Neural Fields with Thermal Activations for Arbitrary-Scale Super-Resolution

[MIR 24] Fully 1x1 Convolutional Network for Lightweight Image Super-Resolution

Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation. In CVPR 2022.

[ECCV 2024] InstructIR: High-Quality Image Restoration Following Human Instructions https://huggingface.co/spaces/marcosv/InstructIR

[AAAI 2025] Official codes of "ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models".

Official implementation of Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting (ECCV 2024)

[CVPR 2024] Deformable Convolution v4

BISMO: A Scalable Bit-Serial Matrix Multiplication Overlay for Reconfigurable Computing

[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

Transformer based DLGSAnetwork for super resolution.

This is the official pytorch implementation for the paper: *Quantformer: Learning Extremely Low-precision Vision Transformers*.

[NeurIPS 2022] ShuffleMixer: An Efficient ConvNet for Image Super-Resolution

[ICCV 2023] Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution; runner-up method for the model complexity track in NTIRE2023 Efficient SR challenge

An official implement of CVPR 2023 paper - NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers

[TMLR] Official PyTorch implementation of paper "Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision"

[TIP 2022] Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training. Plus, an image classification toolbox includes ResNet, Wide-ResNet, ResNeXt, ResNeSt, ResNeXSt, SENet, Shake-Shake,…

[CVPR2023] Implementation of ''Omni Aggregation Networks for Lightweight Image Super-Resolution".

Pytorch implementation of our paper accepted by ECCV 2022 -- ARM: Any-Time Super-Resolution Method (https://arxiv.org/abs/2203.10812)

N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution (CVPR2023 Accepted)

Learning Generative Structure Prior for Blind Text Image Super-resolution [CVPR 2023]

Real-CE: A Benchmark for Chinese-English Scene Text Image Super-resolution (ICCV2023)

PyTorch code for our paper "Image Super-Resolution with Non-Local Sparse Attention" (CVPR2021).

Implementation of "Attention Is Off By One" by Evan Miller

[CVPR 2022] Learnable Lookup Table for Neural Network Quantization