Zero3D: Semantic-Driven Multi-Category 3D Shape Generation
Semantic-driven 3D shape generation aims to generate 3D objects conditioned on text. Previous works face problems with single-category generation, low-frequency 3D details, and requiring a large number of paired datasets for training. To tackle these challenges, we propose a multi-category conditional diffusion model. Specifically, 1) to alleviate the problem of lack of large-scale paired data, we bridge the text, 2D image and 3D shape based on the pre-trained CLIP model, and 2) to obtain the multi-category 3D shape feature, we apply the conditional flow model to generate 3D shape vector conditioned on CLIP embedding. 3) to generate multi-category 3D shape, we employ the hidden-layer diffusion model conditioned on the multi-category shape vector, which greatly reduces the training time and memory consumption.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Shape GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Multi-View Hierarchical Graph Neural Network for Sketch-Based 3D Shape Retrieval
Sketch-based 3D shape retrieval (SBSR) aims to retrieve 3D shapes that are consistent with the category of the input hand-drawn sketch. The core challenge of this task lies in two aspects: existing methods typically empl…
Graph Neural NetworkMultiview Cross-supervision for Semantic Segmentation
This paper presents a semi-supervised learning framework for a customized semantic segmentation task using multiview image streams. A key challenge of the customized task lies in the limited accessibility of the labeled …
3D geometry3D ReconstructionCamera CalibrationSegmentation+1SOCS: Semantically-aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variations
Most learning-based approaches to category-level 6D pose estimation are design around normalized object coordinate space (NOCS). While being successful, NOCS-based methods become inaccurate and less robust when handling …
6D Pose Estimation6D Pose Estimation using RGBObjectPose Estimation+1Dense Object Reconstruction with Semantic Priors
We present a dense reconstruction approach that overcomes the drawbacks of traditional multiview stereo by incorporating semantic information in the form of learned category-level shape priors and object detection. Given…
Objectobject-detectionObject DetectionObject ReconstructionOpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding
We introduce OpenShape, a method for learning multi-modal joint representations of text, image, and point clouds. We adopt the commonly used multi-modal contrastive learning framework for representation alignment, but wi…
3D Classification3D Shape RepresentationContrastive LearningImage Generation+3