no code implementations • 3 Jul 2018 • Jie Liu, Cheng Sun, Xiang Xu, Baomin Xu, Shuangyuan Yu
In this paper we propose a novel Spatial and Temporal Features Mixture Model (STFMM) based on convolutional neural network (CNN) and recurrent neural network (RNN), in which the human body is split into $N$ parts in horizontal direction so that we can obtain more specific features.
1 code implementation • CVPR 2019 • Cheng Sun, Chi-Wei Hsiao, Min Sun, Hwann-Tzong Chen
We present a new approach to the problem of estimating the 3D room layout from a single panoramic image.
3D Room Layouts From A Single RGB Panorama Data Augmentation
no code implementations • 29 May 2019 • Chi-Wei Hsiao, Cheng Sun, Min Sun, Hwann-Tzong Chen
This paper also constructs a benchmark for validating the performance on general layout topologies, where Flat2Layout achieves good performance on general room types.
no code implementations • 3 Oct 2019 • Shih-Han Chou, Cheng Sun, Wen-Yen Chang, Wan-Ting Hsu, Min Sun, Jianlong Fu
In this paper, our goal is to provide a standard dataset to facilitate the vision and machine learning communities in 360{\deg} domain.
1 code implementation • CVPR 2021 • Cheng Sun, Min Sun, Hwann-Tzong Chen
We present HoHoNet, a versatile and efficient framework for holistic understanding of an indoor 360-degree panorama using a Latent Horizontal Feature (LHFeat).
3D Room Layouts From A Single RGB Panorama Depth Estimation +1
no code implementations • 8 Jun 2021 • Yicheng Deng, Cheng Sun, Yongqi Sun, Jiahui Zhu
3D human pose estimation from a single image is still a challenging problem despite the large amount of work that has been performed in this field.
no code implementations • 10 Jun 2021 • Yicheng Deng, Cheng Sun, Jiahui Zhu, Yongqi Sun
In this paper, we present an unsupervised GAN-based model consisting of multiple weight-sharing generators to estimate a 3D human pose from a single image without 3D annotations.
Monocular 3D Human Pose Estimation Unsupervised 3D Human Pose Estimation
1 code implementation • 21 Jun 2021 • Ching-Yu Hsu, Cheng Sun, Hwann-Tzong Chen
We present Omnidirectional Neural Radiance Fields (OmniNeRF), the first method to the application of parallax-enabled novel panoramic view synthesis.
1 code implementation • CVPR 2021 • Cheng Sun, Chi-Wei Hsiao, Ning-Hsu Wang, Min Sun, Hwann-Tzong Chen
Indoor panorama typically consists of human-made structures parallel or perpendicular to gravity.
no code implementations • ICCV 2021 • Chi-Wei Hsiao, Cheng Sun, Hwann-Tzong Chen, Min Sun
We present a novel pyramidal output representation to ensure parsimony with our "specialize and fuse" process for semantic segmentation.
2 code implementations • CVPR 2022 • Cheng Sun, Min Sun, Hwann-Tzong Chen
Finally, evaluation on five inward-facing benchmarks shows that our method matches, if not surpasses, NeRF's quality, yet it only takes about 15 minutes to train from scratch for a new scene.
1 code implementation • 16 Mar 2022 • Ping-Chung Yu, Cheng Sun, Min Sun
In this work, we deal with the data scarcity challenge of 3D tasks by transferring knowledge from strong 2D models via RGB-D images.
no code implementations • 30 Mar 2022 • Hao-Wen Ting, Cheng Sun, Hwann-Tzong Chen
We present the first self-supervised method to train panoramic room layout estimation models without any labeled data.
1 code implementation • 2 Aug 2022 • Chih-Jung Tsai, Cheng Sun, Hwann-Tzong Chen
This paper aims to address a new task of image morphing under a multiview setting, which takes two sets of multiview images as the input and generates intermediate renderings that not only exhibit smooth transitions between the two input sets but also ensure visual consistency across different views at any transition state.
no code implementations • ICCV 2023 • Cheng Sun, Guangyan Cai, Zhengqin Li, Kai Yan, Cheng Zhang, Carl Marshall, Jia-Bin Huang, Shuang Zhao, Zhao Dong
In the last stage, initialized by the neural predictions, we perform PBIR to refine the initial results and obtain the final high-quality reconstruction of object shape, material, and illumination.
Ranked #1 on Depth Prediction on Stanford-ORB
no code implementations • ICCV 2023 • Tao Tu, Shun-Po Chuang, Yu-Lun Liu, Cheng Sun, Ke Zhang, Donna Roy, Cheng-Hao Kuo, Min Sun
The results demonstrate that ImGeoNet outperforms the current state-of-the-art multi-view image-based method, ImVoxelNet, on all three datasets in terms of detection accuracy.
Ranked #24 on 3D Object Detection on ScanNetV2
no code implementations • 18 Sep 2023 • Yu-Cheng Hsieh, Cheng Sun, Suraj Dengale, Min Sun
The volume and diversity of training data are critical for modern deep learningbased methods.
no code implementations • ICCV 2023 • Cheng-Hung Chan, Cheng-Yang Yuan, Cheng Sun, Hwann-Tzong Chen
We present a video decomposition method that facilitates layer-based editing of videos with spatiotemporally varying lighting and motion effects.
no code implementations • 30 Nov 2023 • Cheng Sun, Wei-En Tai, Yu-Lin Shih, Kuan-Wei Chen, Yong-Jing Syu, Kent Selwyn The, Yu-Chiang Frank Wang, Hwann-Tzong Chen
State-of-the-art single-view 360-degree room layout reconstruction methods formulate the problem as a high-level 1D (per-column) regression task.