Megvii (China)

Recent papers from Megvii (China)

1. Learning Physics-Informed Noise Models from Dark Frames for Low-Light Raw Image DenoisingIEEE Transactions on Pattern Analysis and Machine Intelligence · 2026
2. Advancing 3D Object Detection with Depth-aware Spatial Knowledge DistillationIEEE Transactions on Pattern Analysis and Machine Intelligence · 2025
3. Panacea+: Panoramic and Controllable Video Generation for Autonomous DrivingIEEE Transactions on Circuits and Systems for Video Technology · 2025
4. BFA: Best-Feature-Aware Fusion for Multi-View Fine-Grained ManipulationIEEE Robotics and Automation Letters · 2025
5. Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Models2025
6. Bootstrap Masked Visual Modeling via Hard Patch MiningIEEE Transactions on Pattern Analysis and Machine Intelligence · 2025
7. Localization-Guided Track: A Deep Association Multiobject Tracking Framework Based on Localization Confidence of Camera DetectionsIEEE Sensors Journal · 2024
8. Self-Supervised Visual Preference Alignment2024
9. QTrack: Embracing Quality Clues for Robust 3D Multi-Object Tracking2024
10. GroupLane: End-to-End 3D Lane Detection With Channel-Wise GroupingIEEE Robotics and Automation Letters · 2024
11. ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning2024
12. Panacea: Panoramic and Controllable Video Generation for Autonomous Driving2024
13. Motion-Adaptive Separable Collaborative Filters for Blind Motion Deblurring2024
14. FlowDiffuser: Advancing Optical Flow Estimation with Diffusion Models2024
15. Style Variable and Irrelevant Learning for Generalizable Person Re-identificationACM Transactions on Multimedia Computing Communications and Applications · 2024
16. Exploring Recurrent Long-Term Temporal Fusion for Multi-View 3D PerceptionIEEE Robotics and Automation Letters · 2024
17. PillarNeSt: Embracing Backbone Scaling and Pretraining for Pillar-Based 3D Object DetectionIEEE Transactions on Intelligent Vehicles · 2024
18. Far3D: Expanding the Horizon for Surround-View 3D Object Detection2024
19. Compound Text-Guided Prompt Tuning via Image-Adaptive Cues2024
20. GigaHumanDet: Exploring Full-Body Detection on Gigapixel-Level Images2024