SJTU-DeepVisionLab

PosFormer. [ECCV2024] PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer

LaGa. Tackling View-Dependent Semantics in 3D Language Gaussian Splatting (ICML 2025)

FLoRA. Python

HyperCLIP. [CVPR 2025] Understanding Fine-tuning CLIP for Open-vocabulary Semantic Segmentation in Hyperbolic Space

WorldAct. Official implementation of WorldAct

FreeReal. [ECCV2024] Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors

SAM-COBOT. [CVPR2024] Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model

SBM. [CVPR2025] Star with Bilinear Mapping

H-CLIP. [CVPR2025] Parameter-efficient Fine-tuning in Hyperspherical Space for Open-vocabulary Semantic Segmentation

HyperCLIP-Plus-Plus. Official code for the journal extension of HyperCLIP (CVPR 2025).

Forplane. Python

SAM-PARSER. [AAAI2024] SAM-PARSER: Fine-tuning SAM Efficiently by Parameter Space Reconstruction

EADP. [ECCV2026] Combating Textual Noise and Redundancy: Entropy-Aware Dense Visual Token Pruning

Liver_Texture_Generation. Jupyter Notebook

EndoGSLAM. Python

DMformer. Python

SegmentAnythingin3D. Python

Human-Pose-Estimation. Python

ViTree.

PLCP. MATLAB

ContrastMask. Python

CCD. Python

SIGA. Python

CP2. Python

DSC. Python