본문 바로가기

AI

(109)
[DiT-3D or DDPM Code 분석] Github Linkhttps://github.com/DiT-3D/DiT-3D/blob/main/train.py DiT-3D/train.py at main · DiT-3D/DiT-3D🔥🔥🔥Official Codebase of "DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation" - DiT-3D/DiT-3Dgithub.com*매우매우 글이 긴 초장문입니다..!각 코드별로 엄청 상세하게 리뷰했고, 최대한 흐름에 따라서 코드와 수식을 붙여서 설명하였습니다.*DiT-3D 코드를 기반으로 설명하고 있지만, dataloader를 제외한 나머지 리뷰는 2D 기반의 DDPM or Diffusion Transformer 코드의 흐름으로 이..
[MeshAnything 논문 리뷰] - MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers *MeshAnything를 위한 논문 리뷰 글입니다! 궁금하신 점은 댓글로 남겨주세요! MeshAnything paper: https://arxiv.org/abs/2406.10163 MeshAnything: Artist-Created Mesh Generation with Autoregressive TransformersRecently, 3D assets created via reconstruction and generation have matched the quality of manually crafted assets, highlighting their potential for replacement. However, this potential is largely unrealized because thes..
[Mamba 논문 리뷰 5] - Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model *Mamba 논문 리뷰 시리즈5 입니다! 궁금하신 점은 댓글로 남겨주세요!시리즈 1: Hippo시리즈 2: LSSL시리즈 3: S4시리즈 4: Mamba시리즈 5: Vision MambaVision Mamba paper: [2401.09417] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model (arxiv.org)  Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space ModelRecently the state space models (SSMs) with efficient hardware-aw..
[Mamba 논문 리뷰 4] - Mamba: Linear-Time Sequence Modeling with Selective State Spaces *Mamba 논문 리뷰 시리즈4 입니다! 궁금하신 점은 댓글로 남겨주세요!시리즈 1: Hippo시리즈 2: LSSL시리즈 3: S4시리즈 4: Mamba시리즈 5: Vision MambaMamba paper: https://arxiv.org/abs/2312.00752 Mamba: Linear-Time Sequence Modeling with Selective State SpacesFoundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many sub..
[Mamba 논문 리뷰 3] - S4: Efficiently Modeling Long Sequences with Structured State Spaces *Mamba 논문 리뷰 시리즈3 입니다! 궁금하신 점은 댓글로 남겨주세요!시리즈 1: Hippo시리즈 2: LSSL시리즈 3: S4시리즈 4: Mamba시리즈 5: Vision MambaS4 paper: [2111.00396] Efficiently Modeling Long Sequences with Structured State Spaces (arxiv.org)  Efficiently Modeling Long Sequences with Structured State SpacesA central goal of sequence modeling is designing a single principled model that can address sequence data across a range of modal..
[Mamba 논문 리뷰 2] - LSSL: Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers *Mamba 논문 리뷰 시리즈2 입니다! 궁금하신 점은 댓글로 남겨주세요!시리즈 1: Hippo시리즈 2: LSSL시리즈 3: S4시리즈 4: Mamba시리즈 5: Vision MambaLSSL paper: [2110.13985] Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers (arxiv.org)  Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space LayersRecurrent neural networks (RNNs), temporal convolutions, and neural d..
[Mamba 논문 리뷰 1] - HiPPO: Recurrent Memory with Optimal Polynomial Projections *Mamba 논문 리뷰 시리즈1 입니다! 궁금하신 점은 댓글로 남겨주세요!시리즈 1: Hippo시리즈 2: LSSL시리즈 3: S4시리즈 4: Mamba시리즈 5: Vision MambaHiPPO paper: https://arxiv.org/abs/2008.07669 HiPPO: Recurrent Memory with Optimal Polynomial ProjectionsA central problem in learning from sequential data is representing cumulative history in an incremental fashion as more data is processed. We introduce a general framework (HiPPO) for the o..
[LGM 논문 리뷰] Large Multi-View Gaussian Model for High-Resolution 3D Content Creation *LGM를 위한 논문 리뷰 글입니다! 궁금하신 점은 댓글로 남겨주세요! LGM github: LGM (kiui.moe)  LGMLGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation Arxiv 2024 Jiaxiang Tang1, Zhaoxi Chen2, Xiaokang Chen1, Tengfei Wang3, Gang Zeng1, Ziwei Liu2 1 Peking University   2 S-Lab, Nanyang Technological University   3 Shanghai AI Lame.kiui.moeContents1. Simple Introduction2. Background Knowledge: Gaussia..
[3D Gaussian Splatting 간단한 논문 리뷰] *Gaussian Splatting에 대한 간단한 논문 리뷰 입니다!*이해를 돕기 위해 수식은 거의 제외했습니다. GS 논문: repo-sam.inria.fr/fungraph/3d-gaussian-splatting/3d_gaussian_splatting_high.pdf GS github: 3D Gaussian Splatting for Real-Time Radiance Field Rendering (inria.fr) 3D Gaussian Splatting for Real-Time Radiance Field Rendering[Müller 2022] Müller, T., Evans, A., Schied, C. and Keller, A., 2022. Instant neural graphics primitives..
[LRM 논문 리뷰] - LARGE RECONSTRUCTION MODEL FOR SINGLE IMAGE TO 3D *LRM를 위한 논문 리뷰 글입니다! 궁금하신 점은 댓글로 남겨주세요! LRM paper: https://arxiv.org/abs/2311.04400 LRM: Large Reconstruction Model for Single Image to 3DWe propose the first Large Reconstruction Model (LRM) that predicts the 3D model of an object from a single input image within just 5 seconds. In contrast to many previous methods that are trained on small-scale datasets such as ShapeNet in a category-specarxi..
[FNO 논문 리뷰 & 코드 리뷰] - FOURIER NEURAL OPERATOR FOR PARAMETRIC PARTIAL DIFFERENTIAL EQUATIONS *FNO를 위한 논문 리뷰 글입니다! 궁금하신 점은 댓글로 남겨주세요! FNO paper: [2010.08895] Fourier Neural Operator for Parametric Partial Differential Equations (arxiv.org) Fourier Neural Operator for Parametric Partial Differential EquationsThe classical development of neural networks has primarily focused on learning mappings between finite-dimensional Euclidean spaces. Recently, this has been generalized to neural oper..
[SMPL-X Implementation] KyujinHan/Smplify-X-Perfect-Implementation Github: https://github.com/KyujinHan/Smplify-X-Perfect-Implementation GitHub - KyujinHan/Smplify-X-Perfect-Implementation: Smplify-X implementation. (2024. 03. 18 No Error & Recent version) Smplify-X implementation. (2024. 03. 18 No Error & Recent version) - KyujinHan/Smplify-X-Perfect-Implementation github.com Smplify-X Implementation (recent version) SMPL-X를 예전에 구현한 적이 있었는데, 코드가 다시 날아가서 다시 구현하..

반응형