Point Cloud Generation
44 papers with code • 4 benchmarks • 2 datasets
Benchmarks
These leaderboards are used to track progress in Point Cloud Generation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
ShapeNet
JetClass
Latest papers
Taming Transformers for Realistic Lidar Point Cloud Generation
Diffusion Models (DMs) have achieved State-Of-The-Art (SOTA) results in the Lidar point cloud generation task, benefiting from their stable training and iterative refinement during sampling.
LidarDM: Generative LiDAR Simulation in a Generated World
We present LidarDM, a novel LiDAR generative model capable of producing realistic, layout-aware, physically plausible, and temporally coherent LiDAR videos.
Point Cloud Part Editing: Segmentation, Generation, Assembly, and Selection
kaiyizhang/SGAS
•
•
Based on this process, we introduce SGAS, a model for part editing that employs two strategies: feature disentanglement and constraint.
LiDAR Data Synthesis with Denoising Diffusion Probabilistic Models
kazuto1011/r2dm
•
•
In this work, we present R2DM, a novel generative model for LiDAR data that can generate diverse and high-fidelity 3D scene point clouds based on the image representation of range and reflectance intensity.
Echoes Beyond Points: Unleashing the Power of Raw Radar Data in Multi-modality Fusion
tusen-ai/echofusion
•
•
NeurIPS 2023
Radar is ubiquitous in autonomous driving systems due to its low cost and good adaptability to bad weather.
Patch-Wise Point Cloud Generation: A Divide-and-Conquer Approach
A generative model for high-fidelity point clouds is of great importance in synthesizing 3d environments for applications such as autonomous driving and robotics.
DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation
DiT-3D/DiT-3D
•
•
NeurIPS 2023
Recent Diffusion Transformers (e. g., DiT) have demonstrated their powerful effectiveness in generating high-quality 2D images.
Volume-DROID: A Real-Time Implementation of Volumetric Mapping with DROID-SLAM
peterstratton/volume-droid
•
•
Volume-DROID takes camera images (monocular or stereo) or frames from a video as input and combines DROID-SLAM, point cloud registration, an off-the-shelf semantic segmentation network, and Convolutional Bayesian Kernel Inference (ConvBKI) to generate a 3D semantic map of the environment and provide accurate localization for the robot.
NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields
We verify the effectiveness of our NeRF-LiDAR by training different 3D segmentation models on the generated LiDAR point clouds.
EPiC-GAN: Equivariant Point Cloud Generation for Particle Jets
With the vast data-collecting capabilities of current and future high-energy collider experiments, there is an increasing demand for computationally efficient simulations.
