ROOTS learns to represent and render 3D scenes with object-centric models.
problem Learning to represent and render 3D scenes with object-centric compositionality.
method Probabilistic generative model for learning object representations and scene rendering from partial observations.
result The model can infer 3D object representations and render scenes from arbitrary viewpoints.
Generates coherent 3D scenes from monocular videos without supervision.
problem Lack of 3D scene modeling in video generation models.
method Trains a model to generate 3D scenes with moving objects and a background from monocular videos.
result Trained model generates coherent 3D scenes with multiple moving objects and a background.
3D object detection improved using energy-based models.
problem Accurate 3D object detection in cluttered environments from sparse LiDAR data.
method Designing a differentiable pooling operator for 3D bounding boxes integrated into a state-of-the-art 3D object detector.
result Our approach consistently outperforms the SA-SSD baseline across all 3DOD metrics on the KITTI dataset.
Paper proposes a method to reduce annotation time for 3D object detection.
problem Effort and time required for generating 3D object annotations.
method Combines human supervision with pretrained neural networks for 3D point cloud segmentation and bounding box generation.
result Reduces human annotation time by 30x.
Paper develops a differentiable approach for 3D imaging models using Fourier slice theorem.
problem Uncertainty in 3D structure modeling and pose estimation in scientific imaging.
method Differentiable probabilistic models in Fourier space with backpropagation through projection.
result Validates approach on 3D protein reconstruction and extends to probabilistic models.
Generative model creates realistic images with 3D understanding.
problem Lack of 3D understanding in existing image generation models.
method Disentangled 3D representation using shape, viewpoint, and texture.
result Generates more realistic images and enables 3D operations.
3D Adversarial Autoencoder learns compact binary descriptors from 3D point clouds.
problem Learning meaningful representations of 3D shapes for various tasks.
method End-to-end Adversarial Autoencoder model trained on 3D input and output.
result 3D Adversarial Autoencoder (3dAAE) generates state-of-the-art results for 3D points clustering and retrieval.
Proposes a multi-level learning approach for 3D object recognition.
problem Improving 3D object recognition accuracy through multi-scale spatial features.
method End-to-end multi-level learning on a multi-level voxel grid.
result Comparable object recognition performance with lower memory usage.
ObSuRF converts a single image into a 3D model with NeRFs.
problem Creating a 3D model from a single image with object segmentation.
method Unsupervised volume segmentation using Neural Radiance Fields (NeRFs).
result ObSuRF can segment a 3D scene into objects from a single image.
Proposes a model to generate 3D-aware images from 2D images.
problem Generating 3D-aware images from 2D images.
method Likelihood-based top-down model using Neural Radiance Fields and energy-based latent variables.
result Model can infer 3D object structures from 2D images and generate novel views.
KeypointNet learns 3D keypoints for object pose estimation without ground-truth.
problem Learning 3D keypoints for object pose estimation without manual annotations.
method End-to-end geometric reasoning framework to discover keypoints.
result End-to-end framework outperforms fully supervised baseline.
Graph Neural Networks improve 3D object detection in LiDAR point clouds.
problem Challenges in processing LiDAR data due to its 3D geometry and massive volume.
method Proposes a Graph Neural Network (GNN) based framework for 3D object detection.
result GNNs successfully identify objects in 3D LiDAR point clouds.
3D adversarial logos can fool object detectors in real-world settings.
problem Creating robust adversarial attacks in 3D rendering views.
method Constructing 3D adversarial logos via texture mapping and differentiable rendering.
result 3D adversarial logos are more versatile and robust than traditional adversarial patches.
Geometric Capsule Autoencoders group 3D points into parts and objects.
problem Learning object representations from 3D point clouds.
method Geometric capsules with pose and feature components, Multi-View Agreement voting mechanism.
result Learned representations enable object identification and canonical pose recovery.
The article explains Rao distances and conformal mappings for 3D objects.
problem Calculating distances and preserving angles in 3D objects.
method Proposed constructions of distances and angle-preserving mappings.
result Application to virtual tourism and line integrals in complex planes.
3D-CNN method visualizes localized geometric features for manufacturability analysis.
problem Interpreting 3D-CNN decisions for complex geometries.
method 3D-CNN with surface normals, 3D-GradCAM for feature visualization.
result Identifies critical local features for manufacturability.
Paper develops a new method to analyze 3D tree-like objects.
problem Analyzing complex geometrical and topological variations in 3D tree-like objects.
method Extended SRVF representation and new metric for tree-shaped 3D objects.
result Captures full elasticity and topological variations of branches.
We consider the problem of learning object arrangements in a 3D scene. The key idea here is to learn how objects relate to human poses based on their affordances, ease of use and reachability. In contrast to modeling object-object relationships, modeling human-object relationships scales linearly in the number of objec…
Paper uses FMCW radar and FCN for object detection and 3D estimation.
problem Object detection and 3D estimation using FMCW radar.
method Employed deep learning (FCN) over traditional signal processing. Normalization method applied to radar signal.
result System successfully detects and estimates 3D position of objects in noisy environments.
Recently, multiple formulations of vision problems as probabilistic inversions of generative models based on computer graphics have been proposed. However, applications to 3D perception from natural images have focused on low-dimensional latent scenes, due to challenges in both modeling and inference. Accounting for th…
3D-CNN learns local geometric features for manufacturability analysis of drilled holes.
problem Capturing distinguishing local features in 3D CAD geometry.
method 3D-CNN with voxel data augmented by surface normals, using 3D gradient-weighted class activation maps.
result Identification of local features critical for manufacturability analysis.
Local-HDP learns independent topics for each 3D object category in real-time.
problem Learning independent topics for each 3D object category in real-time.
method Local-Hierarchical Dirichlet Process (Local-HDP) with online variational inference.
result Local-HDP outperforms other approaches in accuracy, scalability, and memory efficiency.
3D-PRNN generates shapes from depth images using recurrent neural networks.
problem Representing 3D shapes from limited sensor data.
method Generative Recurrent Neural Network (3D-PRNN) with Gaussian Fields.
result 3D-PRNN synthesizes plausible shapes from primitives, outperforming nearest-neighbor methods.
Paper tackles unsupervised learning of 3D shapes from single images.
problem Learning 3D shapes from single images without supervision.
method Generative models, variational auto-encoders, adversarial methods.
result Model learns 3D shapes and poses from single images, showing potential for various datasets.
Improved reinforcement learning for 3D games using SLAM and object detection.
problem Challenges in 3D game environments, especially partial observability and combinatorial spaces.
method Augmented Deep Q-Learning Network with SLAM and object detection for better policy learning.
result Our approach consistently learns better policies in 3D games like Doom.
Topology-enhanced loss improves 3D object reconstruction from 2D images.
problem Challenges in reconstructing 3D objects from 2D images, especially capturing shape information.
method Integrates multi-scale topological features into the reconstruction loss using cubical complexes and optimal transport distance.
result Topology-aware loss substantially improves 3D reconstruction quality.
InSphereNet uses infilling spheres for 3D object classification, improving accuracy with fewer parameters.
problem 3D object classification using points, voxels, or images.
method Constructs infilling spheres from signed distance field (SDF) for classification.
result InSphereNet achieves superior accuracy with fewer inputs and parameters.
GENESIS generates and samples 3D scenes by capturing object interactions.
problem Lack of models that explicitly capture object interactions in scene generation.
method Object-centric latent variables, spatial GMM, amortized inference, autoregressive prior.
result First object-centric generative model of 3D visual scenes.
Voxel-FPN detects 3D objects from point clouds using raw LIDAR data.
problem 3D object detection in point cloud data for autonomous driving.
method Bottom-up voxel extraction and top-down feature fusion.
result Voxel-FPN outperforms baselines on the KITTI-3D benchmark.
Cooperative perception improves 3D object detection in autonomous vehicles.
problem Limited field-of-view and occlusion in single sensor data.
method Early fusion of point clouds from multiple sensors, late fusion of independently detected bounding boxes, and hybrid combination.
result Early fusion approach outperforms late fusion by significantly higher recall (95%) compared to single-point sensing (30%).
PolyGen models 3D meshes directly, predicting vertices and faces sequentially.
problem Efficiently modeling 3D geometry for computer graphics, robotics, and games.
method Transformer-based autoregressive model for predicting mesh vertices and faces.
result PolyGen produces high-quality, usable 3D meshes and competitive conditional performance.
New method encodes 3D object geometry into neural network weights for efficient reconstruction.
problem Efficiently representing and reconstructing 3D objects with minimal parameters.
method Mapping network that encodes object geometry into neural network weights, reconstructing objects using simple geometric spaces.
result Reconstructed objects have accuracy comparable to state-of-the-art methods with significantly fewer parameters.
CubeNet preserves 3D shape signatures through equivariance.
problem 3D ConvNets fail to capture pose differences.
method Group Convolutional Neural Network with linear equivariance to 3D transformations.
result Achieves state-of-the-art on ModelNet10 classification.
Flexible pipeline for 3D vehicle detection from 2D images.
problem Current methods lack 3D perception of vehicles and other objects.
method Adopt any 2D detection network, fuse with 3D point cloud, develop model fitting algorithm, refine with CNN.
result 3D detection results rank second among algorithms, demonstrating competencies.
A new method for generating realistic and creative 3D shapes from point clouds.
problem Generating realistic and creative 3D shapes from point clouds.
method Learning to interpolate point clouds by encoding prior knowledge about real-world objects.
result Generated 3D shapes are both realistic and creative, unlike any existing forms.
Extracts object-centric frames from unlabeled images.
problem Extracting abstract models of 3D objects from visual measurements.
method Viewpoint factorization and dense equivariant labelling neural network.
result Extracts dense object-centric coordinate frames invariant to deformations.
Enhances safety of 3D object detection neural networks.
problem Ensuring robustness and safety of 3D object detection systems.
method Symbolic error propagation, specialized loss function, safety-aware non-max-inclusion algorithm.
result Improved safety and robustness of 3D object detection neural networks.
Research evaluates adversarial attacks and defenses on 3D point cloud classifiers.
problem Robustness of 3D object classifiers against adversarial attacks.
method Extending 2D adversarial attacks to 3D point clouds and proposing new defenses.
result 3D point cloud classifiers are weak to adversarial attacks but more defensible.
Paper proposes meshAdv to generate adversarial 3D meshes for visual recognition.
problem Vulnerability of deep neural networks to adversarial examples.
method Differentiable renderer to manipulate shape and texture of 3D meshes.
result 3D meshes effectively attack classifiers and object detectors.
ED-NeRF efficiently edits 3D scenes using latent space NeRF and improved loss functions.
problem Slow training speeds and inadequate editing loss functions in existing NeRF editing techniques.
method Embedding real-world scenes into latent space of LDM, using a unique refinement layer and an improved loss function.
result ED-NeRF achieves faster editing speed and improved output quality compared to state-of-the-art models.
The paper proposes a method to learn 3D object pose manifolds using GANs and elasticae.
problem Learning image manifolds of 3D objects with limited data.
method Geom-SGAN and elasticae for geometry-preserving image interpolation.
result The method outperforms state-of-the-art GANs and VAEs in learning rotation paths.
Elastic-InfoGAN learns object identity in class-imbalanced data.
problem Learning disentangled representations in class-imbalanced data.
method Invariance to identity-preserving transformations to learn object identity.
result Effectiveness in disentangling object identity in imbalanced datasets.
AI generates sculptural objects through machine learning.
problem Generating creative and printable 3D sculptures.
method Developed two algorithms: Amalgamated DeepDream (ADD) and Partitioned DeepDream (PDD).
result Generated creative and printable 3D point clouds.
MergeNet detects morphological errors in 3D neuron segmentations.
problem High incidence of merge errors in deep learning 3D connectomics.
method Unsupervised training of MergeNet on various datasets.
result MergeNet can detect morphological errors in neuronal shapes.
A new 3D NoC design optimizes heterogeneous manycore systems for deep learning.
problem Designing energy-efficient 3D manycore platforms for deep learning.
method ML-based multi-objective optimization for heterogeneous requirements.
result 9.6% better Energy-Delay Product compared to thermally-optimized designs.
Noise2Filter improves 3D tomography reconstruction efficiency and accuracy.
problem Efficiently reconstructing 3D tomographic images in real-time with limited data.
method Self-supervised learning and a learned filter method.
result Noise2Filter achieves real-time reconstruction with limited loss of accuracy.
Graph Neural Networks model 3D granular flow simulations.
problem Accurate modeling of complex 3D granular flow processes.
method Graph Neural Networks approach to simulate 3D granular flow using LIGGGHTS.
result Machine learning trajectories match physical granular flow processes.
Proposes a robust 3D classification method for sparse point clouds.
problem Invariance to rotation, positional shift, scaling, and robustness to point sparsity in point cloud classification.
method Introduces a graph-based feature learning approach with an end-to-end neural network.
result Significantly improves 3D object classification and retrieval tasks with sparse point clouds.