Sekunde

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

ControlNet

Let us control diffusion models!

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

stable-dreamfusion

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

point-e

Point cloud diffusion for 3D model synthesis

threestudio

A unified framework for 3D content generation.

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

GET3D

Text2Video-Zero

[ICCV 2023 Oral] Text-to-Image Diffusion Models are Zero-Shot Video Generators

text2mesh

3D mesh stylization driven by a text input in PyTorch

LION

Latent Point Diffusion Models for 3D Shape Generation

3detr

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

point-transformer

This is an unofficial implementation of the Point Transformer paper.

encord-active

The toolkit to test, validate, and evaluate your models and surface, curate, and prioritize the most valuable data for labeling.

SDFusion

panoptic-lifting

[CVPR23 Highlight] Implementation for Panoptic Lifting

habitat-matterport-3dresearch

NeRF-Det

[ICCV 2023] Code for NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection

Diffusion-SDF

Official code repository for the paper: “Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions”

PVD

ROCA

Official code for ROCA: Robust CAD Model Retrieval and Alignment from a Single Image (CVPR 2022)

Diffusion-SDF

[CVPR 2023] Diffusion-SDF: Text-to-Shape via Voxelized Diffusion

LanguageGroundedSemseg

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

RoITr

Rotation-Invariant Transformer for Point Cloud Matching

NSDP

The official implementation for NeurIPS 2022 Spotlight Neural Shape Deformation Priors

PatchComplete

This is the official code for "Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categories"

D3Net

[ECCV2022] D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding

PCR-CG

[ECCV 2022]PCR-CG: Point Cloud Registration via Color and Geometry

4DContrast

4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding, ECCV 2022

Scan2CADRasterizer

A custom rasterizer for Scan2CAD labels over ScanNet images. Created for our ROCA project (CVPR 2022).