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.
V-SysId identifies keypoints and 3D system from unlabeled videos.
problem Identifying keypoints and 3D system from unlabeled videos.
method Alternates between parameter estimation and extrinsic camera calibration, using motion equations as weak supervision.
result Utility of the approach demonstrated across various settings.
The paper uses facial keypoints to estimate post-surgical pain intensity.
problem Accurately assessing pain levels from self-reported ratings is challenging.
method The approach analyzes 2D and 3D facial keypoints to estimate pain intensity.
result The pain estimation model uses multiple instance learning.
We present an unsupervised approach for learning to estimate three dimensional (3D) facial structure from a single image while also predicting 3D viewpoint transformations that match a desired pose and facial geometry. We achieve this by inferring the depth of facial keypoints of an input image in an unsupervised manne…
PRNet registers partial 3D shapes using deep learning.
problem Partial-to-partial point cloud registration.
method Self-supervised deep learning network for non-convex alignment and partial correspondence.
result Outperforms existing methods on synthetic data.
KINet learns object interactions without supervision for robotic pushing.
problem Lack of supervised data for object-centric forward prediction.
method End-to-end unsupervised framework using keypoint representation and contrastive estimation.
result Automatically generalizes to unseen scenarios and accurately predicts future states.
Detect facial keypoints is a critical element in face recognition. However, there is difficulty to catch keypoints on the face due to complex influences from original images, and there is no guidance to suitable algorithms. In this paper, we study different algorithms that can be applied to locate keyponits. Specifical…
Proposes PSGAN for generating high-res anime images with structural consistency.
problem Lack of high-quality, structurally consistent full-body high-resolution anime images.
method Progressive Structure-conditional Generative Adversarial Networks (PSGAN) with progressive training.
result Demonstrates effectiveness through comparisons and diverse anime character generation.
Deep learning animates objects from input images and videos.
problem Animating arbitrary objects from input images and videos.
method A deep learning framework with three modules: Keypoint Detector, Dense Motion prediction network, and Motion Transfer Network.
result Our method outperforms state-of-the-art image animation and video generation methods.
The field of multiple view geometry has seen tremendous progress in reconstruction and calibration due to methods for extracting reliable point features and key developments in projective geometry. Point features, however, are not available in certain applications and result in unstructured point cloud reconstructions.…
A new method for spotting symbols in CAD images reduces annotation costs and improves accuracy.
problem Challenging task of labeling symbols from CAD drawings.
method Pixel-wise point location via Progressive Gaussian Kernels (PGK) and local offset.
result The proposed method achieves good generalization on real-world CAD images.
End-to-end trainable graph matching using improved combinatorial solvers.
problem Graph matching in deep learning.
method Combining deep learning with optimized combinatorial solvers.
result Advances state-of-the-art on deep graph matching benchmarks.
A method for camera calibration using heatmap regression for fisheye images.
problem Accurate and robust camera angle estimation from fisheye images in the Manhattan world.
method Heatmap regression to detect directions of labeled image coordinates, simultaneous rotation and fisheye distortion recovery.
result Our method outperforms conventional methods on large-scale datasets and with off-the-shelf cameras.
New mutual information framework improves contrastive learning for vision tasks.
problem Maximizing mutual information for better unsupervised learning representations.
method Reformulated mutual information as a lower bound, introducing new negative sampling strategies.
result Improved representations outperform previous methods in various vision tasks.
New method improves human mesh recovery for obese people.
problem Improving mesh recovery for obese people.
method Generative optimization of mesh parameters from 2D keypoints.
result Significant improvement in mesh recovery performance on obese person images.
Model discovers causal relationships from video data of physical systems.
problem Discover structural dependencies and causal interactions in physical systems from video data.
method End-to-end model with perception, inference, and dynamics modules; handles unknown interventions.
result Model correctly identifies causal interactions and makes long-term predictions.
We study knots in 3d Chern-Simons theory with complex gauge group SL(N,C), in the context of its relation with 3d N=2 theory (the so-called 3d-3d correspondence). The defect has either co-dimension 2 or co-dimension 4 inside the 6d (2,0) theory, which is compactified on a 3-manifold M^. …
Study of 3d-3d correspondence involving q-Weyl algebra and 3d-index.
problem Understanding the action of a q-Weyl algebra on the 3d-index of knots. method Investigation of the q-Weyl algebra's module action on the 3d-index, conjecturing structural properties. result Bilinear factorization, pair of linear q-difference equations, and rational function matrix for the 3d-index determination. 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.
Simple methods improve regression transferability estimation.
problem Estimating how well regression models transfer between tasks.
method Two simple, computationally efficient approaches based on negative regularized mean squared error.
result Significantly outperform existing methods in accuracy and efficiency.
We tackle here the problem of multimodal image non-rigid registration, which is of prime importance in remote sensing and medical imaging. The difficulties encountered by classical registration approaches include feature design and slow optimization by gradient descent. By analyzing these methods, we note the significa…
3D dual field theories for Virasoro minimal models constructed using Seifert fiber spaces.
problem Constructing 3D dual field theories for Virasoro minimal models.
method 3D-3D correspondence and Seifert fiber spaces.
result 3D dual field theories constructed for Virasoro minimal models.
3D flying wings created for any angle asymptotic cones.
problem Creating 3D steady gradient Ricci solitons with any angle asymptotic cones.
method Constructing 3D flying wings for any angle asymptotic cones.
result 3D flying wings constructed for any angle asymptotic cones.
Autonomous driving requires 3D perception of vehicles and other objects in the in environment. Much of the current methods support 2D vehicle detection. This paper proposes a flexible pipeline to adopt any 2D detection network and fuse it with a 3D point cloud to generate 3D information with minimum changes of the 2D d…
Proposes a new effective central charge for 3d N=2 theories.
problem Understanding the effective central charge in 3d N=2 theories.
method Analyzes the superconformal index to propose a new quantity and discusses its properties and computation.
result Proposes a new effective central charge for 3d N=2 theories.
Smooth 3D flows from non-smooth starting points.
problem Creating smooth Ricci flows from non-smooth initial conditions.
method Generalized singular Ricci flow applied to 3D complete manifolds.
result Existence of smooth Ricci flows starting from non-smooth initial conditions.
3D Axial-Attention improves lung nodule classification accuracy.
problem Limited 3D attention in existing methods.
method Proposes 3D Axial-Attention network with 3D positional encoding.
result 3D Axial-Attention achieves state-of-the-art performance.
The paper tackles mapping tori by proposing a new approach to 3d-3d correspondence.
problem No existing approach fully describes 3d N=2 SCFTs for all types of 3-manifolds. method Systematic study of 3d N=2 gauge theories with non-linear matter fields. result Recovery of 3-manifold invariants from T[M3] indices and proposal of new q-series invariants. Novel method REACH-3D reconstructs 3D chromatin structure from HiC data.
problem Understanding the 3D structure of the genome and its temporal behavior.
method Autoencoders with recurrent neural units for manifold learning.
result REACH-3D outperforms existing methods in reconstructing chromatin structure and dynamics.
DreamFusion uses text-to-image diffusion models to create 3D images efficiently.
problem Lack of large-scale 3D datasets and efficient architectures for 3D synthesis.
method Adapting a 2D diffusion model to 3D synthesis using a loss based on probability density distillation.
result A 3D model can be optimized from a 2D diffusion model, allowing for text-to-3D synthesis.
3D steady gradient Ricci solitons are all O(2)-symmetric.
problem Characterizing 3D steady gradient Ricci solitons.
method Analyzing asymptotic behavior and using O(2) symmetry.
result All 3D steady gradient Ricci solitons are O(2)-symmetric.
Proposes a new layer for efficient 3D shape discrimination.
problem Irregular structure and redundancy in 3D point clouds hinder efficient inter-class discrimination.
method Integrates Blended Convolution and Synthesis layer that projects and synthesizes 3D point clouds, followed by 3D convolution in the unit ball.
result End-to-end architecture achieves compelling results on 3D shape recognition and retrieval.
3D Convolutional Neural Networks (3D-CNN) have been used for object recognition based on the voxelized shape of an object. However, interpreting the decision making process of these 3D-CNNs is still an infeasible task. In this paper, we present a unique 3D-CNN based Gradient-weighted Class Activation Mapping method (3D…
Improved 3D scene understanding from partial point sets using multiview fusion.
problem Challenging task of 3D scene semantic understanding from partial point clouds.
method Multiview representation of 360° point clouds and fusion with original data.
result Overall increase of 31.9% and 4.3% in segmentation accuracy for partial and complete scenes.
Generative model disentangles 3D shapes into independent factors.
problem Learning rich representations of deformable 3D shapes.
method Supervised 3D mesh-convolutional Variational AutoEncoder with latent feature disentanglement.
result Explicit disentanglement of latent factors improves shape generation and downstream tasks.
3D point cloud attacks examine how neural networks can be fooled.
problem Understanding how 3D neural networks can be exploited by attackers.
method Examined two categories of attacks: distributional and shape attacks.
result Some shape attacks can fool 3D point cloud classification models even after preprocessing.
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.
The study connects knot complements to 3d theories via half-index calculations.
problem Understanding the relationship between knot complements and 3d theories.
method Using half-index calculations and inverted Habiro series, the study realizes knot complements as homological blocks.
result The colored Jones polynomial is derived from choosing specific poles in the half-index integral expression.
Efficiently learns 3D convolutions with less data.
problem High parameter and data costs in 3D convolutions.
method Temporal factorization of 3D kernels.
result Significantly reduces training data requirement and parameter count.
GCDM generates valid large 3D molecules and optimizes existing molecules.
problem Lack of geometric properties in 3D molecule generation models.
method Introduces Geometry-Complete Diffusion Model (GCDM) using equivariant GNNs.
result Significantly outperforms existing models in 3D molecule generation and optimization.
Instantiation-Net reconstructs 3D mesh from single 2D image for right ventricle.
problem Reconstructing 3D shape from limited 2D images for surgical navigation.
method Combines DCNN for feature extraction and GCN for mesh reconstruction.
result Demonstrates practical strength and potential clinical use.
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.
The paper studies decay near singularities of 3d Yang-Mills-Higgs fields.
problem Understanding isolated singularities of 3d Yang-Mills-Higgs fields.
method Derives decay estimates and applies removable singularity theorems.
result Generalizes removable singularity theorems for 3d Yang-Mills-Higgs fields.
Researchers discover a new family of 3D solitons that are flying wings.
problem Verifying a conjecture about 3D steady gradient Ricci solitons.
method Analyzing a family of 3D flying wing solitons and proving properties of these solitons.
result 3D flying wing solitons are non-collapsed and have non-zero scalar curvature at infinity.
Defines a map connecting 3d-index and skein module.
problem Connecting mathematical physics predictions with topological quantum field theory.
method Defines a map from skein module to Laurent series ring.
result The map fulfills a supersymmetry prediction and is part of a conjectural topological quantum field theory.
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 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.
Study large N oscillations in 3D theories related to black hole physics.
problem Understanding large N sign oscillations in 3D theories via holography.
method Holographic computation of on-shell actions for Euclidean supergravity solutions, Wick rotation of magnetically charged AdS4 black holes.
result Proposed a non-trivial mathematical conjecture regarding phase factors of twisted Reidemeister-Ray-Singer torsion.