Search Results for author: Cheng Sun

Found 19 papers, 7 papers with code

Hashing Neural Video Decomposition with Multiplicative Residuals in Space-Time

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.

Video Editing

ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection

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.

3D Object Detection object-detection

Neural-PBIR Reconstruction of Shape, Material, and Illumination

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.

Depth Prediction Image Relighting +5

Multiview Regenerative Morphing with Dual Flows

1 code implementation2 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.

Image Morphing

Self-supervised 360$^{\circ}$ Room Layout Estimation

no code implementations30 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.

Active Learning Room Layout Estimation

Data Efficient 3D Learner via Knowledge Transferred from 2D Model

1 code implementation16 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.

Pseudo Label Segmentation +1

Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction

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.

Novel View Synthesis

Specialize and Fuse: Pyramidal Output Representation for Semantic Segmentation

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.

Segmentation Semantic Segmentation +1

Moving in a 360 World: Synthesizing Panoramic Parallaxes from a Single Panorama

1 code implementation21 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.

Novel View Synthesis

SVMAC: Unsupervised 3D Human Pose Estimation from a Single Image with Single-view-multi-angle Consistency

no code implementations10 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

3D Human Pose Estimation Based on 2D-3D Consistency with Synchronized Adversarial Training

no code implementations8 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.

3D Human Pose Estimation Generative Adversarial Network

360-Indoor: Towards Learning Real-World Objects in 360° Indoor Equirectangular Images

no code implementations3 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.

Object object-detection +1

Flat2Layout: Flat Representation for Estimating Layout of General Room Types

no code implementations29 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.

A Spatial and Temporal Features Mixture Model with Body Parts for Video-based Person Re-Identification

no code implementations3 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.

Video-Based Person Re-Identification

Cannot find the paper you are looking for? You can Submit a new open access paper.