Papers with Code 아카이브

Denoising

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 6
평가표: 6
보존된 평가 기록: 15

Denoising is a task in image processing and computer vision that aims to remove or reduce noise from an image. Noise can be introduced into an image due to various reasons, such as camera sensor limitations, lighting conditions, and compression artifacts. The goal of denoising is to recover the original image, which is considered to be noise-free, from a noisy observation.

<span style="color:grey; opacity: 0.6">( Image credit: Beyond a Gaussian Denoiser )</span>

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/toshas/ttnf

공식 코드

TT-NF: Tensor Train Neural Fields

https://github.com/toshihiro-ota/attnbm

공식 코드

Attention in a family of Boltzmann machines emerging from modern Hopfield networks

https://github.com/toyotaresearchinstitute/gradient-estimation-sampler

공식 코드

Interpreting and Improving Diffusion Models from an Optimization Perspective

https://github.com/tqtqliu/free4d

공식 코드

Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency

https://github.com/tr3e/intergen

공식 코드

InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions

https://github.com/trainlaboratory/multiscaletextureloss-mstlf

공식 코드

Multi-Scale Texture Loss for CT denoising with GANs

https://github.com/trestad/mitigating-reversal-curse

공식 코드

An Analysis and Mitigation of the Reversal Curse

https://github.com/tricktreat/diffusionner

공식 코드

DiffusionNER: Boundary Diffusion for Named Entity Recognition

https://github.com/trile83/rqunetvae

공식 코드

Riesz-Quincunx-UNet Variational Auto-Encoder for Satellite Image Denoising

https://github.com/tristan-deep/joint-diffusion

공식 코드

Removing Structured Noise with Diffusion Models

https://github.com/trougnouf/compression

공식 코드

On the Importance of Denoising when Learning to Compress Images

https://github.com/trougnouf/nind-denoise

공식 코드

Natural Image Noise Dataset

https://github.com/trungpx/xmdpt

공식 코드

Cross-view Masked Diffusion Transformers for Person Image Synthesis

https://github.com/tsachiblau/Threat-Model-Agnostic-Adversarial-Defense-using-Diffusion-Models

공식 코드

Threat Model-Agnostic Adversarial Defense using Diffusion Models

https://github.com/tsinghua-fib-lab/gpd

공식 코드

Spatio-Temporal Few-Shot Learning via Diffusive Neural Network Generation

https://github.com/tsinghua-fib-lab/graph-denoising-socialrec

공식 코드

Robust Preference-Guided Denoising for Graph based Social Recommendation

https://github.com/tsinghua-fib-lab/kstdiff-urban-flow-generation

공식 코드

Towards Generative Modeling of Urban Flow through Knowledge-enhanced Denoising Diffusion

https://github.com/tsinghua-fib-lab/spdiff

공식 코드

Social Physics Informed Diffusion Model for Crowd Simulation

https://github.com/tsryo/aae-recommender

공식 코드

Autoencoder-based prediction of ICU clinical codes

https://github.com/tub-rip/event_based_image_rec_inverse_problem

공식 코드

Formulating Event-based Image Reconstruction as a Linear Inverse Problem with Deep Regularization using Optical Flow

https://github.com/tubui/rosteals

공식 코드

RoSteALS: Robust Steganography using Autoencoder Latent Space

https://github.com/tufts-ml/graph-generation-edge

공식 코드

Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling

https://github.com/tum-pbs/diffusion-based-flow-prediction

공식 코드

Uncertainty-aware Surrogate Models for Airfoil Flow Simulations with Denoising Diffusion Probabilistic Models

https://github.com/tum-pbs/smdp

공식 코드

Solving Inverse Physics Problems with Score Matching

https://github.com/tum-vision/learn_prox_ops

공식 코드

Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems

https://github.com/tum-vision/sublabel_relax

공식 코드

Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies

https://github.com/tunglm2203/tirl

공식 코드

On the Perturbed States for Transformed Input-robust Reinforcement Learning

https://github.com/tvlearn/evo

공식 코드

Generic Unsupervised Optimization for a Latent Variable Model With Exponential Family Observables

https://github.com/txphome/dfpir

공식 코드

Degradation-Aware Feature Perturbation for All-in-One Image Restoration

https://github.com/tyshiwo/MemNet

공식 코드

MemNet: A Persistent Memory Network for Image Restoration

https://github.com/ubc-vision/StableKeypoints

공식 코드

Unsupervised Keypoints from Pretrained Diffusion Models

https://github.com/ubcdingxin/ccdm

공식 코드

CCDM: Continuous Conditional Diffusion Models for Image Generation

https://github.com/ucla-starai/tiramisu

공식 코드

Image Inpainting via Tractable Steering of Diffusion Models

https://github.com/uclaopt/Provable_Plug_and_Play

공식 코드

Plug-and-Play Methods Provably Converge with Properly Trained Denoisers

https://github.com/ucsb-nlp-chang/copaint

공식 코드

Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models

https://github.com/ucsb-nlp-chang/diffusion-spacetime-attn

공식 코드

Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.