Repositories list

• GeoAgent

  Public
  [CVPR26] Official code for GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristic

  Python

  •

  Other

  •6•66•0•0•Updated Mar 16, 2026Mar 16, 2026

• ImageCritic

  Public

  HVision-NKU/ImageCritic’s past year of commit activity
  Official implementation of ImageCritic (CVPR 2026)

  fluxcustomizationconsistency+ 2

  fluxcustomizationconsistencyimage-generationdiffusion-models

  Python

  •7•156•3•0•Updated Mar 7, 2026Mar 7, 2026

• ASID-Caption

  Public

  HVision-NKU/ASID-Caption’s past year of commit activity
  ASID-Caption: Attribute-Structured and Quality-Verified Audiovisual Instruction Dataset and Training Pipeline for Fine-Grained Video Understanding.

  Python

  •

  Apache License 2.0

  •2•47•1•0•Updated Mar 3, 2026Mar 3, 2026

• GlimpsePrune

  Public
  Official repository of the paper "A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models"

  inference-efficiencylvlmsmllms+ 2

  inference-efficiencylvlmsmllmsvisual-token-pruningtoken-compression

  Python

  •

  Apache License 2.0

  •1•92•4•0•Updated Feb 13, 2026Feb 13, 2026

• AR123

  Public

  HVision-NKU/AR123’s past year of commit activity
  Official Code for 'AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-View Prediction' (ICCV 2025)

  3d-generationnovel-view-synthesisimage-to-3d+ 1

  3d-generationnovel-view-synthesisimage-to-3d3d-aigc

  Python

  •

  BSD 3-Clause "New" or "Revised" License

  •1•63•1•0•Updated Nov 8, 2025Nov 8, 2025

• TAR3D

  Public

  HVision-NKU/TAR3D’s past year of commit activity
  Official Code for 'TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction' (ICCV 2025)

  3d-reconstruction3d-representation3d-generation+ 2

  3d-reconstruction3d-representation3d-generationimage-to-3dtext-to-3d

  Python

  •

  BSD 3-Clause "New" or "Revised" License

  •1•77•1•0•Updated Nov 8, 2025Nov 8, 2025

• Strip-R-CNN

  Public
  [AAAI 2026]"Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection"

  remote-sensingobject-detection

  remote-sensingobject-detection

  Python

  •

  Other

  •13•116•28•0•Updated Nov 7, 2025Nov 7, 2025

• OffSeg

  Public
  [ICCV 2025] Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment

  semantic-segmentationefficient-modelfeature-alignment+ 1

  semantic-segmentationefficient-modelfeature-alignmentoffset-learning

  Python

  •

  Other

  •0•54•1•0•Updated Oct 14, 2025Oct 14, 2025

• K-LoRA

  Public
  Official code for K-LoRA (CVPR 2025)

  Python

  •7•140•12•1•Updated Sep 27, 2025Sep 27, 2025

• DenseVLM

  Public

  HVision-NKU/DenseVLM’s past year of commit activity
  [ICCV 2025] Unbiased Region-Language Alignment for Open-Vocabulary Dense Prediction

  Python

  •1•52•2•0•Updated Sep 22, 2025Sep 22, 2025

• OneVAE

  Public
  Python

  •0•54•2•0•Updated Sep 21, 2025Sep 21, 2025

• DepthAnythingAC

  Public
  Official code for the paper: Depth Anything At Any Condition

  zero-shotdepth-estimationdepth-map+ 3

  zero-shotdepth-estimationdepth-mapdepth-anythingdepth-anything-v2robust-depth-estimation

  Python

  •20•327•1•3•Updated Aug 21, 2025Aug 21, 2025

• SRFormer

  Public
  Official code for "SRFormer: Permuted Self-Attention for Single Image Super-Resolution" (ICCV 2023) and SRFormerV2

  Python

  •

  Other

  •27•300•27•0•Updated Jul 13, 2025Jul 13, 2025

• ControlSR

  Public
  Python

  •

  Apache License 2.0

  •0•14•1•0•Updated Apr 19, 2025Apr 19, 2025

• MaskCLIPpp

  Public
  Official repository of the paper "High-Quality Mask Tuning Matters for Open-Vocabulary Segmentation"

  image-segmentationclipvision-language-model+ 1

  image-segmentationclipvision-language-modelopen-vocabulary-segmentation

  Python

  •

  Apache License 2.0

  •2•45•4•0•Updated Mar 25, 2025Mar 25, 2025

• AdaptCOD

  Public
  0•0•3•0•Updated Feb 21, 2025Feb 21, 2025

• CamoFormer

  Public
  Python

  •

  MIT License

  •18•122•11•0•Updated Feb 20, 2025Feb 20, 2025

• Conv2Former

  Public
  Python

  •

  Apache License 2.0

  •15•187•9•0•Updated Jan 2, 2025Jan 2, 2025

• MaskDiffusion

  Public
  Python

  •0•14•0•0•Updated Dec 7, 2024Dec 7, 2024

• StoryDiffusion

  Public
  Accepted as [NeurIPS 2024] Spotlight Presentation Paper

  Jupyter Notebook

  •

  Apache License 2.0

  •649•6.4k•117•3•Updated Sep 26, 2024Sep 26, 2024

• Cascade-CLIP

  Public
  Official implement of ICML2024 Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation

  Python

  •

  MIT License

  •3•58•1•0•Updated Aug 15, 2024Aug 15, 2024

• CoordAttention

  Public
  Python

  •

  MIT License

  •1•3•0•0•Updated Nov 21, 2022Nov 21, 2022

• VisionPermutator

  Public
  Python

  •

  MIT License

  •2•6•0•0•Updated Nov 21, 2022Nov 21, 2022