anchored Gaussians to reconstruct multi-layered 3D avatars from images, achieving clean garment separation, stacking control, and physical plausibility.
Segformer: Simple and efficient design for semantic segmentation with transform- ers.Advances in neural information processing systems, 34: 12077–12090, 2021
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
CONDITIONAL 2representative citing papers
A new 490-scan PE dataset and benchmark of nine 2D/3D CNN and ViT models shows 3D U-Net with ResNet blocks as top performer with consistent error patterns across architectures and releases open weights.
citing papers explorer
-
DAMA: Disentangled Body-Anchored Gaussians for Controllable Multi-Layered Avatars
DAMA uses body-anchored Gaussians to reconstruct multi-layered 3D avatars from images, achieving clean garment separation, stacking control, and physical plausibility.
-
Rethinking Pulmonary Embolism Segmentation: A Study of Current Approaches and Challenges with an Open Weight Model
A new 490-scan PE dataset and benchmark of nine 2D/3D CNN and ViT models shows 3D U-Net with ResNet blocks as top performer with consistent error patterns across architectures and releases open weights.