[CVPR 2024] Official implementation of "Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction"

🎉 [CVPR 2024] Pytorch implementation of 'Har Far Can We Compress Instant-NGP Based NeRF?'

🏠 [ECCV 2024] Pytorch implementation of 'HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression'

A differentiable point-based rendering framework.

TriplaneGaussian: A new hybrid representation for single-view 3D reconstruction.

NeRF-SR: High-Quality Neural Radiance Fields using Supersampling

This is the official PyTorch implementation of our paper "Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functions" (CVPR 2023).

Code Release for AAAI 2024, "Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling"

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

The official repo for [NeurIPS'23] "SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model"

PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation

[ICCV 2023] Tracking Anything with Decoupled Video Segmentation

The official implementation of SAGA (Segment Any 3D GAussians)

[ECCV'2024] Gaussian Grouping for open-world Anything reconstruction, segmentation and editing.

The implementation of SUNDAE: Spectrally Pruned Gaussian Fields with Neural Compensation

Code for "Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering"

Official implementation of "Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting"

PointHR: Exploring High-Resolution Architectures for 3D Point Cloud Segmentation

This is the official implementation of "Clustering based Point Cloud Representation Learning for 3D Analysis" (Accepted at ICCV 2023).

[IJCV 2024] P3Former: Position-Guided Point Cloud Panoptic Segmentation Transformer

PlenOctrees construction + rendering PyTorch CUDA extension

PlenOctree Extraction algorithm

PlenOctrees: NeRF-SH Training & Conversion

Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians

PyTorch package for the discrete VAE used for DALL·E.