Yu-Lun (Alex) Liu | 劉育綸

I am an Assistant Professor in the Department of Computer Science at National Yang Ming Chiao Tung University. I work on image/video processing, computer vision, and computational photography, particularly on essential problems requiring machine learning with insights from geometry and domain-specific knowledge.

Prior to joining NYCU, I was a Research Scientist Intern at Meta Reality Labs Research and a senior software engineer at MediaTek Inc. I received my PhD from NTU, CSIE in 2022, where I was a member of CMLab.

I am looking for undergraduate / master's / Ph.D. / postdoc students to join my group. If you are interested in working with me and want to conduct research in image processing, computer vision, and machine learning, don't hesitate to contact me directly with your CV and transcripts.

Email  /  CV  /  Google Scholar  /  Facebook  /  Instagram  /  Github  /  YouTube

• Mar 2024: Two conference papers conditionally accepted to SIGGRAPH 2024
• Mar 2024: Invited Seminar at NTU
• Feb 2024: Two conference papers accepted to CVPR 2024
• Feb 2024: Keynote at 2024 Fun AI Winter Camp
• Jan 2024: One conference paper accepted to ICLR 2024
• Jan 2024: One Journal paper accepted to IJCV 2024
• Dec 2023: One conference paper accepted to AAAI 2024
• Aug 2023: Honored to receive Google's Research Grant!
• Aug 2023: Honored to receive the 中華民國影像處理與圖形識別學會博士優等論文獎 (IPPR Best Ph.D. Thesis Award)!
• July 2023: Excited and honored to have been selected as a 玉山青年學者 (Yushan Young Fellow), 2023!
• July 2023: Two conference papers accepted to ICCV 2023
• May 2023: Talk at MediaTek Inc.
• April 2023: Invited Seminar at NTHU
• Mar 2023: Talk at the 5th AII Workshop
• Mar 2023: Invited Seminar at NYCU
• Mar 2023: Two conference papers accepted to CVPR 2023
• Jan 2023: Talk at Academia Sinica
• Nov 2022: Invited Seminar at NTHU

This paper addresses text-supervised semantic segmentation, aiming to learn a model capable of segmenting arbitrary visual concepts within images by using only imagetext pairs without dense annotations.

This work reconstructs the previous HumanNeRF approach, combining explicit and implicit human representations with both general and specific mapping processes, and shows that explicit shape can filter the information used to fit implicit representation, and frozen general mapping combined with point-specific mapping can effectively avoid overfitting and improve pose generalization performance.

This work proposes a novel dual-branch framework named DAEFR, which introduces an auxiliary LQ branch that extracts crucial information from the LQ inputs and incorporates association training to promote effective synergy between the two branches, enhancing code prediction and output quality.

This work proposes a simple yet effective method for correcting perspective distortions in a single close-up face using GAN inversion using a perspective-distorted input facial image, and develops starting from a short distance, optimization scheduling, reparametrizations, and geometric regularization.

An algorithm that allows joint refinement of camera pose and scene geometry represented by decomposed low-rank tensor, using only 2D images as supervision is proposed, which achieves an equivalent effect to brute-force 3D convolution with only incurring little computational overhead.

This work proposes the continuous exposure value representation (CEVR), which uses an implicit function to generate LDR images with arbitrary EVs, including those unseen during training, to improve HDR reconstruction.

The studies indicate that the proposed image-induced geometry-aware representation can enable image-based methods to attain superior detection accuracy than the seminal point cloud-based method, VoteNet, in two practical scenarios: (1) scenarios where point clouds are sparse and noisy, such as in ARKitScenes, and (2) scenarios involve diverse object classes, particularly classes of small objects, as in the case in ScanNet200.

This work presents an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video, and shows that progressive optimization significantly improves the robustness of the reconstruction.

This work addresses the robustness issue by jointly estimating the static and dynamic radiance fields along with the camera parameters (poses and focal length) and shows favorable performance over the state-of-the-art dynamic view synthesis methods.

This work forms a novel training objective, called Denoising Likelihood Score Matching (DLSM) loss, for the classifier to match the gradients of the true log likelihood density, and concludes that the conditional scores can be accurately modeled, and the effect of the score mismatch issue is alleviated.

This work alternate between estimating dense optical flow fields of the two layers and reconstructing each layer from the flow-warped images via a deep convolutional neural network, facilitates accommodating potential errors in the flow estimation and brittle assumptions, such as brightness consistency.

This paper proposes a method to estimate not only a depth map but an AiF image from a set of images with different focus positions (known as a focal stack), and shows that this method outperforms the state-of-the-art methods both quantitatively and qualitatively, and also has higher efficiency in inference time.

This work presents a frame synthesis algorithm to achieve full-frame video stabilization that first estimate dense warp fields from neighboring frames and then synthesize the stabilized frame by fusing the warped contents.

This paper proposes a learning-based multimodal tone-mapping method, which not only achieves excellent visual quality but also explores the style diversity and shows that the proposed method performs favorably against state-of-the-art tone-Mapping algorithms both quantitatively and qualitatively.

A data-driven approach, where a generative noise model is learned from real-world noise, which is camera-aware and quantitatively and qualitatively outperforms existing statistical noise models and learning-based methods.

This work model the HDR-to-LDR image formation pipeline as the dynamic range clipping, non-linear mapping from a camera response function, and quantization, and proposes to learn three specialized CNNs to reverse these steps.

The method leverages the motion differences between the background and the obstructing elements to recover both layers and alternate between estimating dense optical flow fields of the two layers and reconstructing each layer from the flow-warped images via a deep convolutional neural network.

A novel deep network for estimating depth maps from a light field image that generates an attention map indicating the importance of each view and its potential for contributing to accurate depth estimation and enforce symmetry in the attention map to improve accuracy.

A new loss term, the cycle consistency loss, which can better utilize the training data to not only enhance the interpolation results, but also maintain the performance better with less training data is introduced.

This paper focuses on creating a global background model of a video sequence using the depth maps together with the RGB pictures, and develops a recursive algorithm that iterates between the depth map and color pictures.

A backward warping process is proposed to replace the forward warped process, and the artifacts (particularly the ones produced by quantization) are significantly reduced, so the subjective quality of the synthesized virtual view images is thus much improved.

My research is made possible by the generous support of the following organizations.

Stolen from Jon Barron's website.
Last updated April 2024.