Skip to content

@CVMI-Lab CVMI Lab

Change the repository type filter

All

    Repositories list

    39 repositories

    • ASSIST-3D

      Public
      [AAAI 2026] Code for ASSIST-3D: Adapted Scene Synthesis for Class-Agnostic 3D Instance Segmentation
      Python
      •0•4•0•0•Updated Dec 11, 2025Dec 11, 2025

    • L3DE

      Public
      (ICCV 2025) How Far are AI-generated Videos from Simulating the 3D Visual World: A Learned 3D Evaluation Approach
      video-generationvideo-evaluation
      Python
      •
      Apache License 2.0
      •0•4•1•0•Updated Nov 10, 2025Nov 10, 2025

    • VFMTok

      Public
      (NeurIPS 2025) Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation
      Python
      •
      Apache License 2.0
      •0•64•2•0•Updated Oct 14, 2025Oct 14, 2025

    • VFMTok-RAR

      Public
      (NeurIPS 2025, SOTA) Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation
      Python
      •
      Apache License 2.0
      •0•3•0•0•Updated Oct 14, 2025Oct 14, 2025

    • Hita

      Public
      (ICCV 2025) Holistic Tokenizer for Autoregressive Image Generation
      Python
      •
      MIT License
      •1•30•0•0•Updated Oct 9, 2025Oct 9, 2025

    • Depth_Survey

      Public
      Python
      •0•6•0•0•Updated Aug 8, 2025Aug 8, 2025

    • SC-GS

      Public
      [CVPR 2024] Code for SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes
      dynamic-nerfgaussian-splattingmotion-editing
      Python
      •
      MIT License
      •39•631•32•0•Updated Jun 27, 2025Jun 27, 2025

    • semanticist

      Public
      (ICCV 2025) "Principal Components" Enable A New Language of Images
      Jupyter Notebook
      •
      MIT License
      •6•2•0•0•Updated Mar 26, 2025Mar 26, 2025

    • Deformable-Radial-Kernel-Splatting

      Public
      Python
      •0•5•0•0•Updated Mar 13, 2025Mar 13, 2025

    • SlotMIM

      Public
      (CVPR 2025) A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning
      Python
      •
      Apache License 2.0
      •1•23•1•0•Updated Mar 11, 2025Mar 11, 2025

    • SlotCon

      Public
      (NeurIPS 2022) Self-Supervised Visual Representation Learning with Semantic Grouping
      object-discoveryself-supervised-learningpre-trainingcontrastive-learningneurips-2022slotcon
      Python
      •
      Apache License 2.0
      •10•97•2•0•Updated Mar 10, 2025Mar 10, 2025

    • UniTok

      Public
      A Unified Tokenizer for Visual Generation and Understanding
      Python
      •
      MIT License
      •11•1•0•0•Updated Feb 28, 2025Feb 28, 2025

    • TEXGen

      Public
      [SIGGRAPH Asia 2024, Best Paper Honorable Mention] This is the official implementation of our SIGGRAPH Asia journal artical: TEXGen: a Generative Diffusion Mode…
      Python
      •11•322•13•0•Updated Dec 18, 2024Dec 18, 2024

    • SyncOOD

      Public
      (ECCV 2024) Can OOD Object Detectors Learn from Foundation Models?
      deep-learningobject-detectionsynthetic-dataood-detectioneccv2024open-world-data
      Python
      •
      Apache License 2.0
      •1•25•3•0•Updated Dec 7, 2024Dec 7, 2024

    • clip-beyond-tail

      Public
      (NeurIPS 2024) What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights
      neurips-2024
      Jupyter Notebook
      •
      MIT License
      •1•28•0•0•Updated Oct 28, 2024Oct 28, 2024

    • Total-Decom

      Public
      0•62•1•0•Updated Oct 11, 2024Oct 11, 2024

    • ST3D

      Public
      (CVPR 2021 & T-PAMI 2022) ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection & ST3D++: Denoised Self-training for Unsupervised Domai…
      Python
      •
      Apache License 2.0
      •48•313•7•0•Updated Jul 14, 2024Jul 14, 2024

    • PLA

      Public
      (CVPR 2023) PLA: Language-Driven Open-Vocabulary 3D Scene Understanding & (CVPR2024) RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D S…
      deep-learningopen-world3d-scene-understandingopen-vocabularycvpr2023
      Python
      •
      Apache License 2.0
      •12•298•12•0•Updated Jun 28, 2024Jun 28, 2024

    • CoDet

      Public
      (NeurIPS2023) CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection
      object-detectionopen-vocabularyopen-vocabulary-detection
      Python
      •6•123•4•0•Updated Apr 26, 2024Apr 26, 2024

    • Groma

      Public
      Copy of "Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models"
      Python
      •
      Apache License 2.0
      •45•1•0•0•Updated Apr 22, 2024Apr 22, 2024

    • Speech2Lip

      Public
      [ICCV2023] Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video
      Python
      •11•76•7•0•Updated Mar 28, 2024Mar 28, 2024

    • VideoDemoireing

      Public
      (CVPR 2022) Video Demoireing with Relation-Based Temporal Consistency
      Python
      •
      Apache License 2.0
      •14•93•5•0•Updated Feb 9, 2024Feb 9, 2024

    • SimGCD

      Public
      (ICCV 2023) Parametric Classification for Generalized Category Discovery: A Baseline Study
      open-world-classificationopen-world-semi-supervised-learningnovel-category-discovery
      Python
      •
      MIT License
      •17•126•1•0•Updated Dec 30, 2023Dec 30, 2023

    • Classifier-Score-Distillation

      Public
      (ICLR2024) This is the official PyTorch implementation of ICLR2024 paper: Text-to-3D with Classifier Score Distillation
      Python
      •5•136•1•0•Updated Dec 26, 2023Dec 26, 2023

    • PAConv

      Public
      (CVPR 2021) PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds
      Python
      •
      Apache License 2.0
      •43•305•14•0•Updated Dec 25, 2023Dec 25, 2023

    • Hybrid-Occ-SDF

      Public
      This is the officially implementation of ICCV 2023 paper " Learning A Room with the Occ-SDF Hybrid: Signed Distance Function Mingled with Occupancy Aids Scene R…
      Python
      •
      MIT License
      •0•11•0•0•Updated Dec 7, 2023Dec 7, 2023

    • IST-Net

      Public
      (ICCV2023) IST-Net: Prior-free Category-level Pose Estimation with Implicit Space Transformation
      Python
      •
      MIT License
      •3•119•6•0•Updated Dec 7, 2023Dec 7, 2023

    • Point-UV-Diffusion

      Public
      (ICCV2023) This is the official PyTorch implementation of ICCV2023 paper: Texture Generation on 3D Meshes with Point-UV Diffusion
      C++
      •12•216•7•0•Updated Dec 6, 2023Dec 6, 2023

    • HybridNeuralRendering

      Public
      (CVPR 2023) Hybrid Neural Rendering for Large-Scale Scenes with Motion Blur
      Python
      •
      Apache License 2.0
      •6•67•0•1•Updated Sep 19, 2023Sep 19, 2023

    • UHDM

      Public
      (ECCV2022) This is the official PyTorch implementation of ECCV2022 paper: Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing
      Python
      •
      Apache License 2.0
      •36•268•15•0•Updated Aug 21, 2023Aug 21, 2023