Navi: Category-agnostic image collections with high-quality 3d shape and pose annotations

V Jampani, KK Maninis, A Engelhardt… - Advances in …, 2023‏ - proceedings.neurips.cc
Recent advances in neural reconstruction enable high-quality 3D object reconstruction from
casually captured image collections. Current techniques mostly analyze their progress on …

Sketchsampler: Sketch-based 3d reconstruction via view-dependent depth sampling

C Gao, Q Yu, L Sheng, YZ Song, D Xu - European Conference on …, 2022‏ - Springer
Reconstructing a 3D shape based on a single sketch image is challenging due to the large
domain gap between a sparse, irregular sketch and a regular, dense 3D shape. Existing …

Robust Shape Fitting for 3D Scene Abstraction

F Kluger, E Brachmann, MY Yang… - IEEE transactions on …, 2024‏ - ieeexplore.ieee.org
Humans perceive and construct the world as an arrangement of simple parametric models.
In particular, we can often describe man-made environments using volumetric primitives …

Tetsphere splatting: Representing high-quality geometry with lagrangian volumetric meshes

M Guo, B Wang, K He, W Matusik - arxiv preprint arxiv:2405.20283, 2024‏ - arxiv.org
We introduce TetSphere Splatting, a Lagrangian geometry representation designed for high-
quality 3D shape modeling. TetSphere splatting leverages an underused yet powerful …

Any-shot gin: Generalizing implicit networks for reconstructing novel classes

Y **an, J Chibane, BL Bhatnagar… - … Conference on 3D …, 2022‏ - ieeexplore.ieee.org
We address the task of estimating the 3D shapes of novel shape classes from a single RGB
image. Prior works are either limited to reconstructing known training classes or are unable …

3D Reconstruction From a Single Sketch via View-Dependent Depth Sampling

C Gao, X Wang, Q Yu, L Sheng, J Zhang… - IEEE transactions on …, 2024‏ - ieeexplore.ieee.org
Reconstructing a 3D shape based on a single sketch image is challenging due to the
inherent sparsity and ambiguity present in sketches. Existing methods lose fine details when …

TMSDNet: Transformer with multi‐scale dense network for single and multi‐view 3D reconstruction

X Zhu, X Yao, J Zhang, M Zhu, L You… - … and Virtual Worlds, 2024‏ - Wiley Online Library
Abstract 3D reconstruction is a long‐standing problem. Recently, a number of studies have
emerged that utilize transformers for 3D reconstruction, and these approaches have …

ED2IF2-Net: Learning Disentangled Deformed Implicit Fields and Enhanced Displacement Fields from Single Images Using Pyramid Vision Transformer

X Zhu, X Yao, J Zhang, M Zhu, L You, X Yang… - Applied Sciences, 2023‏ - mdpi.com
There has emerged substantial research in addressing single-view 3D reconstruction and
the majority of the state-of-the-art implicit methods employ CNNs as the backbone network …

ITIR-Net: single-view 3D reconstruction by fusing features of image texture and implicit representation

Q Zhang, C Wang, L Yang, G Gao… - Journal of Electronic …, 2024‏ - spiedigitallibrary.org
The accurate reconstruction of topology and texture details of three-dimensional (3D)
objects from a single two-dimensional image presents a significant challenge in the field of …

SketchPointer: Sketch-Based 3D Modeling with Adversarial Point Rendering for Point Cloud Generation

S **, J Zhang, Y Zang, W Hu - Proceedings of the 2024 8th International …, 2024‏ - dl.acm.org
As computer vision and 3D modeling technologies rapidly evolve, traditional methods of
creating 3D content, such as computer-aided design (CAD), can meet the growing demand …