News

Surface reconstruction from point cloud scans plays a pivotal role in 3D vision and graphics, finding diverse applications in areas such as AR/VR games, cultural heritage preservation, and building information modeling (BIM). This task is inherently challenging due to the ill-posed nature of reconstructing continuous surfaces from discrete points. Moreover, real-world point cloud scans introduce quite a few obstacles such as varying densities and sensor noise. These properties make the problem a long standing one, which keeps driving researchers to look for more effective solutions.
Early research focused on combinatorial methods [1]–[2], which inferred the connectivity between points directly. The mainstream of surface reconstruction adopts an implicit surface approach [3]–[4]. That is, the surface is represented as an unknown continuous function which is solved by the associated partial differential equations (PDEs). Although these methods offer good quality, they often require oriented normals or additional constraints. Recently, people develop deep learning (DL) models [5]–[6] to solve this problem based on a supervised learning framework. DL methods exploits the training data to learn an implicit function representation.
Despite their high reconstruction quality, the generalizability and complexity remain to be challenges for DL models. In scenarios such as point cloud compression, quality assessment, and dynamic point cloud processing, there is a growing need for low-complexity, low-latency surface reconstruction methods. However, existing PDE and DL-based methods tend to sacrifice simplicity for high reconstruction quality, leaving a gap for low-complexity solutions.

We adopt the unsupervised framework, propose a lightweight high-performance method, and name it green point-cloud surface reconstruction (GPSR). It can be categorized to the family of implicit surface reconstruction methods. The main idea lies in building a signed distance field (SDF) through approximated heat diffusion and fine tuning it iteratively. [...]

Saliency detection research predominantly falls within two categories: human eye fixation prediction, which involves the prediction of human gaze locations on images where attention is most concentrated [1], and salient object detection (SOD) [2], which aims to identify salient object regions within an image. Our study specifically focuses on the former saliency prediction, which predicts human gaze from visual stimuli.

Saliency detection constitutes a crucial task in predicting human gaze patterns from visual stimuli. The escalating demand for research in saliency detection is driven by the growing necessity to incorporate such techniques into various computer vision tasks and to understand human visual system. Many existing saliency detection methodologies rely on deep neural networks (DNNs) to achieve good performance. However, the extensive model sizes associated with these approaches impede their integration with other modules or deployment on mobile devices.

To address this need, our study introduces a novel saliency detection method, named “GreenSaliency”, which eschews the use of DNNs while emphasizing a small model footprint and low computational complexity. GreenSaliency comprises two primary steps: 1) multi-layer hybrid feature extraction, and 2) multi-path saliency prediction. Empirical findings demonstrate that GreenSaliency achieves performance levels comparable to certain deep-learning-based (DL-based) methods, while necessitating a considerably smaller model size and significantly reduced computational complexity.

[1] Zhaohui Che, Ali Borji, Guangtao Zhai, Xiongkuo Min, Guodong Guo, and Patrick Le Callet, “How is gaze influenced by image transformations? dataset and model”, IEEE Transactions on Image Processing, 29, 2287–300.

[2] Dingwen Zhang, Junwei Han, Yu Zhang, and Dong Xu, “Synthesizing supervision for learning deep saliency network without human annotation”, IEEE transactions on pattern analysis and machine intelligence, 42(7), 1755–69.

Transfer learning is an approach to extract features from source domain and transfer the knowledge of source domain to the target domain, so as to improve the performance of target learners while relieving the pressure to collect a lot of target-domain data[1]. It has been put into wide applications, such as image classification and text classification.

Domain adaptation on digital number datasets, namely MNIST, USPS and SVHN, is the task of transferring learning models across different data sets, aiming to conduct cross-domain feature alignment and build a generalized model that is able to predict labels among various digital number datasets.
Presently, we have trained a green-learning based transfer learning model between MNIST and USPS. The first step is preprocessing and feature extraction, including feature processing for different dataset in order to make them visually similar, raw Saab feature extraction [2] and LNT feature transformation [3] followed by cosine similarity check to find discriminant features. The second step is joint subspace generation, in which for each label in source domain, k-means with number of clusters as 1, 2, 4, 8 are performed separately in order to generate 10, 20, 40 and 80 subspaces, then assign target features to generated subspaces. The third step is to utilize assigned datas to conduct weakly supervised learning to predict label
for rest target data samples. Our goal is to compare and analyze the performance of our green-learning based transfer learning models with other models. In future, we aim to conduct transfer learning among these three digital number datasets mutually and improve the accuracy by improving cross-domain feature alignment.

[1] Zhuang, Fuzhen, et al. “A comprehensive survey on transfer learning.” Proceedings of the IEEE 109.1 (2020): 43-76.
[2] Y. Chen, M. Rouhsedaghat, [...]

LQBoost operates on the principle of leveraging successive linear regressions to mimic the target regression. Each least-square regression serves as a simulation of the corresponding target regression space, mapping the feature space into the current target space and approximating samples within it. The residue of the current target space becomes the regression target for the next iteration. Iteratively, samples with residuals nearing zero are pruned through a thresholding process. Building upon the foundation of LQBoost, in addition to iteratively optimizing the model through thresholding, we can further enhance the feature set using LNT. In each iteration, by removing samples with residuals close to zero, we obtain a clearer and more accurate approximation of the target space. Subsequently, to enrich the feature set and better capture the complex structures within the data, we can utilize LNT to perform local features transform. This iterative regression reduces the gap between the cumulative simulation and the target, resulting in increasingly accurate approximations.

Before this, we performed preprocessing by clustering the dataset into several clusters and using the purity of each cluster as the initial value for regression. If some clusters have high purity, the samples within those clusters use the major label of the cluster as their predicted value. For other clusters, we use the purity as the initial predicted value, and the residue generated by these clusters serves as the target space for the first layer of least square regression in LQBoost.
This preprocessing step is essential for initializing the regression process effectively. By clustering the dataset and utilizing cluster purity, we can assign more accurate initial predictions for each cluster. High-purity clusters, where most samples belong to a single class, provide a straightforward prediction based on the majority label. On [...]

Congratulations to Xuejing Lei for passing her defense. Xuejing’s thesis is titled “Green Image Generation and Label Transfer Techniques.” Her Dissertation Committee includes Jay Kuo (Chair), Antonio Ortega, and Aiichiro Nakano (Outside Member). The Committee members praised Xuejing’s novel contributions and her excellent presentation. Many thanks to our lab members for participating in her rehearsal and providing valuable feedback. MCL News team invited Xuejing for a short talk on her thesis and PhD experience, and here is the summary. We thank Xuejing for her kind sharing, and wish her all the best in the next journey. A high-level abstract of Xuejing’s thesis is given below:

”We designed several generative modeling solutions for texture synthesis, image generation, and image label transfer. Unlike deep-learning-based methods, Our developed generative methods address small model sizes, mathematical transparency, and efficiency in training and generation. We first presented an efficient and lightweight solution for texture synthesis, which can generate diverse texture images given one exemplary texture image. Then, we proposed a novel generative pipeline named GenHop and reformulated it to improve its efficiency and model sizes, yielding our final Green Image generation method. To demonstrate the generalization ability of our generative modeling concepts, we finally adapt it to an image label transfer task and propose a method called Green Image Label Transfer for unsupervised domain adaptation. ”

Xuejing shared her Ph.D. experience at MCL as follows :

I would like first to express my gratitude to Prof. Kuo for his guidance, patience, and unwavering support throughout this journey. His attitude and passion for research have been invaluable to my growth and success. We have been exploring new directions in this field. Since there were few works we could refer to, I experienced a difficult time when Prof. Kuo asked me to tangle [...]