Hanxue Zhang

Warp-as-History. Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video

Zoo3D. [CVPR2026] Zoo3D: Zero-Shot 3D Object Detection at Scene Level

PonderV2. [T-PAMI 2025] PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm

SpatialLM. [NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling

SGCDet. [ICCV 2025] Boosting Multi-View Indoor 3D Object Detection via Adaptive 3D Volume Construction

cursor-ai-downloads. All Cursor AI's official download links for both the latest and older versions, making it easy for you to update, downgrade, and choose any version. 🚀

Pi3. [ICLR 2026] π^3: Permutation-Equivariant Visual Geometry Learning

dust3r. DUSt3R: Geometric 3D Vision Made Easy

Cosmos-Drive-Dreams. Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models

LongVie. Python

DetAny3D. [ICCV 2025] Detect Anything 3D in the Wild

vggt. [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

Nexus. [ICCV 2025] Nexus: Decoupled Diffusion Sparks Adaptive Scene Generation

ovmono3d. [3DV 2026] Open Vocabulary Monocular 3D Object Detection

UMGen. Code for CVPR2025 paper: Generating Multimodal Driving Scenes via Next-Scene Prediction

omni3d. Code release for "Omni3D A Large Benchmark and Model for 3D Object Detection in the Wild"

MTGS. MTGS: Multi-Traversal Gaussian Splatting

DetAny3D. A demo page for DetAny3D

UniDepth. Universal Monocular Metric Depth Estimation

SUNRGBDtoolbox_python. Python

SJTUThesis. 上海交通大学 LaTeX 论文模板 | Shanghai Jiao Tong University LaTeX Thesis Template

Oneshot_landmark_detection. Official code for "Oneshot Medical Landmark Detection' (MICCAI 2021 early accepted)

Awesome-3D-Object-Detection. Papers, code and datasets about deep learning for 3D Object Detection.

awesome-yolo-object-detection. 🚀🚀🚀 A collection of some awesome public YOLO object detection series projects and the related object detection datasets.

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

LucidDreamer. Official code for the paper "LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes".

LucidDreamer. Official implementation of "LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching"

AnimateDiff. Official implementation of AnimateDiff.

TokenFlow. Official Pytorch Implementation for "TokenFlow: Consistent Diffusion Features for Consistent Video Editing" presenting "TokenFlow" (ICLR 2024)

make-a-video-pytorch. Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch

Awesome-Video-Diffusion-Models. [CSUR] A Survey on Video Diffusion Models

cudaBERT. A Fast Muti-processing BERT-Inference System

cuda_spatial_deform. A fast tool to do image augmentation on GPU(especially elastic_deform), can be helpful to research on Medical Image.

ViDAR. [CVPR 2024 Highlight] Visual Point Cloud Forecasting

DriveLM. [ECCV 2024 Oral] DriveLM: Driving with Graph Visual Question Answering

neuralsim. neuralsim: 3D surface reconstruction and simulation based on 3D neural rendering.

maskalign. [CVPR 2023] Official repository for paper "Stare at What You See: Masked Image Modeling without Reconstruction"

OpenLane. [ECCV 2022 Oral] OpenLane: Large-scale Realistic 3D Lane Dataset

PersFormer_3DLane. [ECCV 2022 Oral] Perspective Transformer on 3D Lane Detection

PPGeo. [ICLR 2023] Pytorch implementation of PPGeo, a fully self-supervised driving policy pre-training framework to learn from unlabeled driving videos.

ST-P3. [ECCV 2022] ST-P3, an end-to-end vision-based autonomous driving framework via spatial-temporal feature learning.

Openpilot-Deepdive. Our insights of Openpilot, a deepdive project on it

ThinkTwice. [CVPR 2023] Pytorch implementation of ThinkTwice, a SOTA Decoder for End-to-end Autonomous Driving under BEV.

HDGT. [IEEE T-PAMI 2023] Unified heterogeneous transformer-based graph neural network for motion prediction

TopoNet. [Accepted at SCIENCE CHINA Information Sciences 2026] Graph-based Topology Reasoning for Driving Scenes

DriveAGI. [CVPR 2024 Highlight] GenAD: Generalized Predictive Model for Autonomous Driving

DriveAdapter. [ICCV 2023 Oral] A New Paradigm for End-to-end Autonomous Driving to Alleviate Causal Confusion

TCP. [NeurIPS 2022] Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline.

OpenLane-V2. [NeurIPS 2023 Track Datasets and Benchmarks] OpenLane-V2: The First Perception and Reasoning Benchmark for Road Driving

OccNet. [ICCV 2023] OccNet: Scene as Occupancy

Birds-eye-view-Perception. [IEEE T-PAMI 2023] Awesome BEV perception research and cookbook for all level audience in autonomous diriving

End-to-end-Autonomous-Driving. [IEEE T-PAMI 2024] All you need for End-to-end Autonomous Driving

UniAD. [CVPR 2023 Best Paper Award] Planning-oriented Autonomous Driving

OpenScene. 3D Occupancy Prediction Benchmark in Autonomous Driving

pygmtools. A Python Graph Matching Toolkit.

BEVFusion. Offical PyTorch implementation of "BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework"

MSF-ADV. MSF-ADV is a novel physical-world adversarial attack method, which can fool the Multi Sensor Fusion (MSF) based autonomous driving (AD) perception in the victim autonomous vehicle (AV) to fail in detecting a front obstacle and thus crash into it. This work is accepted by IEEE S&P 2021.