Comboverse: Compositional 3d assets creation using spatially-aware diffusion guidance

Y Chen, T Wang, T Wu, X Pan, K Jia, Z Liu - European Conference on …, 2024 - Springer
Generating high-quality 3D assets from a given image is highly desirable in various
applications such as AR/VR. Recent advances in single-image 3D generation explore feed …

Cad: Photorealistic 3d generation via adversarial distillation

Z Wan, D Paschalidou, I Huang, H Liu… - Proceedings of the …, 2024 - openaccess.thecvf.com
The increased demand for 3D data in AR/VR robotics and gaming applications gave rise to
powerful generative pipelines capable of synthesizing high-quality 3D objects. Most of these …

Differentiable blocks world: Qualitative 3d decomposition by rendering primitives

T Monnier, J Austin, A Kanazawa… - Advances in Neural …, 2023 - proceedings.neurips.cc
Given a set of calibrated images of a scene, we present an approach that produces a simple,
compact, and actionable 3D world representation by means of 3D primitives. While many …

Deformer: Integrating transformers with deformable models for 3d shape abstraction from a single image

D Liu, X Yu, M Ye, Q Zhangli, Z Li… - Proceedings of the …, 2023 - openaccess.thecvf.com
Explicit 3D shape abstraction from a single 2D image is a long-standing problem in
computer vision and graphics. By leveraging a set of primitives to represent the target shape …

Dpa-net: Structured 3d abstraction from sparse views via differentiable primitive assembly

F Yu, Y Qian, X Zhang, F Gil-Ureta, B Jackson… - … on Computer Vision, 2024 - Springer
We present a differentiable rendering framework to learn structured 3D abstractions in the
form of primitive assemblies from sparse RGB images capturing a 3D object. By leveraging …

Deep deformable models: Learning 3d shape abstractions with part consistency

D Liu, L Zhao, Q Zhangli, Y Gao, T Liu… - ar** of Normals for Sparse-View Reconstruction
X Wang, S Dong, Y Zheng, Y Yang - European Conference on Computer …, 2024 - Springer
Abstract 3D surface reconstruction from multi-view images is esseorgnamential for scene
understanding and interaction. However, complex indoor scenes pose challenges such as …