no code implementations • 27 Nov 2023 • Yuanxun Lu, Jingyang Zhang, Shiwei Li, Tian Fang, David McKinnon, Yanghai Tsin, Long Quan, Xun Cao, Yao Yao
The multi-view 2. 5D diffusion directly models the structural distribution of 3D data, while still maintaining the strong generalization ability of the original 2D diffusion model, filling the gap between 2D diffusion-based and direct 3D diffusion-based methods for 3D content generation.
no code implementations • 17 Nov 2023 • Yongchao Feng, Shiwei Li, Yingjie Gao, Ziyue Huang, Yanan Zhang, Qingjie Liu, Yunhong Wang
Though feature-alignment based Domain Adaptive Object Detection (DAOD) have achieved remarkable progress, they ignore the source bias issue, i. e. the aligned features are more favorable towards the source domain, leading to a sub-optimal adaptation.
no code implementations • 10 Oct 2023 • Jingyang Zhang, Shiwei Li, Yuanxun Lu, Tian Fang, David McKinnon, Yanghai Tsin, Long Quan, Yao Yao
We introduce JointNet, a novel neural network architecture for modeling the joint distribution of images and an additional dense modality (e. g., depth maps).
no code implementations • ICCV 2023 • Jingyang Zhang, Yao Yao, Shiwei Li, Jingbo Liu, Tian Fang, David McKinnon, Yanghai Tsin, Long Quan
We present a novel differentiable rendering framework for joint geometry, material, and lighting estimation from multi-view images.
no code implementations • 12 Dec 2022 • Shiwei Li, Huifeng Guo, Lu Hou, Wei zhang, Xing Tang, Ruiming Tang, Rui Zhang, Ruixuan Li
To this end, we formulate a novel quantization training paradigm to compress the embeddings from the training stage, termed low-precision training (LPT).
no code implementations • CVPR 2022 • Jingyang Zhang, Yao Yao, Shiwei Li, Tian Fang, David McKinnon, Yanghai Tsin, Long Quan
The first one is the Hessian regularization that smoothly diffuses the signed distance values to the entire distance field given noisy and incomplete input.
1 code implementation • 18 Aug 2020 • Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang
As such, the adverse influence of occluded pixels is suppressed in the cost fusion.
Ranked #1 on Point Clouds on DTU
1 code implementation • 11 Aug 2020 • Jingyang Zhang, Yao Yao, Zixin Luo, Shiwei Li, Tianwei Shen, Tian Fang, Long Quan
Finally, a matchability-aware disparity refinement is introduced to improve the depth inference in weakly matchable regions.
Ranked #2 on Stereo Disparity Estimation on KITTI 2015
no code implementations • ECCV 2020 • Mingmin Zhen, Shiwei Li, Lei Zhou, Jiaxiang Shang, Haoan Feng, Tian Fang, Long Quan
In this paper, we introduce a novel network, called discriminative feature network (DFNet), to address the unsupervised video object segmentation task.
Ranked #1 on Video Object Segmentation on FBMS
1 code implementation • ECCV 2020 • Lei Zhou, Zixin Luo, Mingmin Zhen, Tianwei Shen, Shiwei Li, Zhuofei Huang, Tian Fang, Long Quan
In this work, we propose a stochastic bundle adjustment algorithm which seeks to decompose the RCS approximately inside the LM iterations to improve the efficiency and scalability.
1 code implementation • ECCV 2020 • Jiaxiang Shang, Tianwei Shen, Shiwei Li, Lei Zhou, Mingmin Zhen, Tian Fang, Long Quan
Recent learning-based approaches, in which models are trained by single-view images have shown promising results for monocular 3D face reconstruction, but they suffer from the ill-posed face pose and depth ambiguity issue.
Ranked #6 on 3D Face Reconstruction on REALY (side-view)
no code implementations • CVPR 2020 • Mingmin Zhen, Jinglu Wang, Lei Zhou, Shiwei Li, Tianwei Shen, Jiaxiang Shang, Tian Fang, Quan Long
In this paper, we present a joint multi-task learning framework for semantic segmentation and boundary detection.
4 code implementations • CVPR 2020 • Zixin Luo, Lei Zhou, Xuyang Bai, Hongkai Chen, Jiahui Zhang, Yao Yao, Shiwei Li, Tian Fang, Long Quan
This work focuses on mitigating two limitations in the joint learning of local feature detectors and descriptors.
2 code implementations • CVPR 2020 • Yao Yao, Zixin Luo, Shiwei Li, Jingyang Zhang, Yufan Ren, Lei Zhou, Tian Fang, Long Quan
Compared with other computer vision tasks, it is rather difficult to collect a large-scale MVS dataset as it requires expensive active scanners and labor-intensive process to obtain ground truth 3D structures.
1 code implementation • 19 Sep 2019 • Tianwei Shen, Lei Zhou, Zixin Luo, Yao Yao, Shiwei Li, Jiahui Zhang, Tian Fang, Long Quan
The self-supervised learning of depth and pose from monocular sequences provides an attractive solution by using the photometric consistency of nearby frames as it depends much less on the ground-truth data.
no code implementations • CVPR 2019 • Shiwei Li, Zixin Luo, Mingmin Zhen, Yao Yao, Tianwei Shen, Tian Fang, Long Quan
We present a convolutional network architecture for direct feature learning on mesh surfaces through their atlases of texture maps.
1 code implementation • CVPR 2019 • Zixin Luo, Tianwei Shen, Lei Zhou, Jiahui Zhang, Yao Yao, Shiwei Li, Tian Fang, Long Quan
Most existing studies on learning local features focus on the patch-based descriptions of individual keypoints, whereas neglecting the spatial relations established from their keypoint locations.
1 code implementation • CVPR 2019 • Yao Yao, Zixin Luo, Shiwei Li, Tianwei Shen, Tian Fang, Long Quan
However, one major limitation of current learned MVS approaches is the scalability: the memory-consuming cost volume regularization makes the learned MVS hard to be applied to high-resolution scenes.
no code implementations • CVPR 2018 • Shiwei Li, Yao Yao, Tian Fang, Long Quan
We present a novel surface reconstruction method using both curves and point clouds.
4 code implementations • ECCV 2018 • Yao Yao, Zixin Luo, Shiwei Li, Tian Fang, Long Quan
We present an end-to-end deep learning architecture for depth map inference from multi-view images.
Ranked #19 on Point Clouds on Tanks and Temples (Mean F1 (Intermediate) metric)
no code implementations • ICCV 2015 • Runze Zhang, Shiwei Li, Tian Fang, Siyu Zhu, Long Quan
To solve this problem, we propose a joint optimization in a hierarchical framework to obtain the final surface segments and corresponding optimal camera clusters.
no code implementations • ICCV 2015 • Shiwei Li, Lu Yuan, Jian Sun, Long Quan
Line segment is a prominent feature in artificial environments and it can supply sufficient geometrical and structural information of scenes, which not only helps guild to a correct warp in low-texture condition, but also prevents the undesired distortion induced by warping.