Kwang Pyo Choi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Kwang Pyo Choi has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Chang-Su Kim
Korea University
3 shared publications - Min Woo Park
SangMyung University
2 shared publications - Minsoo Park
Samsung Electronics, Seoul, Republic of Korea
2 shared publications - Seungmin Jeon
Korea University
2 shared publications - Youngo Park
Samsung Electronics
2 shared publications - Basel Salahieh
Vimmerse Inc., San Jose, CA, USA
1 shared publication
Latest Publications
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 173568-173584
Beyond One-Size-Fits-All: Learned Image Compression With Explicit Coding Modes
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 173568-173584
Open AccessBeyond One-Size-Fits-All: Learned Image Compression With Explicit Coding Modes
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 13660-13663
OpenAPV: Open Collaborative Innovation in Professional Video Ecosystem
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 13660-13663
Open AccessOpenAPV: Open Collaborative Innovation in Professional Video Ecosystem
- Open Access
Masked Feature Residual Coding for Neural Video Compression
In neural video compression, an approximation of the target frame is predicted, and a mask is subsequently applied to it. Then, the masked predicted frame is subtracted from the target frame and fed into the encoder along with the conditional information. However, this structure has two limitations. First, in the pixel domain, even if the mask is perfectly predicted, the residuals cannot be significantly reduced. Second, reconstructed features with abundant temporal context information cannot be used as references for compressing the next frame. To address these problems, we propose Conditional Masked Feature Residual (CMFR) Coding. We extract features from the target frame and the predicted features using neural networks. Then, we predict the mask and subtract the masked predicted features from the target features. Thereafter, the difference is fed into the encoder with the conditional information. Moreover, to more effectively remove conditional information from the target frame, we introduce a Scaled Feature Fusion (SFF) module. In addition, we introduce a Motion Refiner to enhance the quality of the decoded optical flow. Experimental results show that our model achieves an 11.76% bit saving over the model without the proposed methods, averaged over all HEVC test sequences, demonstrating the effectiveness of the proposed methods.
Open AccessMasked Feature Residual Coding for Neural Video Compression
In neural video compression, an approximation of the target frame is predicted, and a mask is subsequently applied to it. Then, the masked predicted frame is subtracted from the target frame and fed into the encoder along with the conditional information. However, this structure has two limitations. First, in the pixel domain, even if the mask is perfectly predicted, the residuals cannot be significantly reduced. Second, reconstructed features with abundant temporal context information cannot be used as references for compressing the next frame. To address these problems, we propose Conditional Masked Feature Residual (CMFR) Coding. We extract features from the target frame and the predicted features using neural networks. Then, we predict the mask and subtract the masked predicted features from the target features. Thereafter, the difference is fed into the encoder with the conditional information. Moreover, to more effectively remove conditional information from the target frame, we introduce a Scaled Feature Fusion (SFF) module. In addition, we introduce a Motion Refiner to enhance the quality of the decoded optical flow. Experimental results show that our model achieves an 11.76% bit saving over the model without the proposed methods, averaged over all HEVC test sequences, demonstrating the effectiveness of the proposed methods.
- Open Access
Context-Based Trit-Plane Coding for Progressive Image Compression
Trit-plane coding enables deep progressive image compression, but it cannot use autoregressive context models. In this paper, we propose the context-based trit-plane coding (CTC) algorithm to achieve progressive compression more compactly. First, we develop the context-based rate reduction module to estimate trit probabilities of latent elements accurately and thus encode the trit-planes compactly. Second, we develop the context-based distortion reduction module to refine partial latent tensors from the trit-planes and improve the reconstructed image quality. Third, we propose a retraining scheme for the decoder to attain better rate-distortion tradeoffs. Extensive experiments show that CTC outperforms the baseline trit-plane codec significantly in BD-rate on the Kodak lossless dataset, while increasing the time complexity only marginally. Our codes are available at https://github.com/seungminjeon-github/CTC.
Open AccessContext-Based Trit-Plane Coding for Progressive Image Compression
Trit-plane coding enables deep progressive image compression, but it cannot use autoregressive context models. In this paper, we propose the context-based trit-plane coding (CTC) algorithm to achieve progressive compression more compactly. First, we develop the context-based rate reduction module to estimate trit probabilities of latent elements accurately and thus encode the trit-planes compactly. Second, we develop the context-based distortion reduction module to refine partial latent tensors from the trit-planes and improve the reconstructed image quality. Third, we propose a retraining scheme for the decoder to attain better rate-distortion tradeoffs. Extensive experiments show that CTC outperforms the baseline trit-plane codec significantly in BD-rate on the Kodak lossless dataset, while increasing the time complexity only marginally. Our codes are available at https://github.com/seungminjeon-github/CTC.
- 3 November 2022
- Published by Springer Nature
- p. 182-200
Learning Local Implicit Fourier Representation for Image Warping
- 3 November 2022
- Published by Springer Nature
- p. 182-200
Learning Local Implicit Fourier Representation for Image Warping
- Open Access
DPICT: Deep Progressive Image Compression Using Trit-Planes
We propose the deep progressive image compression using trit-planes (DPICT) algorithm, which is the first learning-based codec supporting fine granular scalability (FGS). First, we transform an image into a latent tensor using an analysis network. Then, we represent the latent tensor in ternary digits (trits) and encode it into a compressed bitstream trit-plane by trit-plane in the decreasing order of significance. Moreover, within each trit-plane, we sort the trits according to their rate-distortion priorities and transmit more important information first. Since the compression network is less optimized for the cases of using fewer trit-planes, we develop a postprocessing network for refining reconstructed images at low rates. Experimental results show that DPICT outperforms conventional progressive codecs significantly, while enabling FGS transmission. Codes are available at https://github.com/jaehanlee-mcl/DPICT.
Open AccessDPICT: Deep Progressive Image Compression Using Trit-Planes
We propose the deep progressive image compression using trit-planes (DPICT) algorithm, which is the first learning-based codec supporting fine granular scalability (FGS). First, we transform an image into a latent tensor using an analysis network. Then, we represent the latent tensor in ternary digits (trits) and encode it into a compressed bitstream trit-plane by trit-plane in the decreasing order of significance. Moreover, within each trit-plane, we sort the trits according to their rate-distortion priorities and transmit more important information first. Since the compression network is less optimized for the cases of using fewer trit-planes, we develop a postprocessing network for refining reconstructed images at low rates. Experimental results show that DPICT outperforms conventional progressive codecs significantly, while enabling FGS transmission. Codes are available at https://github.com/jaehanlee-mcl/DPICT.
- Open Access
- 28 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (9) , 6360-6374
Overview and Efficiency of Decoder-Side Depth Estimation in MPEG Immersive Video
This paper presents the overview and rationale behind the Decoder-Side Depth Estimation (DSDE) mode of the MPEG Immersive Video (MIV) standard, using the Geometry Absent profile, for efficient compression of immersive multiview video. A MIV bitstream generated by an encoder operating in the DSDE mode does not include depth maps. It only contains the information required to reconstruct them in the client or in the cloud: decoded views and metadata. The paper explains the technical details and techniques supported by this novel MIV DSDE mode. The description additionally includes the specification on Geometry Assistance Supplemental Enhancement Information which helps to reduce the complexity of depth estimation, when performed in the cloud or at the decoder side. The depth estimation in MIV is a non-normative part of the decoding process, therefore, any method can be used to compute the depth maps. This paper lists a set of requirements for depth estimation, induced by the specific characteristics of the DSDE. The depth estimation reference software, continuously and collaboratively developed with MIV to meet these requirements, is presented in this paper. Several original experimental results are presented. The efficiency of the DSDE is compared to two MIV profiles. The combined non-transmission of depth maps and efficient coding of textures enabled by the DSDE leads to efficient compression and rendering quality improvement compared to the usual encoder-side depth estimation. Moreover, results of the first evaluation of state-of-the-art multiview depth estimators in the DSDE context, including machine learning techniques, are presented.
- 28 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (9) , 6360-6374
Open AccessOverview and Efficiency of Decoder-Side Depth Estimation in MPEG Immersive Video
This paper presents the overview and rationale behind the Decoder-Side Depth Estimation (DSDE) mode of the MPEG Immersive Video (MIV) standard, using the Geometry Absent profile, for efficient compression of immersive multiview video. A MIV bitstream generated by an encoder operating in the DSDE mode does not include depth maps. It only contains the information required to reconstruct them in the client or in the cloud: decoded views and metadata. The paper explains the technical details and techniques supported by this novel MIV DSDE mode. The description additionally includes the specification on Geometry Assistance Supplemental Enhancement Information which helps to reduce the complexity of depth estimation, when performed in the cloud or at the decoder side. The depth estimation in MIV is a non-normative part of the decoding process, therefore, any method can be used to compute the depth maps. This paper lists a set of requirements for depth estimation, induced by the specific characteristics of the DSDE. The depth estimation reference software, continuously and collaboratively developed with MIV to meet these requirements, is presented in this paper. Several original experimental results are presented. The efficiency of the DSDE is compared to two MIV profiles. The combined non-transmission of depth maps and efficient coding of textures enabled by the DSDE leads to efficient compression and rendering quality improvement compared to the usual encoder-side depth estimation. Moreover, results of the first evaluation of state-of-the-art multiview depth estimators in the DSDE context, including machine learning techniques, are presented.
- 28 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (9) , 6375-6384
Depth-Wise Split Unit Coding Order for Video Compression
In this paper, we propose a depth-wise flexible block processing method called split unit coding order (SUCO) for video coding. Conventionally, block-based image and video compression frameworks always apply raster scans to process blocks in order from left to right. Owing to the fixed coding order, the available information for prediction in the coding blocks is limited to adjacent blocks on the left and top. To address the limitations of block-based images and video compression frameworks, the proposed SUCO provides more flexibility in handling coding block sequences than predicted on the left and top, and thus coding blocks can take advantage of adjacent right information, such as reconstructed pixels and motion information. The flexibility is achieved by depth-wise signaling of preferred coding order for the given partitions. The experiment results demonstrate that the proposed SUCO can effectively improve the coding efficiency of both intra and inter prediction in the latest video coding standards.
- 28 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (9) , 6375-6384
Depth-Wise Split Unit Coding Order for Video Compression
In this paper, we propose a depth-wise flexible block processing method called split unit coding order (SUCO) for video coding. Conventionally, block-based image and video compression frameworks always apply raster scans to process blocks in order from left to right. Owing to the fixed coding order, the available information for prediction in the coding blocks is limited to adjacent blocks on the left and top. To address the limitations of block-based images and video compression frameworks, the proposed SUCO provides more flexibility in handling coding block sequences than predicted on the left and top, and thus coding blocks can take advantage of adjacent right information, such as reconstructed pixels and motion information. The flexibility is achieved by depth-wise signaling of preferred coding order for the given partitions. The experiment results demonstrate that the proposed SUCO can effectively improve the coding efficiency of both intra and inter prediction in the latest video coding standards.