Xi Liu

TrackCraft3r. Official code implementation for TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking

HAD. Python

UnSAMv2. Code release for "UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity"

LangHOPS-release. Python

OmniSVG. [NeurIPS 2025] OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from simple icons to intricate anime characters.

Bezier_splatting. Python

UniLIP. [ICLR 2026 🔥 ] Official implementation of "UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editing"

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

layered_vectorization. JavaScript

jonbarron.github.io. HTML

cube. Roblox Foundation Model for 3D Intelligence

SVD_Xtend. Stable Video Diffusion Training Code and Extensions.

MiraGe. [ICML 2025] Official implementation of "MiraGe: Editable 2D Images using Gaussian Splatting"

3DGS-Enhancer.

4d-gaussian-splatting. [ICLR 2024] Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting

Academic-project-page-template. A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

StableSR. [IJCV2024] Exploiting Diffusion Prior for Real-World Image Super-Resolution

MGLD-VSR. Code for ECCV 2024 Paper "Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution"

AdaLoRA. AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning (ICLR 2023).

gaussian-splatting. Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

neurecon. Multi-view 3D reconstruction using neural rendering. Unofficial implementation of UNISURF, VolSDF, NeuS and more.

stable-dreamfusion. Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

banmo. BANMo Building Animatable 3D Neural Models from Many Casual Videos

real-world-haskell-cn. 《Real World Haskell》中文翻译项目

mmdetection3d. OpenMMLab's next-generation platform for general 3D object detection.

mmocr. OpenMMLab Text Detection, Recognition and Understanding Toolbox

mmdetection3d. OpenMMLab's next-generation platform for general 3D object detection.