Stars
[CVPR 2026] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
Official repository of Text-Image Conditioned 3D Generation (TIGON, CVPR 2026)
A comprehensive list of papers for the definition of World Models and using World Models for General Video Generation, Embodied AI, and Autonomous Driving, including papers, codes, and related webs…
Native and Compact Structured Latents for 3D Generation
WorldGrow: Generating Infinite 3D World [AAAI 2026 Oral]
UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generation
Segment Anything in 3D with NeRFs (NeurIPS 2023 & IJCV 2025)
The official implementation of Segment Any 3D GAussians (AAAI-25)
[AAAI 2026] Few-step Flow for 3D Generation via Marginal-Data Transport Distillation
The repository of "Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds"
Tackling View-Dependent Semantics in 3D Language Gaussian Splatting (ICML 2025)
[Arxiv'25] MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization
[CVPR'24] Group Anything with Radiance Fields
[Lumina具身智能社区] 具身智能技术指南 Embodied-AI-Guide
GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting (SIGGRAPH Asia 2024, TOG)
Official implementation of Continuous 3D Perception Model with Persistent State
Awesome-LLM-3D: a curated list of Multi-modal Large Language Model in 3D world Resources
[NeurIPS 2024] OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding
this is an codewise illustration of the simple_knn algorithm used in many 3d gaussian splatting projects.
GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Quality
A 3D Gaussian Splatting framework with various derived algorithms and an interactive web viewer
[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
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.
[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
[CVPR 2024] GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models