Fudan Zhang Vision Group

[NeurIPS 2021 Spotlight] & [IJCV 2024] SOFT: Softmax-free Transformer with Linear Complexity

fudan-zvg

[CVPR 2021] Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

fudan-zvg

[CVPR 2021] Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection

fudan-zvg

[NeurIPS 2022] DeepInteraction: 3D Object Detection via Modality Interaction

fudan-zvg

[TPAMI 2022 & CVPR 2020 Oral] Dynamic Graph Message Passing Networks

fudan-zvg

[ECCV 2022] Learning Ego 3D Representation as Ray Tracing

fudan-zvg

[ECCV 2022] Accelerating Score-based Generative Models with Preconditioned Diffusion Sampling

fudan-zvg

[AAAI 2023] PolarFormer: Multi-camera 3D Object Detection with Polar Transformers

fudan-zvg

fudan-zvg

Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).

fudan-zvg