no code implementations • 10 Apr 2024 • Junsheng Zhou, Weiqi Zhang, Baorui Ma, Kanle Shi, Yu-Shen Liu, Zhizhong Han
In this work, we present UDiFF, a 3D diffusion model for unsigned distance fields (UDFs) which is capable to generate textured 3D shapes with open surfaces from text conditions or unconditionally.
no code implementations • 23 Dec 2023 • Shujuan Li, Junsheng Zhou, Baorui Ma, Yu-Shen Liu, Zhizhong Han
At inference time, we randomly sample queries around the sparse point cloud, and project these query points onto the zero-level set of the learned implicit field to generate a dense point cloud.
1 code implementation • NeurIPS 2023 • Junsheng Zhou, Baorui Ma, Wenyuan Zhang, Yi Fang, Yu-Shen Liu, Zhizhong Han
To address these problems, we propose to learn a structured cross-modality latent space to represent pixel features and 3D features via a differentiable probabilistic PnP solver.
2 code implementations • 29 Nov 2023 • Baorui Ma, Haoge Deng, Junsheng Zhou, Yu-Shen Liu, Tiejun Huang, Xinlong Wang
We justify that the refined 3D geometric priors aid in the 3D-aware capability of 2D diffusion priors, which in turn provides superior guidance for the refinement of 3D geometric priors.
2 code implementations • 10 Oct 2023 • Junsheng Zhou, Jinsheng Wang, Baorui Ma, Yu-Shen Liu, Tiejun Huang, Xinlong Wang
Scaling up representations for images or text has been extensively investigated in the past few years and has led to revolutions in learning vision and language.
Ranked #1 on Zero-shot 3D classification on Objaverse LVIS (using extra training data)
2 code implementations • ICCV 2023 • Junsheng Zhou, Baorui Ma, Shujuan Li, Yu-Shen Liu, Zhizhong Han
We pull the non-zero level sets onto the zero level set with gradient constraints which align gradients over different level sets and correct unsigned distance errors on the zero level set, leading to a smoother and more continuous unsigned distance field.
1 code implementation • 2 Jun 2023 • Baorui Ma, Yu-Shen Liu, Zhizhong Han
However, without ground truth signed distances, point normals or clean point clouds, current methods still struggle from learning SDFs from noisy point clouds.
1 code implementation • CVPR 2023 • Baorui Ma, Junsheng Zhou, Yu-Shen Liu, Zhizhong Han
Our insight is to propagate the zero level set to everywhere in the field through consistent gradients to eliminate uncertainty in the field that is caused by the discreteness of 3D point clouds or the lack of observations from multi-view images.
1 code implementation • 30 Nov 2022 • Shujuan Li, Junsheng Zhou, Baorui Ma, Yu-Shen Liu, Zhizhong Han
To resolve these issues, we propose an implicit function to learn an angle field around the normal of each point in the spherical coordinate system, which is dubbed as Neural Angle Fields (NeAF).
Ranked #3 on Surface Normals Estimation on PCPNet
1 code implementation • 6 Oct 2022 • Junsheng Zhou, Baorui Ma, Yu-Shen Liu, Yi Fang, Zhizhong Han
In this paper, we propose a novel method to learn consistency-aware unsigned distance functions directly from raw point clouds.
1 code implementation • CVPR 2022 • Baorui Ma, Yu-Shen Liu, Matthias Zwicker, Zhizhong Han
To reconstruct a surface at a specific query location at inference time, these methods then match the local reconstruction target by searching for the best match in the local prior space (by optimizing the parameters encoding the local context) at the given query location.
2 code implementations • CVPR 2022 • Baorui Ma, Yu-Shen Liu, Zhizhong Han
Our key idea is to infer signed distances by pushing both the query projections to be on the surface and the projection distance to be the minimum.
1 code implementation • 26 Mar 2022 • Junsheng Zhou, Xin Wen, Baorui Ma, Yu-Shen Liu, Yue Gao, Yi Fang, Zhizhong Han
To address this problem, we present a novel and efficient self-supervised point cloud representation learning framework, named 3D Occlusion Auto-Encoder (3D-OAE), to facilitate the detailed supervision inherited in local regions and global shapes.
1 code implementation • 26 Nov 2020 • Baorui Ma, Zhizhong Han, Yu-Shen Liu, Matthias Zwicker
Specifically, we train a neural network to pull query 3D locations to their closest points on the surface using the predicted signed distance values and the gradient at the query locations, both of which are computed by the network itself.