ModelNet40
PulseAugur coverage of ModelNet40 — every cluster mentioning ModelNet40 across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New Neuro-Symbolic Framework Enhances 3D Geometric Reconstruction
Researchers have developed NeuSOGA3D, a novel framework that merges neural networks with symbolic reasoning for 3D geometric reconstruction. This hybrid approach projects point clouds onto planes, creates symbolic splin…
-
H3DNAS framework compresses 3D point cloud models for edge hardware via ONNX
Researchers have developed H3DNAS, a novel framework designed to compress 3D point cloud models for deployment on edge hardware like the NVIDIA Jetson Orin Nano. Unlike existing methods that require original source code…
-
New H3DNAS framework compresses 3D point cloud models on ONNX binaries
Researchers have developed H3DNAS, a novel framework for compressing 3D point cloud models that operates directly on ONNX binaries without needing original source code. This method addresses the limitations of deploying…
-
New AI Framework Translates Observations to Symbolic Math Representations
Researchers have introduced NeuSOGA, a novel framework designed to translate raw observations into explicit symbolic mathematical representations. This neuro-symbolic approach aims to bridge the gap between the latent, …
-
3D-MRL introduces nested multimodal 3D representations for varied computational budgets
Researchers have introduced 3D Matryoshka Representation Learning (3D-MRL), a novel framework for pre-training multimodal 3D representations. This approach allows a single model to generate embeddings at various dimensi…
-
New framework offers guaranteed SPD uncertainty for tensor-valued geometric learning
Researchers have developed a new framework for uncertainty quantification in tensor-valued geometric learning, specifically addressing the prediction of symmetric rank-2 tensors. This method ensures positive-definite co…
-
Active Spiking Perception uses membrane potential for anytime 3D recognition
Researchers have developed Active Spiking Perception (ASP), a novel approach for 3D point cloud recognition that utilizes the membrane potential of spiking neural networks as a belief state. This method allows the netwo…
-
Active Spiking Perception uses membrane potential for anytime 3D recognition
Researchers have developed Active Spiking Perception (ASP), a novel approach for 3D point cloud recognition that utilizes the membrane potential of spiking neural networks as a belief state. This method allows the netwo…
-
Self-supervised encoders show promise for efficient 3D LLMs
Researchers investigated the effectiveness of low-cost self-supervised point cloud encoders, specifically PCP-MAE and Point-MAE, as alternatives to expensive multi-modal encoders for 3D large language models (3D-LLMs). …
-
New framework enables efficient fine-tuning of Spiking Neural Networks for point clouds
Researchers have introduced SpikePEFT, a novel parameter-efficient fine-tuning framework designed for Spiking Neural Networks (SNNs) used in point cloud analysis. This method addresses the high parameter and storage ove…
-
New frameworks tackle scale mismatch and rotation in point-cloud registration
Two new research papers introduce novel frameworks for point-cloud registration, a critical task in 3D perception for robotics. The first, R-SLPR, addresses the challenge of aligning small or incomplete point clouds wit…
-
New MiSS Framework Explains 3D Point Cloud Classifier Decisions
Researchers have developed MiSS, a novel framework for explaining the decisions of 3D point cloud classifiers. This black-box system uses perturbation-relative sufficiency reasoning to identify minimal sufficient coalit…
-
DM3D: Dynamic Mamba architecture enhances point cloud understanding
Researchers have developed DM3D, a novel dynamic Mamba architecture designed to enhance point cloud understanding. This approach addresses the limitations of existing State Space Models (SSMs) by adapting local feature …
-
GaussFusion advances 3D Gaussian pretraining with multimodal learning · 3 sources tracked
Researchers have introduced GaussFusion, a novel multimodal pre-training framework designed for 3D Gaussian representations. This framework enhances existing methods by integrating image and text supervision through cro…
-
Federated learning and knowledge distillation benchmarked for 3D point cloud classification
A new research paper benchmarks the combined use of federated learning (FL) and knowledge distillation (KD) for 3D point cloud classification, particularly in privacy-sensitive and resource-constrained environments. The…
-
ITNet architecture unifies convolution, attention, and recurrence
Researchers have introduced ITNet, a novel neural network architecture that unifies convolution, attention, and recurrence into a single learnable integral transform. This architecture uses a learnable kernel, implement…
-
Sigma-Branch framework cuts active parameters for edge AI
Researchers have introduced Sigma-Branch (SigmaB), a novel framework designed to optimize deep neural networks for memory-constrained edge devices. SigmaB restructures dense networks into a hierarchical tree with shared…
-
GridPE introduces neuroscience-inspired embeddings for arbitrary dimensions
Researchers have introduced GridPE, a novel positional embedding framework inspired by the spatial cognition of grid cells in mammals. This method aims to improve the understanding of spatial relationships across arbitr…
-
New MAPR method boosts 3D point cloud robustness against attacks
Researchers have developed a new method called Manifold-Aligned Point Recognition (MAPR) to improve the robustness of 3D point cloud networks against adversarial attacks. MAPR addresses the issue of latent geometry misa…
-
New t-FCW graph representation enhances point cloud analysis
Researchers have developed an enhanced transposed Fully Connected Weighted (t-FCW) graph representation to embed point clouds into a metric space. This new method analyzes the properties that make t-FCW effective, leadi…