(NeurIPS 2024) What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

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 Representation"

LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models (ECCV 2024)

(ICCV2023) IST-Net: Prior-free Category-level Pose Estimation with Implicit Space Transformation

(CVPR 2023) Hybrid Neural Rendering for Large-Scale Scenes with Motion Blur

We extend Segment Anything to 3D perception by combining it with VoxelNeXt.

This is the project for DreamStone: TPAMI & ISS: ICLR 2023 spotlight

(ECCV2022) This is the official PyTorch implementation of ECCV2022 paper: Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing

(ICCV 2021 Oral) Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation.

(CVPR 2021) PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds

(CVPR 2021 & T-PAMI 2022) ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection & ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection

A Unified Framework for Surface Reconstruction

(CVPR 2023) PLA: Language-Driven Open-Vocabulary 3D Scene Understanding & (CVPR2024) RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding

(NeurlPS 2022) Spatial Pruned Sparse Convolution for Efficient 3D Object Detection

Is synthetic data from generative models ready for image recognition?

(NeurlPS 2022) Towards Efficient 3D Object Detection with Knowledge Distillation

(NeurIPS 2022) Self-Supervised Visual Representation Learning with Semantic Grouping

[NeurIPS 2022] Official implementation of the paper "Rethinking Resolution in the Context of Efficient Video Recognition".

R-PointHop: A Green, Accurate and Unsupervised Point Cloud Registration Method

(ECCV 2022) DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation

Towards-Implicit-Text-Guided-3D-Shape-Generation. CVPR 2022

CVPR 2020

(CVPR 2022) Video Demoireing with Relation-Based Temporal Consistency

[ICML 2021, Long Talk] Delving into Deep Imbalanced Regression

https://arxiv.org/abs/2104.02246 One Thing One Click (CVPR 2021) https://arxiv.org/abs/2303.14727 One Thing One Click++ (Arxiv)

CVPR 2021 Oral https://arxiv.org/abs/2104.02243

A general video understanding codebase from SenseTime X-Lab

TMI 2018. H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes