no code implementations • 20 Feb 2024 • Shitao Tang, Jiacheng Chen, Dilin Wang, Chengzhou Tang, Fuyang Zhang, Yuchen Fan, Vikas Chandra, Yasutaka Furukawa, Rakesh Ranjan
MVDiffusion++ achieves superior flexibility and scalability with two surprisingly simple ideas: 1) A ``pose-free architecture'' where standard self-attention among 2D latent features learns 3D consistency across an arbitrary number of conditional and generation views without explicitly using camera pose information; and 2) A ``view dropout strategy'' that discards a substantial number of output views during training, which reduces the training-time memory footprint and enables dense and high-resolution view synthesis at test time.
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 • 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 • CVPR 2022 • Chengzhou Tang, Yuqiang Yang, Bing Zeng, Ping Tan, Shuaicheng Liu
To these ends, we design a method that receives a low-resolution RAW as the input and estimates the desired higher-resolution RAW jointly with the degradation model.
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.
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.
no code implementations • CVPR 2020 • Chengzhou Tang, Lu Yuan, Ping Tan
We study the energy minimization problem in low-level vision tasks from a novel perspective.
no code implementations • ICLR 2019 • Chengzhou Tang, Ping Tan
The network first generates several basis depth maps according to the input image, and optimizes the final depth as a linear combination of these basis depth maps via feature-metric BA.
1 code implementation • 13 Jun 2018 • Chengzhou Tang, Ping Tan
The network first generates several basis depth maps according to the input image and optimizes the final depth as a linear combination of these basis depth maps via feature-metric BA.
no code implementations • 16 Aug 2017 • Chengzhou Tang, Oliver Wang, Ping Tan
Many monocular visual SLAM algorithms are derived from incremental structure-from-motion (SfM) methods.
no code implementations • 6 Mar 2015 • Zhaopeng Cui, Nianjuan Jiang, Chengzhou Tang, Ping Tan
This paper derives a novel linear position constraint for cameras seeing a common scene point, which leads to a direct linear method for global camera translation estimation.