A conference attendee examines a detailed scientific poster titled "Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization" during the CVPR event held in Seattle, WA, on June 17-21, 2024. The poster presents research conducted by Insu Kim, Jae Seok Choi, Geonseok Seo, Kinan Kwon, Jinwoo Shin, and Hyong-Euk Lee from KAIST and Samsung Advanced Institute of Technology, South Korea. The research focuses on developing an efficient blind motion deblurring model for practical applications, addressing the deblurring regression problem, and solving blur classification using pixel discretization and continuous conversion. The left section provides an overview and motivation, highlighting image residual error causes and their correlation with motion types. The middle section explains their methodology, divided into two stages; Stage I involves Blur Pixel Discretization for blur segmentation mapping, while Stage II includes Discrete-to-Continuous (D2C) conversion for simple regression. The poster visually expresses these concepts with charts, diagrams, and sample images. On the right, the Blur Segmentation Map displays examples of blur, sharp images, and image residual error segmented into object motion versus camera motion. At the bottom right, experimental results are showcased, including comparative tables (Table 1 RealBlur and Table 2 RSBlur) and images demonstrating the effectiveness of their methodologies against various existing techniques. The attendee, with their back partially visible, seems engaged with the content, gesturing towards a specific part of the research findings, possibly discussing or contemplating the methodologies or results presented. The setting reflects a formal and interactive environment typical for academic and research conferences. Text transcribed from the image: KAISTS Advanced Institute of SAMSUNG Science and Technology Overview SAMSUNG ADVANCED INSTITUTE OF TECHNOLOGY Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization Insoo Kim¹.2, Jae Seok Choi¹, Geonseok Seo¹, Kinam Kwon¹, Jinwoo Shin2, Hyong-Euk Lee¹ Efficient Blind Motion Deblurring Model for Practical Usage Solving the original deblurring regression problem Solving the blur classification problem and discrete-to-continuous conversion (simple regression) problem Motivation: Image Residual Error Object Blur: Motion region vs. Non-motion region (motion type) No Motion Region Low Error 1Samsung Advanced Institute of Technology (SAIT), South Korea 2Korea Advanced Institute of Science and Technology (KAIST), South Korea Real-World Efficient Motion Deblurring Class 2 Image TLCVPR SEATTLE, WA JUNE 17-21, 2024 Blur Segmentaion Map Camera Motion "Discrete" "Continuous" Classes Class 3- Patch Motion Blur Image Discretized Image Residual Error Residual Error Stage 1: Blur Pixel Discretization Stage II: Discrete-to-Continuous Conversion [Stage 1] Blur Pixel Discretization (Classification) Object Motion " Blur Segmentation Map is optimized by conducting pixel-wise sampling on deconvolved class images. It visually aligns with image residual error Blur Log-T FTEXP Experimental Results Ranyack Sharp Image Residual Error Blur Segmentation Map Kernel Estimator Sampling Object Motion Region Bur Latent Sharp Basis Kemels High Error Deconvolved Class images Deconvolved Image Sharp Image Blur Image Uniform Blur: High-frequency vs. Low-frequ hboring pixels) -Frequency Region -Low Error Bor Pixel Discretizac Blur Segmentation Map Stage 1: Classification Model Flapjack [Stage II] D2C conversion (Simple Regression) Image residual error is estimated by converting blur segmentation map, i.e., discretized image residual error into a continuous form B Concatenation Methods GMAC High-Frequency Region RealBlur-J PSNRY SSIM - High error MPRNet 35 MIMO-UNet+ 777.80 154.41 PMIMO-UN operty ey component Stipficemer 349 MAXIM-35 (35) FFTFormer [21] GRL-8[21] 80.21 109.99 399.50 31.76 0.922 31.92 0.929 32.65 0.933 32.48 0.529 32.84 0.535 Methods SRN-Debilur (53 MIMO-UNet- MPRNet 132.45 2285 28 NAFN-645 63.64 Bur Blur Phel Discretizer D2C quency property Segmentation Map Image Converter Residual Emor Deblumed Image SepDeblum-So 34.44 22.62 0.502 32.82 0.532 32.50 0:328 32.53 8327 Restumer (4 Uliorer-8 [38 Seg Debilar-Lou NAFNes-64 þ SerDeblur-Sum) Samsung EnhanceX Google Uniblur NAFNes-32+ RealBiler-R. PSNR SSIM 39.32 0.572 41.00 0.572 38.84 0.574 38.45 0.962 41.39 0.573 41.20 0.574 38.99 0.93 39.75 0.973 SegDebitur-S R:580ur GMAC 1434.82 PSNR SSIMT 32.53 8.540 154.41 33.37 41856 772.00 41963 141.00 33.69 01963 86150 3338 4.966 6354 33.97 4.966 34.44 33.96 865 6268 12.56 0.534 41:23 0.975 SepDeblur-nurs) SegDebilan-Lours) 6268 3423 6248 33.50 0.938 41.79 6.576 SegDebitur-Lo Stage : Debiluming Model 6258 34.63 ALSTS [Table 1] RealBlur [Table 2] RSBlur