Pose Adaptive Dual Mixup for Few-Shot Single-View 3D Reconstruction
원문 초록
We present a pose adaptive few-shot learning procedure and a two-stage data interpolation regularization, termed Pose Adaptive Dual Mixup (PADMix), for single-image 3D reconstruction. While augmentations via interpolating feature-label pairs are effective in classification tasks, they fall short in shape predictions potentially due to inconsistencies between interpolated products of two images and volumes when rendering viewpoints are unknown. PADMix targets this issue with two sets of mixup procedures performed sequentially. We first perform an input mixup which, combined with a pose adaptive learning procedure, is helpful in learning 2D feature extraction and pose adaptive latent encoding. The stagewise training allows us to build upon the pose invariant representations to perform a follow-up latent mixup under one-to-one correspondences between features and ground-truth volumes. PADMix significantly outperforms previous literature on few-shot settings over the ShapeNet dataset and sets new benchmarks on the more challenging real-world Pix3D dataset.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ViT-NeBLa: A Hybrid Vision Transformer and Neural Beer-Lambert Framework for Single-View 3D Reconstruction of Oral Anatomy from Panoramic Radiographs
SR3D: Unleashing Single-view 3D Reconstruction for Transparent and Specular Object Grasping
ACT-R: Adaptive Camera Trajectories for Single View 3D Reconstruction
SpatialTrackerV2: 3D Point Tracking Made Easy
Few-Shot Learning by Explicit Physics Integration: An Application to Groundwater Heat Transport
SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment
토론
이 논문과 연결된 포럼 글이 아직 없습니다.