ICCV 2023 | 论文及代码合集

近日，世界三大顶级视觉会议之一ICCV公开了最新录用结果。

根据文件里给出的ID，总共有2160篇论文入选。

我们整理了部分录用论文及其代码合集（持续更新…）

[1] Rethinking Mobile Block for Efficient Attention-based Models

[Code]GitHub - zhangzjn/EMO: [ICCV 2023] Official PyTorch implementation of "Rethinking Mobile Block for Efficient Attention-based Models"

[Area]backbone

[2] IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesis

[Code]https://zju3dv.github.io/intrinsic_nerf/

[Area]NeRF

[3] PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment

[Code]PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment

[Area]Diffusion Models

[4] FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model

[Code]GitHub - vvictoryuki/FreeDoM: [ICCV 2023] Official PyTorch implementation for the paper "FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model"

[Area]Diffusion Models

[5] Femtodet: an object detection baseline for energy versus performance tradeoffs

[Code]https://github.com/yh-pengtu/FemtoDet

[Area]目标检测

[6] Segment Anything

[Code]GitHub - facebookresearch/segment-anything: The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

[Area]语义分割

[7] MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation

[Code]GitHub - shjo-april/MARS: [ICCV2023] MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation

[Area]语义分割

[8] DVIS: Decoupled Video Instance Segmentation Framework

[Code]GitHub - zhang-tao-whu/DVIS: DVIS: Decoupled Video Instance Segmentation Framework

[Area]视频实例分割

[9] Robo3D: Towards Robust and Reliable 3D Perception against Corruptions

[Code]GitHub - ldkong1205/Robo3D: [ICCV'23] Robo3D: Towards Robust and Reliable 3D Perception against Corruptions

[Area]3D点云

[10] PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images

[Code]GitHub - megvii-research/PETR: [ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection & [ICCV2023] PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images

[Area]3D目标检测

[11] DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection

[Code]GitHub - AIR-DISCOVER/DQS3D: DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection

[Area]3D目标检测

[12] SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection

[Code]GitHub - yichen928/SparseFusion: [ICCV 2023] SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection

[Area]3D目标检测

[13] StreamPETR: Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection

[Code]GitHub - exiawsh/StreamPETR: [ICCV 2023] StreamPETR: Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection

[Area]3D目标检测

[14] Cross Modal Transformer: Towards Fast and Robust 3D Object Detection

[Code]https://github.com/junjie18/CMT

[Area]3D目标检测

[15] Rethinking Range View Representation for LiDAR Segmentation

[Code]None

[Area]3D语义分割

[16] Unmasked Teacher: Towards Training-Efficient Video Foundation Models

[Code]GitHub - OpenGVLab/unmasked_teacher: [ICCV2023] Unmasked Teacher: Towards Training-Efficient Video Foundation Models

[Area]视频理解

[17] FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model

[Code]GitHub - vvictoryuki/FreeDoM: [ICCV 2023] Official PyTorch implementation for the paper "FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model"

[Area]图像生成

[18] Simulating Fluids in Real-World Still Images

[Code]https://github.com/simon3dv/SLR-SFS

[Area]视频生成

[19] FateZero: Fusing Attentions for Zero-shot Text-based Video Editing

[Code]Fate/Zero

[Area]视频编辑

[20] Implicit Neural Representation for Cooperative Low-light Image Enhancement

[Code]https://github.com/Ysz2022/NeRCo

[Area]低光照图像增强