Lists (21)
3R
Agent
Compression
condition INR
funny
gaussian
job
large gaussian
little project
LLM 3D
MLP
nerf
other deep-learning
paper
reading works
some interesting worksSR
tools
viewer
world model
yolo/deepsort
生成式Generation
Stars
high-performance inference and serving library for interactive autoregressive video and world models
NVIDIA OmniDreams is a world model that generates photorealistic video for autonomous-driving simulation in real time.
Wan: Open and Advanced Large-Scale Video Generative Models
Our inference and training framework to run on the Cosmos Models
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini C…
Post-training scripts and samples for NVIDIA Cosmos ecosystem
Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control inputs.
A curated list of awesome 3D generation resources, papers, and tools for AI-powered 3D content creation.
A modular graph-based Retrieval-Augmented Generation (RAG) system
拼好RAG：手搓并融合了GraphRAG、LightRAG、Neo4j-llm-graph-builder进行知识图谱构建以及搜索；整合DeepSearch技术实现私域RAG的推理；自制针对GraphRAG的评估框架| Integrate GraphRAG, LightRAG, and Neo4j-llm-graph-builder for knowledge graph construct…
[ICCV 2025] WIPES: Wavelet-based Visual Primitives
Awesome-LLM-3D: a curated list of Multi-modal Large Language Model in 3D world Resources
Official repo for paper "Sparse Representation and Construction for High-Resolution 3D Shapes Modeling".
Native and Compact Structured Latents for 3D Generation
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
A Collection of Papers and Codes for CVPR2026/CVPR2025/ICCV2025/CVPR2024/ECCV2024 AIGC
An implementation for "S2D: Sparse to Dense Lifting for 3D Reconstruction with Minimal Inputs"
One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more
An efficient and research-friendly Gaussian Splatting framework described in the CVPR'26 paper "Faster-GS: Analyzing and Improving Gaussian Splatting Optimization"
[ICLR 2026] π^3: Permutation-Equivariant Visual Geometry Learning
[CVPR 2026] iLRM: An Iterative Large 3D Reconstruction Model
Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels
本项目是一个基于3DGS（3D Gaussian Splatting）技术的移动端三维重建系统，允许用户通过手机拍摄视频来自动生成高质量的三维模型。该系统不仅支持多种三维文件格式导出，还提供了在线三维场景漫游功能