Computer Vision133 [2025-1] 임수연 - SPVNAS https://arxiv.org/abs/2007.16100 Searching Efficient 3D Architectures with Sparse Point-Voxel ConvolutionSelf-driving cars need to understand 3D scenes efficiently and accurately in order to drive safely. Given the limited hardware resources, existing 3D perception models are not able to recognize small instances (e.g., pedestrians, cyclists) very well due toarxiv.org안녕하세요, 이번 글에서는 Searching Eff.. 2025. 3. 7. [2025-1] 김유현 - Wasserstein GAN https://arxiv.org/abs/1701.07875 Wasserstein GANWe introduce a new algorithm named WGAN, an alternative to traditional GAN training. In this new model, we show that we can improve the stability of learning, get rid of problems like mode collapse, and provide meaningful learning curves useful for debuggiarxiv.org 1. IntroductionGAN의 목적은 데이터 $x$의 분포 $P(x)$를 직접 학습하는 것이 목적이다. $P(x)$를 매개변수 θ를 사용하여 .. 2025. 2. 28. [2025-1] 전연주 - VoteNet: Deep Hough Voting for 3D Object Detection in Point Clouds 논문 링크: 1904.09664저자:Charles R. Qi (Facebook AI Research)Or Litany (Facebook AI Research)Kaiming He (Facebook AI Research)Leonidas J. Guibas (Facebook AI Research, Stanford University)발행일: 2019. 08. 221. Introduction3D 객체 탐지의 핵심 목표는 3D 장면에서 객체를 찾아(3D 바운딩 박스) 분류(semantic class)하는 것이다. 이미지를 통한 2D 객체 탐지와 달리, 포인트 클라우드(point cloud)는 객체의 정확한 기하학 정보를 직접 제공하므로 조명 변화 등에 강인한 장점이 있다. 하지만 포인트 클라우드는 불규칙(spars.. 2025. 2. 26. [2025-1] 박서형 - DemoFusion: Democratising High-Resolution Image Generation With No $$$ https://arxiv.org/abs/2311.16973 DemoFusion: Democratising High-Resolution Image Generation With No $$$High-resolution image generation with Generative Artificial Intelligence (GenAI) has immense potential but, due to the enormous capital investment required for training, it is increasingly centralised to a few large corporations, and hidden behind paywallsarxiv.org 1. Abstracthigh-resolution im.. 2025. 2. 22. 이전 1 ··· 7 8 9 10 11 12 13 ··· 34 다음
