Official implementation of NerualSVG

Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…

[NeurIPS'24] Large Spatial Model: End-to-end Unposed Images to Semantic 3D

[2024-NeurIPS] TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control

[NeurIPS 2024 Spotlight] Tetrahedron Splatting for 3D Generation

[NIPS'24] Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection

[NeurIPS 2024] OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding

😎 Awesome lists of papers and codes about open-vocabulary perception, including both 3D and 2D

Implementation for ECCV 2022 paper Language-Grounded Indoor 3D Semantic Segmentation in the Wild

Uncommon Objects in 3D dataset

Open-Sora: Democratizing Efficient Video Production for All

SplatFormer: Point Transformer for Robust 3D Gaussian Splatting

DreamUV - 3D viewport UV editing tools for Blender

[AAAI' 25] Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior

[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

Code for "EnvGS: Modeling View-Dependent Appearance with Environment Gaussian", arXiv 2024. Including a fully differentiable 2D Gaussian ray tracer built on 2DGS and OptiX, supporting multiple-boun…

An official implementation of RoDyGS: Robust Dynamic Gaussian Splatting for Casual Videos

Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation

Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".

[AAAI2025] UniDet3D: Multi-dataset Indoor 3D Object Detection

ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images (NeurIPS2024)

Official code for NeurIPS2023 paper: CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

Code & Models for 3DETR - an End-to-end transformer model for 3D object detection

[WACV 2024] Amodal Intra-class Instance Segmentation: Synthetic Dataset and Benchmark

[NeurIPS 2024] L4GM: Large 4D Gaussian Reconstruction Model

SAMPart3D: Segment Any Part in 3D Objects