3d shape generation and completion through point-voxel diffusion

L Zhou, Y Du, J Wu - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
We propose a novel approach for probabilistic generative modeling of 3D shapes. Unlike
most existing models that learn to deterministically translate a latent vector to a shape, our …

Dit-3d: Exploring plain diffusion transformers for 3d shape generation

S Mo, E ** of objects with uncertain information: A review
C Wang, X Zhang, X Zang, Y Liu, G Ding, W Yin, J Zhao - Sensors, 2020 - mdpi.com
As there come to be more applications of intelligent robots, their task object is becoming
more varied. However, it is still a challenge for a robot to handle unfamiliar objects. We …

Point2mesh: A self-prior for deformable meshes

R Hanocka, G Metzer, R Giryes, D Cohen-Or - arxiv preprint arxiv …, 2020 - arxiv.org
In this paper, we introduce Point2Mesh, a technique for reconstructing a surface mesh from
an input point cloud. Instead of explicitly specifying a prior that encodes the expected shape …

Total3dunderstanding: Joint layout, object pose and mesh reconstruction for indoor scenes from a single image

Y Nie, X Han, S Guo, Y Zheng… - Proceedings of the …, 2020 - openaccess.thecvf.com
Semantic reconstruction of indoor scenes refers to both scene understanding and object
reconstruction. Existing works either address one part of this problem or focus on …

Multi-view supervision for single-view reconstruction via differentiable ray consistency

S Tulsiani, T Zhou, AA Efros… - Proceedings of the IEEE …, 2017 - openaccess.thecvf.com
We study the notion of consistency between a 3D shape and a 2D observation and propose
a differentiable formulation which allows computing gradients of the 3D shape given an …

Shape prior deformation for categorical 6d object pose and size estimation

M Tian, MH Ang, GH Lee - Computer Vision–ECCV 2020: 16th European …, 2020 - Springer
We present a novel learning approach to recover the 6D poses and sizes of unseen object
instances from an RGB-D image. To handle the intra-class shape variation, we propose a …

Pixel2mesh++: Multi-view 3d mesh generation via deformation

C Wen, Y Zhang, Z Li, Y Fu - Proceedings of the IEEE/CVF …, 2019 - openaccess.thecvf.com
We study the problem of shape generation in 3D mesh representation from a few color
images with known camera poses. While many previous works learn to hallucinate the …