VISION-SJTU

3dSwap

[CVPR 2023] 3D-Aware Face Swapping

CM3DDet

[WACV2021] Cross-Modality 3D Object Detection

IoUattack

[CVPR2021] IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking

Lightning-NeRF

[ICRA 2024] Lightning NeRF: Efficient Hybrid Scene Representation for Autonomous Driving

PillarNet

[ECCV 2022] PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection

PillarNet-LTS

PointAugmenting

[CVPR2021] PointAugmenting: Cross-Modal Augmentation for 3D Object Detection

RECCE

[CVPR2022] End-to-End Reconstruction-Classification Learning for Face Forgery Detection

SparseOcc

Official implementation for 'SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction' (CVPR 2024)

USOT

[ICCV2021] Learning to Track Objects from Unlabeled Videos

VISION-SJTU/PillarNet-LTS

VISION-SJTU/RECCE

[CVPR2022] End-to-End Reconstruction-Classification Learning for Face Forgery Detection

VISION-SJTU/PointAugmenting

[CVPR2021] PointAugmenting: Cross-Modal Augmentation for 3D Object Detection

VISION-SJTU/Lightning-NeRF

[ICRA 2024] Lightning NeRF: Efficient Hybrid Scene Representation for Autonomous Driving

VISION-SJTU/3dSwap

[CVPR 2023] 3D-Aware Face Swapping

VISION-SJTU/USOT

[ICCV2021] Learning to Track Objects from Unlabeled Videos

VISION-SJTU/IoUattack

[CVPR2021] IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking

VISION-SJTU/SparseOcc

Official implementation for 'SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction' (CVPR 2024)

VISION-SJTU/PillarNet

[ECCV 2022] PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection

VISION-SJTU/QuadMamba

VISION-SJTU/CM3DDet

[WACV2021] Cross-Modality 3D Object Detection

VISION-SJTU/DiffusionTrack

[CVPR2024] DiffusionTrack: Point set Diffussion Model for Visual Object Tracking

VISION-SJTU/VidToMe

[CVPR 2024] VidToMe: Video Token Merging for Zero-Shot Video Editing

VISION-SJTU/RTAA

[ECCV2020] Robust Tracking against Adversarial Attacks

VISION-SJTU/UniDefense

[IJCV 2024] Towards Unified Defense for Face Forgery and Spoofing Attacks via Dual Space Reconstruction Learning

VISION-SJTU/SPOT

[TIP2024] Sparsely-Supervised Object Tracking

VISION-SJTU/USOL

[WACV2022] Unsupervised Sounding Object Localization with Bottom-Up and Top-Down Attention

VISION-SJTU/SuperSBT

[TPAMI 2024] SuperSBT. Correlation-Embedded Transformer Tracking: A Single-Branch Framework

VISION-SJTU/3DAiALane

[SPL 2024] 3D Lane Detection With Attention in Attention

VISION-SJTU/id2reflectance

ID2Reflectance Paper website