Research Article Hub

Explore the latest peer-reviewed research with AI-generated summaries, key findings, and insights for easy understanding. All content is legally sourced from academic metadata with links to original papers.

2,222Articles
5Disciplines
3Live Sources
🔍
🤖 Artificial Intelligence OpenAlex

RePaint: Inpainting using Denoising Diffusion Probabilistic Models

📅 Jun 2022 👤 Andreas Lugmayr, Martin Danelljan, Andrés Romero et al. 📊 1,469 citations

Free-form inpainting is the task of adding new content to an image in the regions specified by an arbitrary binary mask. Re-Paint outperforms advanced Autoregressive, and GAN approaches for at least f...

🤖 Artificial Intelligence OpenAlex

Towards Total Recall in Industrial Anomaly Detection

📅 Jun 2022 👤 Karsten Roth, Latha Pemula, Joaquin Zepeda et al. 📊 1,348 citations

Being able to spot defective parts is a critical component in large-scale industrial manufacturing. We further report competitive results on two additional datasets and also find competitive results i...

🤖 Artificial Intelligence OpenAlex

Scaling Up Your Kernels to 31×31: Revisiting Large Kernel Design in CNNs

📅 Jun 2022 👤 Xiaohan Ding, Xiangyu Zhang, Jungong Han et al. 📊 1,323 citations

We revisit large kernel design in modern convolutional neural networks (CNNs). Our study further reveals that, in contrast to small-kernel CNNs, large-kernel CNNs have much larger effective receptive...

🤖 Artificial Intelligence OpenAlex

ResNeSt: Split-Attention Networks

📅 Jun 2022 👤 Hang Zhang, Chongruo Wu, Zhongyue Zhang et al. 📊 1,278 citations

The ability to learn richer network representations generally boosts the performance of deep learning models. Adding a Split-Attention module into the architecture design space of RegNet-Y and FBNetV2...

🤖 Artificial Intelligence OpenAlex

Plenoxels: Radiance Fields without Neural Networks

📅 Jun 2022 👤 Sara Fridovich-Keil, Alex Yu, Matthew Tancik et al. 📊 1,252 citations

We introduce Plenoxels (plenoptic voxels), a systemfor photorealistic view synthesis. On standard, benchmark tasks, Plenoxels are optimized two orders of magnitude faster than Neural Radiance Fields w...

🤖 Artificial Intelligence OpenAlex

CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows

📅 Jun 2022 👤 Xiaoyi Dong, Jianmin Bao, Dongdong Chen et al. 📊 1,228 citations

We present CSWin Transformer, an efficient and effective Transformer-based backbone for general-purpose vision tasks. By further pretraining on the larger dataset ImageNet-21K, we achieve 87.5% Top-1...

🤖 Artificial Intelligence OpenAlex

SimMIM: a Simple Framework for Masked Image Modeling

📅 Jun 2022 👤 Zhenda Xie, Zheng Zhang, Yue Cao et al. 📊 1,146 citations

This paper presents SimMIM, a simple framework for masked image modeling. We also leverage this approach to address the data-hungry issue faced by large-scale model training, that a 3B model (Swin V2-...

🤖 Artificial Intelligence OpenAlex

MetaFormer is Actually What You Need for Vision

📅 Jun 2022 👤 Weihao Yu, Mi Luo, Pan Zhou et al. 📊 1,132 citations

Transformers have shown great potential in computer vision tasks. This work calls for more future research dedicated to improving MetaFormer instead of focusing on the token mixer modules.

🤖 Artificial Intelligence OpenAlex

Efficient Geometry-aware 3D Generative Adversarial Networks

📅 Jun 2022 👤 Eric R. Chan, Connor Z. Lin, Matthew A. Chan et al. 📊 998 citations

Unsupervised generation of high-quality multi-view-consistent images and 3D shapes using only collections of single-view 2D photographs has been a long-standing challenge. By decoupling feature genera...

🤖 Artificial Intelligence OpenAlex

Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrare...

📅 Jun 2022 👤 Jinyuan Liu, Xin Fan, Zhanbo Huang et al. 📊 961 citations

This study addresses the issue of fusing infrared and visible images that appear differently for object detection. Extensive experiments on several public datasets and our benchmark demonstrate that o...

🤖 Artificial Intelligence OpenAlex

Toward Fast, Flexible, and Robust Low-Light Image Enhancement

📅 Jun 2022 👤 Long Ma, Tengyu Ma, Risheng Liu et al. 📊 946 citations

Existing low-light image enhancement techniques are mostly not only difficult to deal with both visual quality and computational efficiency but also commonly invalid in unknown complex scenarios. Appl...

🤖 Artificial Intelligence OpenAlex

TrackFormer: Multi-Object Tracking with Transformers

📅 Jun 2022 👤 Tim Meinhardt, Alexander Kirillov, Laura Leal-Taixé et al. 📊 942 citations

The challenging task of multi-object tracking (MOT) requires simultaneous reasoning about track initialization, identity, and spatio-temporal trajectories. TrackFormer introduces a new tracking-by-att...

🤖 Artificial Intelligence OpenAlex

DN-DETR: Accelerate DETR Training by Introducing Query DeNoising

📅 Jun 2022 👤 Feng Li, Hao Zhang, Shilong Liu et al. 📊 908 citations

We present in this paper a novel denoising training method to speedup DETR (DEtection TRansformer) training and offer a deepened understanding of the slow convergence issue of DETR-like methods. Compa...

🤖 Artificial Intelligence OpenAlex

Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction

📅 Jun 2022 👤 Cheng Sun, Min Sun, Hwann-Tzong Chen 📊 869 citations

We present a super-fast convergence approach to reconstructing the per-scene radiance field from a set of images that capture the scene with known poses. Finally, evaluation on five inward-facing benc...

🤖 Artificial Intelligence OpenAlex

Decoupled Knowledge Distillation

📅 Jun 2022 👤 Borui Zhao, Quan Cui, Renjie Song et al. 📊 854 citations

advanced distillation methods are mainly based on distilling deep features from intermediate layers, while the significance of logit distillation is greatly overlooked. This paper proves the great pot...

🤖 Artificial Intelligence OpenAlex

Vision Transformer with Deformable Attention

📅 Jun 2022 👤 Zhuofan Xia, Xuran Pan, Shiji Song et al. 📊 851 citations

Transformers have recently shown superior performances on various vision tasks. Extensive experi-ments show that our models achieve consistently improved results on comprehensive benchmarks.

🤖 Artificial Intelligence OpenAlex

CMT: Convolutional Neural Networks Meet Vision Transformers

📅 Jun 2022 👤 Jianyuan Guo, Kai Han, Han Wu et al. 📊 850 citations

Vision transformers have been successfully applied to image recognition tasks due to their ability to capture long-range dependencies within an image. In particular, our CMT-S achieves 83.5% top-1 acc...

🤖 Artificial Intelligence OpenAlex

TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers

📅 Jun 2022 👤 Xuyang Bai, Zeyu Hu, Xinge Zhu et al. 📊 810 citations

LiDAR and camera are two important sensors for 3D object detection in autonomous driving. We provide extensive experiments to demonstrate its robustness against degenerated image quality and calibrati...

🤖 Artificial Intelligence OpenAlex

Scaling Vision Transformers

📅 Jun 2022 👤 Xiaohua Zhai, Alexander Kolesnikov, Neil Houlsby et al. 📊 783 citations

Attention-based neural networks such as the Vision Transformer (ViT) have recently attained advanced results on many computer vision benchmarks. As a result, we successfully train a ViT model with two...

🤖 Artificial Intelligence OpenAlex

Depth-supervised NeRF: Fewer Views and Faster Training for Free

📅 Jun 2022 👤 Kangle Deng, Andrew Liu, Jun-Yan Zhu et al. 📊 764 citations

A commonly observed failure mode of Neural Radiance Field (NeRF) is fitting incorrect geometries when given an insufficient number of input views. Further, we show that our loss is compatible with oth...

📜 Legal Notice: All articles are sourced via open-access academic APIs (OpenAlex, arXiv, PubMed). Only metadata (titles, authors, publication dates, DOIs) and AI-generated plain-English summaries are displayed — never full copyrighted article text. Original abstracts are not copied or reproduced. Each article links back to the original source for full access.