Open-Sora: Democratizing Efficient Video Production for All

A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.

OpenMMLab's next-generation platform for general 3D object detection.

SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

[ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

gradslam is an open source differentiable dense SLAM library for PyTorch

[ICCV 2023] Tracking Anything with Decoupled Video Segmentation

Point-NeRF: Point-based Neural Radiance Fields

Pure PyTorch Implementation of NVIDIA paper on Instant Training of Neural Graphics primitives: https://nvlabs.github.io/instant-ngp/

[ICCV 2023] SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis

[CVPR2023] LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion

DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DOF Relocalization

[ECCV 2024 - Oral] Analytic-Splatting Anti-Aliased 3D Gaussian Splatting via Analytic Integration