Data-Free Learning of Student Networks
- Hanting Chen, Yunhe Wang, Qi Tian
- Computer ScienceIEEE International Conference on Computer Vision
- 2 April 2019
A novel framework for training efficient deep neural networks by exploiting generative adversarial networks (GANs) is proposed, where the pre-trained teacher networks are regarded as a fixed discriminator and the generator is utilized for derivating training samples which can obtain the maximum response on the discriminator.
A Benchmark Dataset and Evaluation for Non-Lambertian and Uncalibrated Photometric Stereo
- Boxin Shi, Zhipeng Mo, Zhe Wu, Dinglong Duan, S. Yeung, P. Tan
- Computer ScienceComputer Vision and Pattern Recognition
- 1 February 2019
This paper survey and categorize existing methods using a photometric stereo taxonomy emphasizing on non-Lambertian and uncalibrated methods, and introduces the 'DiLiGenT' photomet stereo image dataset with calibrated Directional Lightings, objects of General reflectance, and 'ground Truth' shapes (normals).
Robust Photometric Stereo via Low-Rank Matrix Completion and Recovery
- Lun Wu, Arvind Ganesh, Boxin Shi, Y. Matsushita, Yongtian Wang, Yi Ma
- Computer ScienceAsian Conference on Computer Vision
- 8 November 2010
This work presents a new approach to robustly solve photometric stereo problems by using advanced convex optimization techniques that are guaranteed to find the correct low-rank matrix by simultaneously fixing its missing and erroneous entries.
Self-Calibrating Deep Photometric Stereo Networks
- Guanying Chen, K. Han, Boxin Shi, Y. Matsushita, Kwan-Yee Kenneth Wong
- Computer ScienceComputer Vision and Pattern Recognition
- 18 March 2019
An uncalibrated photometric stereo method for non-Lambertian scenes based on deep learning that can effectively take advantage of intermediate supervision, resulting in reduced learning difficulty compared to a single-stage model is proposed.
RIFE: Real-Time Intermediate Flow Estimation for Video Frame Interpolation
- Zhewei Huang, Tianyuan Zhang, Wen Heng, Boxin Shi, Shuchang Zhou
- Computer ScienceEuropean Conference on Computer Vision
- 12 November 2020
A real-time intermediate flow estimation algorithm (RIFE) for video frame interpolation (VFI) that can be trained end-to-end and achieve excellent performance and achieves state-of-the-art index on several benchmarks is proposed.
DIST: Rendering Deep Implicit Signed Distance Function With Differentiable Sphere Tracing
- Shaohui Liu, Yinda Zhang, Songyou Peng, Boxin Shi, M. Pollefeys, Zhaopeng Cui
- Computer ScienceComputer Vision and Pattern Recognition
- 29 November 2019
This work proposes a differentiable sphere tracing algorithm that can effectively reconstruct accurate 3D shapes from various inputs, such as sparse depth and multi-view images, through inverse optimization and shows excellent generalization capability and robustness against various noises.
Mop Moiré Patterns Using MopNet
- Bin He, Ce Wang, Boxin Shi, Ling-yu Duan
- Computer ScienceIEEE International Conference on Computer Vision
- 1 October 2019
Quantitative and qualitative experimental comparison validate the state-of-the-art performance of MopNet.
Deep Photometric Stereo Network
- Hiroaki Santo, M. Samejima, Yusuke Sugano, Boxin Shi, Y. Matsushita
- Computer ScienceIEEE International Conference on Computer Vision…
- 1 October 2017
A deep photometric stereo network (DPSN) that takes reflectance observations under varying light directions and infers the corresponding surface normal per pixel and Evaluation using simulation and real-world scenes shows effectiveness of the proposed approach over previous techniques.
Benchmarking Single-Image Reflection Removal Algorithms
- Renjie Wan, Boxin Shi, Ling-yu Duan, A. Tan, A. Kot
- Computer ScienceIEEE International Conference on Computer Vision
- 1 October 2017
This paper presents the first captured Single-image Reflection Removal dataset ‘SIR2’ with 40 controlled and 100 wild scenes, ground truth of background and reflection, and performs quantitative and visual quality comparisons for four state-of-the-art single-image reflection removal algorithms using four error metrics.
CARS: Continuous Evolution for Efficient Neural Architecture Search
- Zhaohui Yang, Yunhe Wang, Chang Xu
- Computer ScienceComputer Vision and Pattern Recognition
- 11 September 2019
This work develops an efficient continuous evolutionary approach for searching neural networks that provides a series of networks with the number of parameters ranging from 3.7M to 5.1M under mobile settings and surpasses those produced by the state-of-the-art methods on the benchmark ImageNet dataset.
...
...