NeurIPS 2024 accepted papers on Point clouds
52 of the 4,560 papers accepted at NeurIPS 2024 (1.1%) are on Point clouds, compared with 1.3% at NeurIPS 2023. They fall into 4 topics.
See NeurIPS 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Point cloud classification · 28 papers
- PointMamba: A Simple State Space Model for Point Cloud Analysis (81 citations)
- OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding (27 citations)
- DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks (13 citations)
- PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders (7 citations)
- PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection (7 citations)
- TAPVid-3D: A Benchmark for Tracking Any Point in 3D (6 citations)
- AllClear: A Comprehensive Dataset and Benchmark for Cloud Removal in Satellite Imagery (5 citations)
- Fast Encoder-Based 3D from Casual Videos via Point Track Processing (4 citations)
- LinNet: Linear Network for Efficient Point Cloud Representation Learning (3 citations)
- Rethinking 3D Convolution in $\ell_p$-norm Space (3 citations)
- Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem (2 citations)
- Conjugate Bayesian Two-step Change Point Detection for Hawkes Process (2 citations)
and 16 more in the interactive map.
Segmentation and detection · 12 papers
- Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection (35 citations)
- LION: Linear Group RNN for 3D Object Detection in Point Clouds (29 citations)
- 3DET-Mamba: Causal Sequence Modelling for End-to-End 3D Object Detection (3 citations)
- ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images (3 citations)
- LESS: Label-Efficient and Single-Stage Referring 3D Segmentation (3 citations)
- Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation (2 citations)
- Generated and Pseudo Content guided Prototype Refinement for Few-shot Point Cloud Segmentation (2 citations)
- Spherical Frustum Sparse Convolution Network for LiDAR Point Cloud Semantic Segmentation (2 citations)
- Voxel Proposal Network via Multi-Frame Knowledge Distillation for Semantic Scene Completion (2 citations)
- One for All: Multi-Domain Joint Training for Point Cloud Based 3D Object Detection (1 citation)
- Just Add $100 More: Augmenting Pseudo-LiDAR Point Cloud for Resolving Class-imbalance Problem
- STONE: A Submodular Optimization Framework for Active 3D Object Detection
Registration and matching · 6 papers
- A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registration (8 citations)
- 3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration (6 citations)
- Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration (2 citations)
- Multi-scale Consistency for Robust 3D Registration via Hierarchical Sinkhorn Tree (2 citations)
- GeoNLF: Geometry guided Pose-Free Neural LiDAR Fields (1 citation)
- A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization
Shape and surface completion · 6 papers
- Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Images (2 citations)
- MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-Step (2 citations)
- UV-free Texture Generation with Denoising and Geodesic Heat Diffusion (2 citations)
- Flatten Anything: Unsupervised Neural Surface Parameterization (1 citation)
- Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priors (1 citation)
- LAM3D: Large Image-Point Clouds Alignment Model for 3D Reconstruction from Single Image (1 citation)