✨Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling

📝 Summary:
Upsample Anything is a novel test-time optimization framework that enhances low-resolution features to high-resolution outputs without training. It learns an anisotropic Gaussian kernel per image, acting as a universal edge-aware operator. This method achieves state-of-the-art results in tasks li...

🔹 Publication Date: Published on Nov 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.16301
• PDF: https://arxiv.org/pdf/2511.16301

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#Upsampling #ComputerVision #ImageProcessing #DeepLearning #AI

✨POLARIS: Projection-Orthogonal Least Squares for Robust and Adaptive Inversion in Diffusion Models

📝 Summary:
POLARIS minimizes approximate noise errors in diffusion models during image inversion. It robustly treats the guidance scale as a step-wise variable, significantly improving image editing and restoration accuracy by reducing errors at each step.

🔹 Publication Date: Published on Nov 29

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.00369
• PDF: https://arxiv.org/pdf/2512.00369
• Project Page: https://polaris-code-official.github.io/
• Github: https://github.com/Chatonz/POLARIS

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#DiffusionModels #ImageProcessing #AI #MachineLearning #ComputerVision

✨FMA-Net++: Motion- and Exposure-Aware Real-World Joint Video Super-Resolution and Deblurring

📝 Summary:
FMA-Net++ addresses joint video super-resolution and deblurring by modeling motion and dynamic exposure. It employs an exposure-aware sequence architecture, decoupling degradation learning from restoration for top accuracy and efficiency.

🔹 Publication Date: Published on Dec 4

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.04390
• PDF: https://arxiv.org/pdf/2512.04390
• Project Page: https://kaist-viclab.github.io/fmanetpp_site/
• Github: https://kaist-viclab.github.io/fmanetpp_site/

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#VideoSuperResolution #VideoDeblurring #ComputerVision #DeepLearning #ImageProcessing

✨RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenes

📝 Summary:
RL-AWB is a novel framework combining statistical methods with deep reinforcement learning for improved nighttime auto white balance. It is the first RL approach for color constancy, mimicking expert tuning. This method shows superior generalization across various lighting conditions, and a new m...

🔹 Publication Date: Published on Jan 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.05249
• PDF: https://arxiv.org/pdf/2601.05249
• Project Page: https://ntuneillee.github.io/research/rl-awb/

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#ReinforcementLearning #ComputerVision #ImageProcessing #AutoWhiteBalance #LowLightImaging

✨RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenes

📝 Summary:
RL-AWB is a novel framework for nighttime auto white balance. It combines statistical methods with deep reinforcement learning, mimicking expert tuning to improve color constancy in low-light scenes. The method shows superior generalization across various lighting conditions and includes a new mu...

🔹 Publication Date: Published on Jan 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.05249
• PDF: https://arxiv.org/pdf/2601.05249
• Project Page: https://ntuneillee.github.io/research/rl-awb/
• Github: https://github.com/BrianChen1120/RL-AWB

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#ReinforcementLearning #DeepLearning #ComputerVision #ImageProcessing #AWB

✨360Anything: Geometry-Free Lifting of Images and Videos to 360°

📝 Summary:
360Anything is a geometry-free framework using diffusion transformers to lift perspective images and videos to 360 panoramas without camera metadata. It achieves state-of-the-art results and uses circular latent encoding to eliminate seam artifacts.

🔹 Publication Date: Published on Jan 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.16192
• PDF: https://arxiv.org/pdf/2601.16192
• Github: https://360anything.github.io/

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#ComputerVision #DiffusionModels #360Photography #ImageProcessing #DeepLearning

✨HyPER-GAN: Hybrid Patch-Based Image-to-Image Translation for Real-Time Photorealism Enhancement

📝 Summary:
HyPER-GAN is a lightweight U-Net based model for real-time photorealism enhancement. Its hybrid training strategy, using real-world patches, improves visual realism, semantic consistency, and inference speed over state-of-the-art methods.

🔹 Publication Date: Published on Mar 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.10604
• PDF: https://arxiv.org/pdf/2603.10604
• Github: https://github.com/stefanos50/HyPER-GAN

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#GAN #ComputerVision #DeepLearning #ImageProcessing #Photorealism

✨It Takes Two: A Duet of Periodicity and Directionality for Burst Flicker Removal

📝 Summary:
Flicker artifacts in short-exposure photos are addressed by Flickerformer, a transformer-based architecture. It leverages flicker's intrinsic periodicity and directionality to effectively remove artifacts without introducing ghosting, outperforming existing methods.

🔹 Publication Date: Published on Mar 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.22794
• PDF: https://arxiv.org/pdf/2603.22794

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#ImageProcessing #DeepLearning #ComputerVision #Transformers #FlickerRemoval

🔥 ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition

💡 The paper ReDesign presents a novel approach to recovering editable design structures from images, a common and costly bottleneck in modern design workflows. The problem is challenging because it requires recovering multiple attributes such as typography, vector geometry, colors, grouping, and layer ordering. The proposed method, ReDesign, uses an agentic framework that grows an editable layer hierarchy by selecting and composing specialized tools across modalities. To ensure reliability despite imperfect tool outputs, the framework introduces a verification mechanism at each expansion step, providing local accept, prune, or retry feedback that prevents error accumulation and avoids large-scale reruns.

The authors evaluate the method's editability at scale using the Figma Edit Replay Benchmark, consisting of 909 raw Figma files and 14796 controlled edit instructions that replay edits on reconstructed outputs. The results show that ReDesign achieves strong visual fidelity while delivering the highest editability across layout, color, and text edits, outperforming layered decomposition baselines and serial tool use pipelines. The paper's contributions include the introduction of the ReDesign framework, the Figma Edit Replay Benchmark, and the demonstration of the method's effectiveness in recovering editable design structures from images. Overall, the paper presents a significant advancement in the field of design recovery and editing, with potential applications in various design workflows.

📅 Published on Jul 28

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2607.25565
• PDF: https://arxiv.org/pdf/2607.25565
• Project Page: https://jintae-00.github.io/ReDesign/

📊 Datasets citing this paper:
• https://huggingface.co/datasets/Jintae-Park/ReDesign-Figma909

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#ComputerVision #GraphicDesignAutomation #ImageProcessing #VectorGraphicsRecovery #DesignStructureExtraction