Category-Specific Object Reconstruction from a Single Image
Object reconstruction from a single image -- in the wild -- is a problem where we can make progress and get meaningful results today. This is the main message of this paper, which introduces an automated pipeline with pixels as inputs and 3D surfaces of various rigid categories as outputs in images of realistic scenes. At the core of our approach are deformable 3D models that can be learned from 2D annotations available in existing object detection datasets, that can be driven by noisy automatic object segmentations and which we complement with a bottom-up module for recovering high-frequency shape details. We perform a comprehensive quantitative analysis and ablation study of our approach using the recently introduced PASCAL 3D+ dataset and show very encouraging automatic reconstructions on PASCAL VOC.
Code (0)
등록된 구현이 없습니다.
Tasks
Objectobject-detectionObject DetectionObject ReconstructionSimilar Papers 제목 키워드 기반
Self-supervised Single-view 3D Reconstruction via Semantic Consistency
We learn a self-supervised, single-view 3D reconstruction model that predicts the 3D mesh shape, texture and camera pose of a target object with a collection of 2D images and silhouettes. The proposed method does not nec…
3D ReconstructionObjectSingle-View 3D ReconstructionWhen 3D Reconstruction Meets Ubiquitous RGB-D Images
3D reconstruction from a single image is a classical problem in computer vision. However, it still poses great challenges for the reconstruction of daily-use objects with irregular shapes. In this paper, we propose to le…
3D ReconstructionFew-Shot Generalization for Single-Image 3D Reconstruction via Priors
Recent work on single-view 3D reconstruction shows impressive results, but has been restricted to a few fixed categories where extensive training data is available. The problem of generalizing these models to new classes…
3D ReconstructionSingle-View 3D ReconstructionPre-train, Self-train, Distill: A simple recipe for Supersizing 3D Reconstruction
Our work learns a unified model for single-view 3D reconstruction of objects from hundreds of semantic categories. As a scalable alternative to direct 3D supervision, our work relies on segmented image collections for le…
3D ReconstructionSingle-View 3D ReconstructionMulti-Category Mesh Reconstruction From Image Collections
Recently, learning frameworks have shown the capability of inferring the accurate shape, pose, and texture of an object from a single RGB image. However, current methods are trained on image collections of a single categ…
Object