no code implementations • 3 Apr 2024 • Yisheng He, Weihao Yuan, Siyu Zhu, Zilong Dong, Liefeng Bo, QiXing Huang
This paper enables high-fidelity, transferable NeRF editing by frequency decomposition.
no code implementations • 22 Mar 2024 • Yifei Zeng, Yanqin Jiang, Siyu Zhu, Yuanxun Lu, Youtian Lin, Hao Zhu, Weiming Hu, Xun Cao, Yao Yao
Recent progress in pre-trained diffusion models and 3D generation have spurred interest in 4D content creation.
1 code implementation • 21 Mar 2024 • Shenhao Zhu, Junming Leo Chen, Zuozhuo Dai, Yinghui Xu, Xun Cao, Yao Yao, Hao Zhu, Siyu Zhu
In this study, we introduce a methodology for human image animation by leveraging a 3D human parametric model within a latent diffusion framework to enhance shape alignment and motion guidance in curernt human generative techniques.
no code implementations • 19 Mar 2024 • Junhao Cai, Yisheng He, Weihao Yuan, Siyu Zhu, Zilong Dong, Liefeng Bo, Qifeng Chen
Derived from OmniObject3D, OO3D-9D is the largest and most diverse dataset in the field of category-level object pose and size estimation.
no code implementations • 18 Mar 2024 • Qi Zuo, Xiaodong Gu, Lingteng Qiu, Yuan Dong, Zhengyi Zhao, Weihao Yuan, Rui Peng, Siyu Zhu, Zilong Dong, Liefeng Bo, QiXing Huang
Images from video generative models are more suitable for multi-view generation because the underlying network architecture that generates them employs a temporal module to enforce frame consistency.
no code implementations • 10 Feb 2024 • Fedor Borisyuk, Mingzhou Zhou, Qingquan Song, Siyu Zhu, Birjodh Tiwana, Ganesh Parameswaran, Siddharth Dangi, Lars Hertel, Qiang Xiao, Xiaochen Hou, Yunbo Ouyang, Aman Gupta, Sheallika Singh, Dan Liu, Hailing Cheng, Lei Le, Jonathan Hung, Sathiya Keerthi, Ruoyan Wang, Fengyu Zhang, Mohit Kothari, Chen Zhu, Daqi Sun, Yun Dai, Xun Luan, Sirou Zhu, Zhiwei Wang, Neil Daftary, Qianqi Shen, Chengming Jiang, Haichao Wei, Maneesh Varshney, Amol Ghoting, Souvik Ghosh
We present LiRank, a large-scale ranking framework at LinkedIn that brings to production state-of-the-art modeling architectures and optimization methods.
no code implementations • 6 Dec 2023 • Youtian Lin, Zuozhuo Dai, Siyu Zhu, Yao Yao
Moreover, the explicit deformation modeling for discretized Gaussian points ensures ultra-fast training and rendering of a 4D scene, which is comparable to the original 3DGS designed for static 3D reconstruction.
1 code implementation • 21 Nov 2023 • Zuozhuo Dai, Zhenghao Zhang, Yao Yao, Bingxue Qiu, Siyu Zhu, Long Qin, Weizhi Wang
Image animation is a key task in computer vision which aims to generate dynamic visual content from static image.
no code implementations • 18 Nov 2023 • Jiayang Liu, Siyu Zhu, Siyuan Liang, Jie Zhang, Han Fang, Weiming Zhang, Ee-Chien Chang
Various techniques have emerged to enhance the transferability of adversarial attacks for the black-box scenario.
no code implementations • 5 Sep 2023 • Kayhan Behdin, Ayan Acharya, Aman Gupta, Qingquan Song, Siyu Zhu, Sathiya Keerthi, Rahul Mazumder
Particularly noteworthy is our outlier-aware algorithm's capability to achieve near or sub-3-bit quantization of LLMs with an acceptable drop in accuracy, obviating the need for non-uniform quantization or grouping techniques, improving upon methods such as SpQR by up to two times in terms of perplexity.
no code implementations • 14 Jul 2023 • Zuozhuo Dai, Fangtao Shao, Qingkun Su, Zilong Dong, Siyu Zhu
In the second stage, we propose a novel decoupled video text cross attention module to capture fine-grained multimodal information in spatial and temporal dimensions.
no code implementations • 22 May 2023 • Zhenghao Zhang, Zhichao Wei, Shengfan Zhang, Zuozhuo Dai, Siyu Zhu
Unsupervised video object segmentation has made significant progress in recent years, but the manual annotation of video mask datasets is expensive and limits the diversity of available datasets.
1 code implementation • 31 Jan 2023 • Weihao Yuan, Xiaodong Gu, Heng Li, Zilong Dong, Siyu Zhu
In this work, we propose an SDF transformer network, which replaces the role of 3D CNN for better 3D feature aggregation.
no code implementations • 20 Jan 2023 • Zhenghao Zhang, Fangtao Shao, Zuozhuo Dai, Siyu Zhu
In this paper, we observe the temporal information is important as well and we propose TAFormer to aggregate spatio-temporal features both in transformer encoder and decoder.
no code implementations • 16 Jan 2023 • Zhichao Wei, Xiaohao Chen, Mingqiang Chen, Siyu Zhu
Referring image segmentation aims to segment the image region of interest according to the given language expression, which is a typical multi-modal task.
no code implementations • 26 Jul 2022 • Jiahui Zhang, Shitao Tang, Kejie Qiu, Rui Huang, Chuan Fang, Le Cui, Zilong Dong, Siyu Zhu, Ping Tan
Visual relocalization has been a widely discussed problem in 3D vision: given a pre-constructed 3D visual map, the 6 DoF (Degrees-of-Freedom) pose of a query image is estimated.
no code implementations • 23 May 2022 • Xiaodong Gu, Chengzhou Tang, Weihao Yuan, Zuozhuo Dai, Siyu Zhu, Ping Tan
In the experiments, we evaluate the proposed method on both the 3D scene flow estimation and the point cloud registration task.
1 code implementation • CVPR 2022 • Weihao Yuan, Xiaodong Gu, Zuozhuo Dai, Siyu Zhu, Ping Tan
While recent works design increasingly complicated and powerful networks to directly regress the depth map, we take the path of CRFs optimization.
Ranked #1 on Depth Prediction on Matterport3D
1 code implementation • ICLR 2022 • Shitao Tang, Jiahui Zhang, Siyu Zhu, Ping Tan
Transformers have been successful in many vision tasks, thanks to their capability of capturing long-range dependency.
no code implementations • CVPR 2022 • Weihao Yuan, Xiaodong Gu, Zuozhuo Dai, Siyu Zhu, Ping Tan
Estimating the accurate depth from a single image is challenging since it is inherently ambiguous and ill-posed.
1 code implementation • CVPR 2022 • Xiaodong Gu, Chengzhou Tang, Weihao Yuan, Zuozhuo Dai, Siyu Zhu, Ping Tan
In the experiments, we evaluate the proposed method on both the 3D scene flow estimation and the point cloud registration task.
no code implementations • 22 Nov 2021 • Lizhe Liu, Mingqiang Chen, Xiaohao Chen, Siyu Zhu, Ping Tan
Our GB-CosFace introduces an adaptive global boundary to determine whether two face samples belong to the same identity so that the optimization objective is aligned with the testing process from the perspective of open set classification.
no code implementations • ICCV 2021 • Zhiwen Fan, Lingjie Zhu, Honghua Li, Xiaohao Chen, Siyu Zhu, Ping Tan
The proposed CNN-GCN method achieved state-of-the-art (SOTA) performance on the task of semantic symbol spotting, and help us build a baseline network for the panoptic symbol spotting task.
3 code implementations • ICCV 2021 • Lizhe Liu, Xiaohao Chen, Siyu Zhu, Ping Tan
Modern deep-learning-based lane detection methods are successful in most scenarios but struggling for lane lines with complex topologies.
Ranked #8 on Lane Detection on CurveLanes (using extra training data)
no code implementations • 9 Apr 2021 • Weihao Yuan, Yazhan Zhang, Bingkun Wu, Siyu Zhu, Ping Tan, Michael Yu Wang, Qifeng Chen
Self-supervised learning for depth estimation possesses several advantages over supervised learning.
1 code implementation • CVPR 2021 • Shitao Tang, Chengzhou Tang, Rui Huang, Siyu Zhu, Ping Tan
We present a new method for scene agnostic camera localization using dense scene matching (DSM), where a cost volume is constructed between a query image and a scene.
no code implementations • 27 Mar 2021 • Rui Huang, Chuan Fang, Kejie Qiu, Le Cui, Zilong Dong, Siyu Zhu, Ping Tan
Secondly, we propose an AR mapping pipeline which takes the input from the scanning device and produces accurate AR Maps.
1 code implementation • 24 Mar 2021 • Xiaodong Gu, Weihao Yuan, Zuozhuo Dai, Siyu Zhu, Chengzhou Tang, Zilong Dong, Ping Tan
There are increasing interests of studying the video-to-depth (V2D) problem with machine learning techniques.
3 code implementations • 22 Mar 2021 • Zuozhuo Dai, Guangyuan Wang, Weihao Yuan, Xiaoli Liu, Siyu Zhu, Ping Tan
Thus, our method can solve the problem of cluster inconsistency and be applicable to larger data sets.
Ranked #1 on Unsupervised Person Re-Identification on PersonX
1 code implementation • 6 Feb 2021 • Hualie Jiang, Zhe Sheng, Siyu Zhu, Zilong Dong, Rui Huang
Besides, we also designed a more effective fusion module for our fusion scheme.
Ranked #1 on Depth Estimation on Matterport3D
no code implementations • 17 Oct 2020 • Rakesh Shrestha, Zhiwen Fan, Qingkun Su, Zuozhuo Dai, Siyu Zhu, Ping Tan
Deep learning based 3D shape generation methods generally utilize latent features extracted from color images to encode the semantics of objects and guide the shape generation process.
1 code implementation • CVPR 2020 • Feitong Tan, Hao Zhu, Zhaopeng Cui, Siyu Zhu, Marc Pollefeys, Ping Tan
Previous methods on estimating detailed human depth often require supervised training with `ground truth' depth data.
1 code implementation • CVPR 2020 • Lei Li, Siyu Zhu, Hongbo Fu, Ping Tan, Chiew-Lan Tai
In this work, we propose an end-to-end framework to learn local multi-view descriptors for 3D point clouds.
Ranked #5 on Point Cloud Registration on 3DMatch Benchmark
4 code implementations • CVPR 2020 • Xiaodong Gu, Zhiwen Fan, Zuozhuo Dai, Siyu Zhu, Feitong Tan, Ping Tan
The deep multi-view stereo (MVS) and stereo matching approaches generally construct 3D cost volumes to regularize and regress the output depth or disparity.
Ranked #12 on Point Clouds on Tanks and Temples
1 code implementation • ICCV 2019 • Sicong Tang, Feitong Tan, Kelvin Cheng, Zhaoyang Li, Siyu Zhu, Ping Tan
To achieve this goal, we separate the depth map into a smooth base shape and a residual detail shape and design a network with two branches to regress them respectively.
1 code implementation • 26 Nov 2018 • Tianwei Shen, Zixin Luo, Lei Zhou, Runze Zhang, Siyu Zhu, Tian Fang, Long Quan
Convolutional Neural Networks (CNNs) have achieved superior performance on object image retrieval, while Bag-of-Words (BoW) models with handcrafted local features still dominate the retrieval of overlapping images in 3D reconstruction.
5 code implementations • ICCV 2019 • Zuozhuo Dai, Mingqiang Chen, Xiaodong Gu, Siyu Zhu, Ping Tan
In this paper, we propose the Batch DropBlock (BDB) Network which is a two branch network composed of a conventional ResNet-50 as the global branch and a feature dropping branch.
Ranked #8 on Person Re-Identification on Market-1501-C
1 code implementation • ECCV 2018 • Zixin Luo, Tianwei Shen, Lei Zhou, Siyu Zhu, Runze Zhang, Yao Yao, Tian Fang, Long Quan
Learned local descriptors based on Convolutional Neural Networks (CNNs) have achieved significant improvements on patch-based benchmarks, whereas not having demonstrated strong generalization ability on recent benchmarks of image-based 3D reconstruction.
no code implementations • ECCV 2018 • Lei Zhou, Siyu Zhu, Zixin Luo, Tianwei Shen, Runze Zhang, Mingmin Zhen, Tian Fang, Long Quan
Critical to the registration of point clouds is the establishment of a set of accurate correspondences between points in 3D space.
no code implementations • CVPR 2018 • Siyu Zhu, Runze Zhang, Lei Zhou, Tianwei Shen, Tian Fang, Ping Tan, Long Quan
This work proposes a divide-and-conquer framework to solve very large global SfM at the scale of millions of images.
no code implementations • ICCV 2017 • Lei Zhou, Siyu Zhu, Tianwei Shen, Jinglu Wang, Tian Fang, Long Quan
In this paper, we propose a scale-invariant image matching approach to tackling the very large scale variation of views.
no code implementations • ICCV 2017 • Runze Zhang, Siyu Zhu, Tian Fang, Long Quan
In this paper, we propose a distributed approach to coping with this global bundle adjustment for very large scale Structure-from-Motion computation.
no code implementations • 28 Feb 2017 • Siyu Zhu, Tianwei Shen, Lei Zhou, Runze Zhang, Jinglu Wang, Tian Fang, Long Quan
In this paper, we tackle the accurate and consistent Structure from Motion (SfM) problem, in particular camera registration, far exceeding the memory of a single computer in parallel.
no code implementations • CVPR 2016 • Siyu Zhu, Richard Zanibbi
We propose a system that finds text in natural scenes using a variety of cues.
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 • 24 Oct 2014 • Christoph Riedl, Richard Zanibbi, Marti A. Hearst, Siyu Zhu, Michael Menietti, Jason Crusan, Ivan Metelsky, Karim R. Lakhani
We report the findings of a month-long online competition in which participants developed algorithms for augmenting the digital version of patent documents published by the United States Patent and Trademark Office (USPTO).
no code implementations • CVPR 2014 • Siyu Zhu, Tian Fang, Jianxiong Xiao, Long Quan
To this end, we propose a segment-based approach to readjust the camera poses locally and improve the reconstruction for fine geometry details.