75 citations · 139 across the 15 of their papers we have counts for
16 papers
Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
Guocheng Qian, Jinjie Mai, Abdullah Hamdi +8
We present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors. In the…
Dynamically Masked Discriminator for Generative Adversarial Networks
Wentian Zhang, Haozhe Liu, Bing Li +5
Training Generative Adversarial Networks (GANs) remains a challenging problem. The discriminator trains the generator by learning the distribution of real/generated data. However,…
Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models
Zhimin Chen, Longlong Jing, Yingwei Li +1
Foundation models have achieved remarkable results in 2D and language tasks like image segmentation, object detection, and visual-language understanding. However, their potential t…
Improving GAN Training via Feature Space Shrinkage
Haozhe Liu, Wentian Zhang, Bing Li +6
Due to the outstanding capability for data generation, Generative Adversarial Networks (GANs) have attracted considerable attention in unsupervised learning. However, training GANs…
CVRecon: Rethinking 3D Geometric Feature Learning For Neural Reconstruction
Ziyue Feng, Liang Yang, Pengsheng Guo +1
Recent advances in neural reconstruction using posed image sequences have made remarkable progress. However, due to the lack of depth information, existing volumetric-based techniq…
Be Careful with Rotation: A Uniform Backdoor Pattern for 3D Shape
Linkun Fan, Fazhi He, Qing Guo +3
For saving cost, many deep neural networks (DNNs) are trained on third-party datasets downloaded from internet, which enables attacker to implant backdoor into DNNs. In 2D domain,…
Decoupled Mixup for Generalized Visual Recognition
Haozhe Liu, Wentian Zhang, Jinheng Xie +7
Convolutional neural networks (CNN) have demonstrated remarkable performance when the training and testing data are from the same distribution. However, such trained CNN models oft…
Class-Level Confidence Based 3D Semi-Supervised Learning
Zhimin Chen, Longlong Jing, Liang Yang +2
Recent state-of-the-art method FlexMatch firstly demonstrated that correctly estimating learning status is crucial for semi-supervised learning (SSL). However, the estimation metho…
Combating Mode Collapse in GANs via Manifold Entropy Estimation
Haozhe Liu, Bing Li, Haoqian Wu +5
Generative Adversarial Networks (GANs) have shown compelling results in various tasks and applications in recent years. However, mode collapse remains a critical problem in GANs. I…
Learning Scene Flow in 3D Point Clouds with Noisy Pseudo Labels
Bing Li, Cheng Zheng, Guohao Li +1
We propose a novel scene flow method that captures 3D motions from point clouds without relying on ground-truth scene flow annotations. Due to the irregularity and sparsity of poin…
Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth
Ziyue Feng, Liang Yang, Longlong Jing +3
Conventional self-supervised monocular depth prediction methods are based on a static environment assumption, which leads to accuracy degradation in dynamic scenes due to the misma…
Multimodal Semi-Supervised Learning for 3D Objects
Zhimin Chen, Longlong Jing, Yang Liang +2
In recent years, semi-supervised learning has been widely explored and shows excellent data efficiency for 2D data. There is an emerging need to improve data efficiency for 3D task…
Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR
Ziyue Feng, Longlong Jing, Peng Yin +2
Self-supervised monocular depth prediction provides a cost-effective solution to obtain the 3D location of each pixel. However, the existing approaches usually lead to unsatisfacto…
SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation
Bing Li, Cheng Zheng, Silvio Giancola +1
We propose a novel scene flow estimation approach to capture and infer 3D motions from point clouds. Estimating 3D motions for point clouds is challenging, since a point cloud is u…
AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation
Bing Li, Yuanlue Zhu, Yitong Wang +3
In this paper, we propose a novel framework to translate a portrait photo-face into an anime appearance. Our aim is to synthesize anime-faces which are style-consistent with a give…
MVTN: Multi-View Transformation Network for 3D Shape Recognition
Abdullah Hamdi, Silvio Giancola, Bernard Ghanem
Multi-view projection methods have demonstrated their ability to reach state-of-the-art performance on 3D shape recognition. Those methods learn different ways to aggregate informa…