paper-with-me

홈 › Papers

Single-View Reconstruction via Joint Analysis of Image and Shape Collections

2015-12-01 · ACM Transactions on Graphics 2015 12 · Qixing Huang, Hai Wang, Vladlen Koltun

We present an approach to automatic 3D reconstruction of objects depicted in Web images. The approach reconstructs objects from single views. The key idea is to jointly analyze a collection of images of different objects along with a smaller collection of existing 3D models. The images are analyzed and reconstructed together. Joint analysis regularizes the formulated optimization problems, stabilizes correspondence estimation, and leads to reasonable reproduction of object appearance without traditional multi-view cues.

📄 PDF Abstract BibTeX

Code (1)

huangqx/image_shape_align

Tasks

3D Reconstruction

Similar Papers 제목 키워드 기반

ArtSplat: Feed-Forward Articulated 3D Gaussian Splatting from Sparse Multi-State Uncalibrated Views

2026-05-23 · Inseo Lee, Yoonji Kim, Eugene Sohn, Jiwoong Lee 외 arxiv

Articulated object reconstruction from sparse-view images is an ill-posed problem that requires simultaneous inference of geometry and underlying articulation structure. Existing methods for articulated object reconstruc…

3DCarGen: Scalable 3D Car Generation via 3D-consistent Multi-view Synthesis

2026-06-23 · Hongli Xiao, Youjian Zhang, Yaohui Jin, Xiaoguang Ren 외 arxiv

High-quality 3D vehicle assets are essential for autonomous driving simulation. Although multi-view diffusion-based paradigms enable controllable single-image reconstruction, they typically produce limited viewpoints and…

Image ReconstructionAutonomous Driving

SHARE: Single-view Human Adversarial REconstruction

2023-12-30 · Shreelekha Revankar, Shijia Liao, Yu Shen, Junbang Liang 외

The accuracy of 3D Human Pose and Shape reconstruction (HPS) from an image is progressively improving. Yet, no known method is robust across all image distortion. To address issues due to variations of camera poses, we i…

Data Augmentation

MExECON: Multi-view Extended Explicit Clothed humans Optimized via Normal integration

2025-08-21 · Fulden Ece Uğur, Rafael Redondo, Albert Barreiro, Stefan Hristov 외 arxiv

This work presents MExECON, a novel pipeline for 3D reconstruction of clothed human avatars from sparse multi-view RGB images. Building on the single-view method ECON, MExECON extends its capabilities to leverage multipl…

3D ReconstructionPose Estimation

GarmentCrafter: Progressive Novel View Synthesis for Single-View 3D Garment Reconstruction and Editing

2025-03-11 · Yuanhao Wang, Cheng Zhang, Gonçalo Frazão, Jinlong Yang 외

We introduce GarmentCrafter, a new approach that enables non-professional users to create and modify 3D garments from a single-view image. While recent advances in image generation have facilitated 2D garment design, cre…

3D ReconstructionDepth EstimationDepth PredictionGarment Reconstruction+3