Huu-Phu Do
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Huu-Phu Do has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Ching-Chun Huang
National Yang Ming Chiao Tung University, Hsinchu, Taiwan
5 shared publications - Hao-Chien Hsueh
Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
3 shared publications - Che-Kai Liu
Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
2 shared publications - Po-Chih Hu
National yang Ming Chiao Tung University
2 shared publications - Vu-Hoang Tran
Ho Chi Minh City University of Technology and Engineering, Vietnam
2 shared publications - Wen-Hsiao Peng
National yang Ming Chiao Tung University
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 13620-13628
FreeLit: Paired-Free Indoor Relighting via Physics-Guided Diffusion
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 13620-13628
Open AccessFreeLit: Paired-Free Indoor Relighting via Physics-Guided Diffusion
- Open Access
- 19 February 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 17 (2) , 1-22
ExReg: Wide-range Photo Exposure Correction via a Multi-dimensional Regressor with Attention
Photo exposure correction is widely investigated, but fewer studies focus on correcting under- and over-exposed images simultaneously. Three issues remain open to handle and correct both under- and over-exposed images in a unified way. First, a locally adaptive exposure adjustment may be more flexible instead of learning a global mapping. Second, it is an ill-posed problem to determine the suitable exposure values locally. Third, photos with the same content but different exposures may not reach consistent adjustment results. To this end, we proposed a novel exposure correction network, ExReg, to address the challenges by formulating exposure correction as a multi-dimensional regression process. Given an input image, a compact multi-exposure generation network is introduced to generate images with different exposure conditions for multi-dimensional regression and exposure correction in the next stage. An auxiliary module is designed to predict the region-wise exposure values, guiding the proposed Encoder–Decoder ANP (Attentive Neural Process) to regress the final corrected image. The experimental results show that ExReg can generate well-exposed results and outperform the SOTA method in PSNR for extensive exposure problems. Furthermore, the processing speed, with 0.05 seconds per image on an RTX 3090, is efficient. When tested on the same image under various exposure levels, ExReg also yields results that are visually consistent and physically accurate.
- 19 February 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 17 (2) , 1-22
Open AccessExReg: Wide-range Photo Exposure Correction via a Multi-dimensional Regressor with Attention
Photo exposure correction is widely investigated, but fewer studies focus on correcting under- and over-exposed images simultaneously. Three issues remain open to handle and correct both under- and over-exposed images in a unified way. First, a locally adaptive exposure adjustment may be more flexible instead of learning a global mapping. Second, it is an ill-posed problem to determine the suitable exposure values locally. Third, photos with the same content but different exposures may not reach consistent adjustment results. To this end, we proposed a novel exposure correction network, ExReg, to address the challenges by formulating exposure correction as a multi-dimensional regression process. Given an input image, a compact multi-exposure generation network is introduced to generate images with different exposure conditions for multi-dimensional regression and exposure correction in the next stage. An auxiliary module is designed to predict the region-wise exposure values, guiding the proposed Encoder–Decoder ANP (Attentive Neural Process) to regress the final corrected image. The experimental results show that ExReg can generate well-exposed results and outperform the SOTA method in PSNR for extensive exposure problems. Furthermore, the processing speed, with 0.05 seconds per image on an RTX 3090, is efficient. When tested on the same image under various exposure levels, ExReg also yields results that are visually consistent and physically accurate.
- Open Access
Blind Super Resolution with Reference Images and Implicit Degradation Representation
Previous studies in blind super-resolution (BSR) have primarily concentrated on estimating degradation kernels directly from low-resolution (LR) inputs to enhance super-resolution. However, these degradation kernels, which model the transition from a high-resolution (HR) image to its LR version, should account for not only the degradation process but also the downscaling factor. Applying the same degradation kernel across varying super-resolution scales may be impractical. Our research acknowledges degradation kernels and scaling factors as pivotal elements for the BSR task and introduces a novel strategy that utilizes HR images as references to establish scale-aware degradation kernels. By employing content-irrelevant HR reference images alongside the target LR image, our model adaptively discerns the degradation process. It is then applied to generate additional LR-HR pairs through down-sampling the HR reference images, which are keys to improving the SR performance. Our reference-based training procedure is applicable to proficiently trained blind SR models and zero-shot blind SR methods, consistently outperforming previous methods in both scenarios. This dual consideration of blur kernels and scaling factors, coupled with the use of a reference image, contributes to the effectiveness of our approach in blind super-resolution tasks.
Open AccessBlind Super Resolution with Reference Images and Implicit Degradation Representation
Previous studies in blind super-resolution (BSR) have primarily concentrated on estimating degradation kernels directly from low-resolution (LR) inputs to enhance super-resolution. However, these degradation kernels, which model the transition from a high-resolution (HR) image to its LR version, should account for not only the degradation process but also the downscaling factor. Applying the same degradation kernel across varying super-resolution scales may be impractical. Our research acknowledges degradation kernels and scaling factors as pivotal elements for the BSR task and introduces a novel strategy that utilizes HR images as references to establish scale-aware degradation kernels. By employing content-irrelevant HR reference images alongside the target LR image, our model adaptively discerns the degradation process. It is then applied to generate additional LR-HR pairs through down-sampling the HR reference images, which are keys to improving the SR performance. Our reference-based training procedure is applicable to proficiently trained blind SR models and zero-shot blind SR methods, consistently outperforming previous methods in both scenarios. This dual consideration of blur kernels and scaling factors, coupled with the use of a reference image, contributes to the effectiveness of our approach in blind super-resolution tasks.
- 8 December 2024
- Published by Springer Nature
- p. 38-53
Blind Super Resolution with Reference Images and Implicit Degradation Representation
- 8 December 2024
- Published by Springer Nature
- p. 38-53
Blind Super Resolution with Reference Images and Implicit Degradation Representation
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 253-262
TimeNeRF: Building Generalizable Neural Radiance Fields across Time from Few-Shot Input Views
We present TimeNeRF, a generalizable neural rendering approach for rendering novel views at arbitrary viewpoints and at arbitrary times, even with few input views. For real-world applications, it is expensive to collect multiple views and inefficient to re-optimize for unseen scenes. Moreover, as the digital realm, particularly the metaverse, strives for increasingly immersive experiences, the ability to model 3D environments that naturally transition between day and night becomes paramount. While current techniques based on Neural Radiance Fields (NeRF) have shown remarkable proficiency in synthesizing novel views, the exploration of NeRF's potential for temporal 3D scene modeling remains limited, with no dedicated datasets available for this purpose. To this end, our approach harnesses the strengths of multi-view stereo, neural radiance fields, and disentanglement strategies across diverse datasets. This equips our model with the capability for generalizability in a few-shot setting, allows us to construct an implicit content radiance field for scene representation, and further enables the building of neural radiance fields at any arbitrary time. Finally, we synthesize novel views of that time via volume rendering. Experiments show that TimeNeRF can render novel views in a few-shot setting without per-scene optimization. Most notably, it excels in creating realistic novel views that transition smoothly across different times, adeptly capturing intricate natural scene changes from dawn to dusk.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 253-262
Open AccessTimeNeRF: Building Generalizable Neural Radiance Fields across Time from Few-Shot Input Views
We present TimeNeRF, a generalizable neural rendering approach for rendering novel views at arbitrary viewpoints and at arbitrary times, even with few input views. For real-world applications, it is expensive to collect multiple views and inefficient to re-optimize for unseen scenes. Moreover, as the digital realm, particularly the metaverse, strives for increasingly immersive experiences, the ability to model 3D environments that naturally transition between day and night becomes paramount. While current techniques based on Neural Radiance Fields (NeRF) have shown remarkable proficiency in synthesizing novel views, the exploration of NeRF's potential for temporal 3D scene modeling remains limited, with no dedicated datasets available for this purpose. To this end, our approach harnesses the strengths of multi-view stereo, neural radiance fields, and disentanglement strategies across diverse datasets. This equips our model with the capability for generalizability in a few-shot setting, allows us to construct an implicit content radiance field for scene representation, and further enables the building of neural radiance fields at any arbitrary time. Finally, we synthesize novel views of that time via volume rendering. Experiments show that TimeNeRF can render novel views in a few-shot setting without per-scene optimization. Most notably, it excels in creating realistic novel views that transition smoothly across different times, adeptly capturing intricate natural scene changes from dawn to dusk.