Search Results for author:
Found 159 papers, 63 papers with code
Layout2Scene: 3D Semantic Layout Guided Scene Generation via Geometry and Appearance Diffusion Priors
To fully leverage 2D diffusion priors in geometry and appearance generation, we introduce a semantic-guided geometry diffusion model and a semantic-geometry guided diffusion model which are finetuned on a scene dataset.
DAS3R: Dynamics-Aware Gaussian Splatting for Static Scene Reconstruction
Our proposed method is termed DAS3R, an abbreviation for Dynamics-Aware Gaussian Splatting for Static Scene Reconstruction.
Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs
The rise of large language models (LLMs) has created a significant disparity: industrial research labs with their computational resources, expert teams, and advanced infrastructures, can effectively fine-tune LLMs, while individual developers and small organizations face barriers due to limited resources.
CogNav: Cognitive Process Modeling for Object Goal Navigation with LLMs
Inspired by neuroscientific evidence that humans consistently update their cognitive states while searching for objects in unseen environments, we present CogNav, which attempts to model this cognitive process with the help of large language models.
Neural Observation Field Guided Hybrid Optimization of Camera Placement
Consequently, most existing methods tackle this challenge by leveraging non-gradient-based optimization methods. In this work, we present a hybrid camera placement optimization approach that incorporates both gradient-based and non-gradient-based optimization methods.
Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models
Exploratory data analysis (EDA), coupled with SQL, is essential for data analysts involved in data exploration and analysis.
VideoDirector: Precise Video Editing via Text-to-Video Models
Despite the typical inversion-then-editing paradigm using text-to-image (T2I) models has demonstrated promising results, directly extending it to text-to-video (T2V) models still suffers severe artifacts such as color flickering and content distortion.
GSEditPro: 3D Gaussian Splatting Editing with Attention-based Progressive Localization
With the emergence of large-scale Text-to-Image(T2I) models and implicit 3D representations like Neural Radiance Fields (NeRF), many text-driven generative editing methods based on NeRF have appeared.
CAD-NeRF: Learning NeRFs from Uncalibrated Few-view Images by CAD Model Retrieval
Given sparse-view input images, we run a model and pose retrieval from the library, to get a model with similar shapes, serving as the density supervision and pose initializations.
CDR: Customizable Density Ratios of Strong-over-weak LLMs for Preference Annotation
In our experiment using density ratio from a pair of Mistral-7B models, CDR achieves a RewardBench score of 82. 6, outperforming the best trained reward functions from same model class and demonstrating competitive performance against SoTA models in Safety (91. 0) and Reasoning (88. 0) domains.
Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training
Training generative models with differential privacy (DP) typically involves injecting noise into gradient updates or adapting the discriminator's training procedure.
PH-Dropout: Practical Epistemic Uncertainty Quantification for View Synthesis
View synthesis using Neural Radiance Fields (NeRF) and Gaussian Splatting (GS) has demonstrated impressive fidelity in rendering real-world scenarios.
Generic Objects as Pose Probes for Few-shot View Synthesis
COLMAP is frequently employed for preprocessing to estimate poses, while it necessitates a large number of feature matches to operate effectively, and it struggles with scenes characterized by sparse features, large baselines between images, or a limited number of input images.
Urban context and delivery performance: Modelling service time for cargo bikes and vans across diverse urban environments
We introduce two datasets that allow for in-depth analysis and modelling of service times of cargo bikes and use existing datasets to reason about differences in delivery performance across vehicle types.
Ensemble Predicate Decoding for Unbiased Scene Graph Generation
Scene Graph Generation (SGG) aims to generate a comprehensive graphical representation that accurately captures the semantic information of a given scenario.
LLM-enhanced Scene Graph Learning for Household Rearrangement
The household rearrangement task involves spotting misplaced objects in a scene and accommodate them with proper places.
PartGS:Learning Part-aware 3D Representations by Fusing 2D Gaussians and Superquadrics
In this paper, we introduce $\textbf{PartGS}$, $\textbf{part}$-aware 3D reconstruction by a hybrid representation of 2D $\textbf{G}$aussians and $\textbf{S}$uperquadrics, which parses objects or scenes into semantic parts, digging 3D structural clues from multi-view image inputs.
Learning High-Frequency Functions Made Easy with Sinusoidal Positional Encoding
Fourier features based positional encoding (PE) is commonly used in machine learning tasks that involve learning high-frequency features from low-dimensional inputs, such as 3D view synthesis and time series regression with neural tangent kernels.
Parametric Primitive Analysis of CAD Sketches with Vision Transformer
This framework consists of a primitive network and a constraint network, transforming the sketch analysis task into a set prediction problem to enhance the effective handling of primitives and constraints.
DISCO: Efficient Diffusion Solver for Large-Scale Combinatorial Optimization Problems
Combinatorial Optimization (CO) problems are fundamentally important in numerous real-world applications across diverse industries, characterized by entailing enormous solution space and demanding time-sensitive response.
Relighting Scenes with Object Insertions in Neural Radiance Fields
The insertion of objects into a scene and relighting are commonly utilized applications in augmented reality (AR).
Quantum Compiling with Reinforcement Learning on a Superconducting Processor
To effectively implement quantum algorithms on noisy intermediate-scale quantum (NISQ) processors is a central task in modern quantum technology.
Improving Reward-Conditioned Policies for Multi-Armed Bandits using Normalized Weight Functions
Recently proposed reward-conditioned policies (RCPs) offer an appealing alternative in reinforcement learning.
LInK: Learning Joint Representations of Design and Performance Spaces through Contrastive Learning for Mechanism Synthesis
Moreover, we introduce a significantly more challenging benchmark, named LINK ABC, which involves synthesizing linkages that trace the trajectories of English capital alphabets, an inverse design benchmark task that existing methods struggle with due to large nonlinearities and tiny feasible space.
Part-aware Shape Generation with Latent 3D Diffusion of Neural Voxel Fields
This paper presents a novel latent 3D diffusion model for the generation of neural voxel fields, aiming to achieve accurate part-aware structures.
NeRF-Guided Unsupervised Learning of RGB-D Registration
In this paper, we present NeRF-UR, a novel frame-to-model optimization framework for unsupervised RGB-D registration.
Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes
The superpoint correspondences are then extended to instance candidates at the fine level according to the instance masks.
InterFusion: Text-Driven Generation of 3D Human-Object Interaction
In this study, we tackle the complex task of generating 3D human-object interactions (HOI) from textual descriptions in a zero-shot text-to-3D manner.
Surface Reconstruction from Point Clouds via Grid-based Intersection Prediction
On the other hand, UDF-based methods can effectively represent open surfaces but often introduce noise, leading to artefacts in the mesh.
LAB: Large-Scale Alignment for ChatBots
This work introduces LAB (Large-scale Alignment for chatBots), a novel methodology designed to overcome the scalability challenges in the instruction-tuning phase of large language model (LLM) training.
Learning Dual-arm Object Rearrangement for Cartesian Robots
To achieve the goal, the core idea is to develop an effective object-to-arm task assignment strategy for minimizing the cumulative task execution time and maximizing the dual-arm cooperation efficiency.
Conversational Crowdsensing: A Parallel Intelligence Powered Novel Sensing Approach
The transition from CPS-based Industry 4. 0 to CPSS-based Industry 5. 0 brings new requirements and opportunities to current sensing approaches, especially in light of recent progress in Chatbots and Large Language Models (LLMs).
GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding
Speculative decoding is a relatively new decoding framework that leverages small and efficient draft models to reduce the latency of LLMs.
The Risk of Federated Learning to Skew Fine-Tuning Features and Underperform Out-of-Distribution Robustness
To tackle the scarcity and privacy issues associated with domain-specific datasets, the integration of federated learning in conjunction with fine-tuning has emerged as a practical solution.
DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection
With the recent success of the diffusion probabilistic model (DPM), we found it is especially suitable for accurate and crisp edge detection since the denoising process is directly applied to the original image size.
Latent Space Explorer: Visual Analytics for Multimodal Latent Space Exploration
Machine learning models built on training data with multiple modalities can reveal new insights that are not accessible through unimodal datasets.
DAP: Domain-aware Prompt Learning for Vision-and-Language Navigation
Then we introduce soft visual prompts in the input space of the visual encoder in a pretrained model.
Polyhedral Surface: Self-supervised Point Cloud Reconstruction Based on Polyhedral Surface
This method provides more flexible to represent sharp feature and surface boundary on open surface.
Imitator Learning: Achieve Out-of-the-Box Imitation Ability in Variable Environments
In this work, we focus on imitator learning based on only one expert demonstration.
Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement
The capacity of a modern deep learning system to determine if a sample falls within its realm of knowledge is fundamental and important.
Ranked #1 on
Out-of-Distribution Detection
on Far-OOD
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Accurate and Fast Compressed Video Captioning
Addressing this, we study video captioning from a different perspective in compressed domain, which brings multi-fold advantages over the existing pipeline: 1) Compared to raw images from the decoded video, the compressed video, consisting of I-frames, motion vectors and residuals, is highly distinguishable, which allows us to leverage the entire video for learning without manual sampling through a specialized model design; 2) The captioning model is more efficient in inference as smaller and less redundant information is processed.
Ranked #8 on
Video Captioning
on VATEX
Prompt-based Context- and Domain-aware Pretraining for Vision and Language Navigation
In the indoor-aware stage, we apply an efficient tuning paradigm to learn deep visual prompts from an indoor dataset, in order to augment pretrained models with inductive biases towards indoor environments.
Stage-by-stage Wavelet Optimization Refinement Diffusion Model for Sparse-View CT Reconstruction
Diffusion models have emerged as potential tools to tackle the challenge of sparse-view CT reconstruction, displaying superior performance compared to conventional methods.
SuperUDF: Self-supervised UDF Estimation for Surface Reconstruction
The key insight is that if the UDF is estimated correctly, the 3D points should be locally projected onto the underlying surface following the gradient of the UDF.
MIPS-Fusion: Multi-Implicit-Submaps for Scalable and Robust Online Neural RGB-D Reconstruction
For the first time, randomized optimization is made possible in neural tracking with several key designs to the learning process, enabling efficient and robust tracking even under fast camera motions.
2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Clouds
The commonly adopted detect-then-match approach to registration finds difficulties in the cross-modality cases due to the incompatible keypoint detection and inconsistent feature description.
PlaneRecTR++: Unified Query Learning for Joint 3D Planar Reconstruction and Pose Estimation
With an initial camera pose and per-frame plane predictions provided from the first stage, exclusively designed modules, potentially relying on extra plane correspondence labelling, are applied to merge multi-view plane entities and produce 6DoF camera pose.
GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer
They seek correspondences over downsampled superpoints, which are then propagated to dense points.
RayMVSNet++: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereo
In particular, we propose RayMVSNet which learns sequential prediction of a 1D implicit field along each camera ray with the zero-crossing point indicating scene depth.
Tensorformer: Normalized Matrix Attention Transformer for High-quality Point Cloud Reconstruction
Surface reconstruction from raw point clouds has been studied for decades in the computer graphics community, which is highly demanded by modeling and rendering applications nowadays.
Delving into Crispness: Guided Label Refinement for Crisp Edge Detection
Learning-based edge detection usually suffers from predicting thick edges.
Simultaneous Image-to-Zero and Zero-to-Noise: Diffusion Models with Analytical Image Attenuation
We propose incorporating an analytical image attenuation process into the forward diffusion process for high-quality (un)conditioned image generation with significantly fewer denoising steps compared to the vanilla diffusion model requiring thousands of steps.
Graphical vs. Deep Generative Models: Measuring the Impact of Differentially Private Mechanisms and Budgets on Utility
We believe our work will aid the deployment of DP synthetic data techniques by navigating through the best candidate models vis-a-vis the dataset features, desired privacy levels, and downstream tasks.
Estimating the Density Ratio between Distributions with High Discrepancy using Multinomial Logistic Regression
We show that if these auxiliary densities are constructed such that they overlap with $p$ and $q$, then a multi-class logistic regression allows for estimating $\log p/q$ on the domain of any of the $K+2$ distributions and resolves the distribution shift problems of the current state-of-the-art methods.
Enhancing Video Super-Resolution via Implicit Resampling-based Alignment
We show that bilinear interpolation inherently attenuates high-frequency information while an MLP-based coordinate network can approximate more frequencies.
Ranked #2 on
Video Super-Resolution
on REDS4- 4x upscaling
Weakly-supervised Single-view Image Relighting
For re-rendering, we propose a differentiable specular rendering layer to render low-frequency non-Lambertian materials under various illuminations of spherical harmonics.
SOCS: Semantically-aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variations
We propose Semantically-aware Object Coordinate Space (SOCS) built by warping-and-aligning the objects guided by a sparse set of keypoints with semantically meaningful correspondence.
Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registration
We first design a local spatial consistency measure over the deformation graph of the point cloud, which evaluates the spatial compatibility only between the correspondences in the vicinity of a graph node.
Learning Accurate Template Matching with Differentiable Coarse-to-Fine Correspondence Refinement
To tackle the challenges, we propose an accurate template matching method based on differentiable coarse-to-fine correspondence refinement.
NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction from Multi-view Images
We study the problem of reconstructing 3D feature curves of an object from a set of calibrated multi-view images.
Multi-Symmetry Ensembles: Improving Diversity and Generalization via Opposing Symmetries
In this work, we present Multi-Symmetry Ensembles (MSE), a framework for constructing diverse ensembles by capturing the multiplicity of hypotheses along symmetry axes, which explore the hypothesis space beyond stochastic perturbations of model weights and hyperparameters.
SSR-2D: Semantic 3D Scene Reconstruction from 2D Images
Most deep learning approaches to comprehensive semantic modeling of 3D indoor spaces require costly dense annotations in the 3D domain.
Modelling the performance of delivery vehicles across urban micro-regions to accelerate the transition to cargo-bike logistics
Light goods vehicles (LGV) used extensively in the last mile of delivery are one of the leading polluters in cities.
MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval
The first is a Temporal Adaptation Module that is incorporated in the video branch to introduce global and local temporal contexts.
Edge Preserving Implicit Surface Representation of Point Clouds
Among them, the differential Laplican regularizer can effectively alleviate the implicit surface unsmoothness caused by the point cloud quality deteriorates; Meanwhile, in order to reduce the excessive smoothing at the edge regions of implicit suface, we proposed a dynamic edge extract strategy for sampling near the sharp edge of point cloud, which can effectively avoid the Laplacian regularizer from smoothing all regions.
BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration
Extensive experiments on real-world scenarios demonstrate that our method achieves the best of both worlds in accuracy, efficiency, and generalization.
Learning Physically Realizable Skills for Online Packing of General 3D Shapes
We study the problem of learning online packing skills for irregular 3D shapes, which is arguably the most challenging setting of bin packing problems.
Multi-resolution Monocular Depth Map Fusion by Self-supervised Gradient-based Composition
Therefore, we propose a novel depth map fusion module to combine the advantages of estimations with multi-resolution inputs.
3D-Aware Object Goal Navigation via Simultaneous Exploration and Identification
However, leveraging 3D scene representation can be prohibitively unpractical for policy learning in this floor-level task, due to low sample efficiency and expensive computational cost.
NIFT: Neural Interaction Field and Template for Object Manipulation
Given a few object manipulation demos, NIFT guides the generation of the interaction imitation for a new object instance by matching the Neural Interaction Template (NIT) extracted from the demos in the target Neural Interaction Field (NIF) defined for the new object.
6DOF Pose Estimation of a 3D Rigid Object based on Edge-enhanced Point Pair Features
We introduce a well-targeted down-sampling strategy that focuses more on edge area for efficient feature extraction of complex geometry.
HybridGNN: Learning Hybrid Representation in Multiplex Heterogeneous Networks
One of the most important tasks in recommender systems is to predict the potential connection between two nodes under a specific edge type (i. e., relationship).
AutoTransition: Learning to Recommend Video Transition Effects
First we learn the embedding of video transitions through a video transition classification task.
Repairing Systematic Outliers by Learning Clean Subspaces in VAEs
Seeing as a systematic outlier is a combination of patterns of a clean instance and systematic error patterns, our main insight is that inliers can be modelled by a smaller representation (subspace) in a model than outliers.
dpart: Differentially Private Autoregressive Tabular, a General Framework for Synthetic Data Generation
We propose a general, flexible, and scalable framework dpart, an open source Python library for differentially private synthetic data generation.
RayMVSNet: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereo
In particular, we propose RayMVSNet which learns sequential prediction of a 1D implicit field along each camera ray with the zero-crossing point indicating scene depth.
Learning High-DOF Reaching-and-Grasping via Dynamic Representation of Gripper-Object Interaction
To resolve the sample efficiency issue in learning the high-dimensional and complex control of dexterous grasping, we propose an effective representation of grasping state characterizing the spatial interaction between the gripper and the target object.
DisARM: Displacement Aware Relation Module for 3D Detection
However, adopting relations between all the object or patch proposals for detection is inefficient, and an imbalanced combination of local and global relations brings extra noise that could mislead the training.
DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training
A standard hardware bottleneck when training deep neural networks is GPU memory.
3DRM:Pair-wise relation module for 3D object detection
Context has proven to be one of the most important factors in object layout reasoning for 3D scene understanding.
ARM3D: Attention-based relation module for indoor 3D object detection
In the field of 3D object detection, previous methods have been taking the advantage of context encoding, graph embedding, or explicit relation reasoning to extract relation context.
Geometric Transformer for Fast and Robust Point Cloud Registration
Such sparse and loose matching requires contextual features capturing the geometric structure of the point clouds.
RIM-Net: Recursive Implicit Fields for Unsupervised Learning of Hierarchical Shape Structures
Each level of the tree corresponds to an assembly of shape parts, represented as implicit functions, to reconstruct the input shape.
STEdge: Self-training Edge Detection with Multi-layer Teaching and Regularization
In particular, we impose a consistency regularization which enforces the outputs from each of the multiple layers to be consistent for the input image and its perturbed counterpart.
Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision
In this paper, we introduce a neural architecture, termed Box2Seg, to learn point-level semantics of 3D point clouds with bounding box-level supervision.
Decoupling Makes Weakly Supervised Local Feature Better
Weakly supervised learning can help local feature methods to overcome the obstacle of acquiring a large-scale dataset with densely labeled correspondences.
Ranked #1 on
Camera Localization
on Aachen Day-Night benchmark
A Bayesian-Symbolic Approach to Reasoning and Learning in Intuitive Physics
In this paper, we propose a Bayesian-symbolic framework (BSP) for physical reasoning and learning that is close to human-level sample-efficiency and accuracy.
Targeted Neural Dynamical Modeling
These approaches, however, are limited in their ability to capture the underlying neural dynamics (e. g. linear) and in their ability to relate the learned dynamics back to the observed behaviour (e. g. no time lag).
Learning Efficient Online 3D Bin Packing on Packing Configuration Trees
PCT is a full-fledged description of the state and action space of bin packing which can support packing policy learning based on deep reinforcement learning (DRL).
Scaling Densities For Improved Density Ratio Estimation
As such, estimating density ratios accurately using only samples from $p$ and $q$ is of high significance and has led to a flurry of recent work in this direction.
Learning Practically Feasible Policies for Online 3D Bin Packing
In this problem, the items are delivered to the agent without informing the full sequence information.
Accelerating Video Object Segmentation with Compressed Video
We propose an efficient plug-and-play acceleration framework for semi-supervised video object segmentation by exploiting the temporal redundancies in videos presented by the compressed bitstream.
Deep Tiny Network for Recognition-Oriented Face Image Quality Assessment
Based on the proposed quality measurement, we propose a deep Tiny Face Quality network (tinyFQnet) to learn a quality prediction function from data.
Objective-aware Traffic Simulation via Inverse Reinforcement Learning
Traffic simulators act as an essential component in the operating and planning of transportation systems.
ROSEFusion: Random Optimization for Online Dense Reconstruction under Fast Camera Motion
We propose to tackle the difficulties of fast-motion camera tracking in the absence of inertial measurements using random optimization, in particular, the Particle Filter Optimization (PFO).
Potential Convolution: Embedding Point Clouds into Potential Fields
In this work, rather than defining a continuous or discrete kernel, we directly embed convolutional kernels into the learnable potential fields, giving rise to potential convolution.
Learning Fine-Grained Segmentation of 3D Shapes without Part Labels
Learning-based 3D shape segmentation is usually formulated as a semantic labeling problem, assuming that all parts of training shapes are annotated with a given set of tags.
StablePose: Learning 6D Object Poses from Geometrically Stable Patches
According to the theory of geometric stability analysis, a minimal set of three planar/cylindrical patches are geometrically stable and determine the full 6DoFs of the object pose.
A Bayesian-Symbolic Approach to Learning and Reasoning for Intuitive Physics
As such, learning the laws is then reduced to symbolic regression and Bayesian inference methods are used to obtain the distribution of unobserved properties.
Selective Sensing: A Data-driven Nonuniform Subsampling Approach for Computation-free On-Sensor Data Dimensionality Reduction
In this paper, we propose a selective sensing framework that adopts the novel concept of data-driven nonuniform subsampling to reduce the dimensionality of acquired signals while retaining the information of interest in a computation-free fashion.
Study of charmonium-like and fully-charm tetraquark spectroscopy
The masses of tetraquark states of all $qc\bar q \bar c$ and $cc\bar c \bar c$ quark configurations are evaluated in a constituent quark model, where the Cornell-like potential and one-gluon exchange spin-spin coupling are employed.
High Energy Physics - Phenomenology
Hausdorff Point Convolution with Geometric Priors
We show that HPC constitutes a powerful point feature learning with a rather compact set of only four types of geometric priors as kernels.
On Learning the Right Attention Point for Feature Enhancement
We present a novel attention-based mechanism to learn enhanced point features for point cloud processing tasks, e. g., classification and segmentation.
A geometry-based relaxation algorithm for equilibrating a trivalent polygonal network in two dimensions and its implications
The succeed of simulation strongly supports the ellipse packing hypothesis that was proposed to explain the dynamic behaviors of a trivalent 2D structure.
Biological Physics Adaptation and Self-Organizing Systems Cell Behavior
Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modeling
Current autoencoder-based disentangled representation learning methods achieve disentanglement by penalizing the (aggregate) posterior to encourage statistical independence of the latent factors.
WarpCore: A Library for fast Hash Tables on GPUs
The rapidly growing amount of data emerging in many fields motivated the need for accelerated hash tables designed for modern parallel architectures.
Distributed, Parallel, and Cluster Computing
SymmetryNet: Learning to Predict Reflectional and Rotational Symmetries of 3D Shapes from Single-View RGB-D Images
We propose an end-to-end deep neural network which is able to predict both reflectional and rotational symmetries of 3D objects present in the input RGB-D image.
PIE-NET: Parametric Inference of Point Cloud Edges
We introduce an end-to-end learnable technique to robustly identify feature edges in 3D point cloud data.
Online 3D Bin Packing with Constrained Deep Reinforcement Learning
We solve a challenging yet practically useful variant of 3D Bin Packing Problem (3D-BPP).
AReLU: Attention-based Rectified Linear Unit
Adding the attention module with a rectified linear unit (ReLU) results in an amplification of positive elements and a suppression of negative ones, both with learned, data-adaptive parameters.
Telescoping Density-Ratio Estimation
Density-ratio estimation via classification is a cornerstone of unsupervised learning.
MLCVNet: Multi-Level Context VoteNet for 3D Object Detection
We demonstrate these by capturing contextual information at patch, object and scene levels.
Ranked #2 on
3D Object Detection
on ARKitScenes
Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation
Online semantic 3D segmentation in company with real-time RGB-D reconstruction poses special challenges such as how to perform 3D convolution directly over the progressively fused 3D geometric data, and how to smartly fuse information from frame to frame.
A multiple-instance densely-connected ConvNet for aerial scene classification
It regards aerial scene classification as a multiple-instance learning problem so that local semantics can be further investigated.
Ranked #3 on
Scene Recognition
on AID
Learning in the Frequency Domain
Experiment results show that learning in the frequency domain with static channel selection can achieve higher accuracy than the conventional spatial downsampling approach and meanwhile further reduce the input data size.
DynamicPPL: Stan-like Speed for Dynamic Probabilistic Models
Since DynamicPPL is a modular, stand-alone library, any probabilistic programming system written in Julia, such as Turing. jl, can use DynamicPPL to specify models and trace their model parameters.
Deep Differentiable Grasp Planner for High-DOF Grippers
We present an end-to-end algorithm for training deep neural networks to grasp novel objects.
Robotics
Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation
To tackle intra-class shape variations, we learn canonical shape space (CASS), a unified representation for a large variety of instances of a certain object category.
Constructing the F-Graph with a Symmetric Constraint for Subspace Clustering
Based on further studying the low-rank subspace clustering (LRSC) and L2-graph subspace clustering algorithms, we propose a F-graph subspace clustering algorithm with a symmetric constraint (FSSC), which constructs a new objective function with a symmetric constraint basing on F-norm, whose the most significant advantage is to obtain a closed-form solution of the coefficient matrix.
Reinforcement Learning-based Visual Navigation with Information-Theoretic Regularization
The regularization maximizes the mutual information between navigation actions and visual observation transforms of an agent, thus promoting more informed navigation decisions.
Robotics
Decoupling Features and Coordinates for Few-shot RGB Relocalization
To address this issue, we approach camera relocalization with a decoupled solution where feature extraction, coordinate regression, and pose estimation are performed separately.
PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes
We introduce PQ-NET, a deep neural network which represents and generates 3D shapes via sequential part assembly.
Bijectors.jl: Flexible transformations for probability distributions
Transforming one probability distribution to another is a powerful tool in Bayesian inference and machine learning.
AdvancedHMC.jl: A robust, modular and efficient implementation of advanced HMC algorithms
Stan's Hamilton Monte Carlo (HMC) has demonstrated remarkable sampling robustness and efficiency in a wide range of Bayesian inference problems through carefully crafted adaption schemes to the celebrated No-U-Turn sampler (NUTS) algorithm.
Rescan: Inductive Instance Segmentation for Indoor RGBD Scans
In depth-sensing applications ranging from home robotics to AR/VR, it will be common to acquire 3D scans of interior spaces repeatedly at sparse time intervals (e. g., as part of regular daily use).
Experimental demonstration of entanglement-enabled universal quantum cloning in a circuit
No-cloning theorem forbids perfect cloning of an unknown quantum state.
Quantum Physics
Multiple instance dense connected convolution neural network for aerial image scene classification
While the current convolution neural network tends to extract global features and global semantic information in a scene, the geo-spatial objects can be located at anywhere in an aerial image scene and their spatial arrangement tends to be more complicated.
Building change detection based on multi-scale filtering and grid partition
Exhaustive experiments indicate that the proposed method can detect building change types directly and outperform the current multi-index learning method.
Active Scene Understanding via Online Semantic Reconstruction
In our method, the exploratory robot scanning is both driven by and targeting at the recognition and segmentation of semantic objects from the scene.
NeoNav: Improving the Generalization of Visual Navigation via Generating Next Expected Observations
First, the latent distribution is conditioned on current observations and the target view, leading to a model-based, target-driven navigation.
Learning Part Generation and Assembly for Structure-aware Shape Synthesis
Enlightened by the fact that 3D shape structure is characterized as part composition and placement, we propose to model 3D shape variations with a part-aware deep generative network, coined as PAGENet.
Scalable Spike Source Localization in Extracellular Recordings using Amortized Variational Inference
Determining the positions of neurons in an extracellular recording is useful for investigating functional properties of the underlying neural circuitry.
Learning Phase Competition for Traffic Signal Control
Increasingly available city data and advanced learning techniques have empowered people to improve the efficiency of our city functions.
Diagnosing Reinforcement Learning for Traffic Signal Control
In this paper, we propose to re-examine the RL approaches through the lens of classic transportation theory.
CoLight: Learning Network-level Cooperation for Traffic Signal Control
To enable cooperation of traffic signals, in this paper, we propose a model, CoLight, which uses graph attentional networks to facilitate communication.
Multi-agent Reinforcement Learning
Reinforcement Learning
+1
Spatiotemporal CNN for Video Object Segmentation
Specifically, the temporal coherence branch pretrained in an adversarial fashion from unlabeled video data, is designed to capture the dynamic appearance and motion cues of video sequences to guide object segmentation.
Ranked #2 on
Semi-Supervised Video Object Segmentation
on YouTube
AdaCoSeg: Adaptive Shape Co-Segmentation with Group Consistency Loss
While the part prior network can be trained with noisy and inconsistently segmented shapes, the final output of AdaCoSeg is a consistent part labeling for the input set, with each shape segmented into up to (a user-specified) K parts.
Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes
For the task of mobility analysis of 3D shapes, we propose joint analysis for simultaneous motion part segmentation and motion attribute estimation, taking a single 3D model as input.
PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation
Meanwhile, to increase the segmentation accuracy at each node, we enhance the recursive contextual feature with the shape feature extracted for the corresponding part.
Ranked #16 on
3D Part Segmentation
on ShapeNet-Part
(Class Average IoU metric)
Generating Grasp Poses for a High-DOF Gripper Using Neural Networks
The quality of the grasp poses is on par with the groundtruth poses in the dataset.
Robotics
SCORES: Shape Composition with Recursive Substructure Priors
The network may significantly alter the geometry and structure of the input parts and synthesize a novel shape structure based on the inputs, while adding or removing parts to minimize a structure plausibility loss.
Learning to Group and Label Fine-Grained Shape Components
We propose to generate part hypotheses from the components based on a hierarchical grouping strategy, and perform labeling on those part groups instead of directly on the components.
VERAM: View-Enhanced Recurrent Attention Model for 3D Shape Classification
Multi-view deep neural network is perhaps the most successful approach in 3D shape classification.
Triangle Lasso for Simultaneous Clustering and Optimization in Graph Datasets
The reason is that it finds the similar instances according to their features directly, which is usually impacted by the imperfect data, and thus returns sub-optimal results.
Learning Discriminative 3D Shape Representations by View Discerning Networks
In this network, a Score Generation Unit is devised to evaluate the quality of each projected image with score vectors.
LAPRAN: A Scalable Laplacian Pyramid Reconstructive Adversarial Network for Flexible Compressive Sensing Reconstruction
We propose a scalable Laplacian pyramid reconstructive adversarial network (LAPRAN) that enables high-fidelity, flexible and fast CS images reconstruction.
GRAINS: Generative Recursive Autoencoders for INdoor Scenes
We present a generative neural network which enables us to generate plausible 3D indoor scenes in large quantities and varieties, easily and highly efficiently.
Graphics
Generative Ratio Matching Networks
In this work, we take their insight of using kernels as fixed adversaries further and present a novel method for training deep generative models that does not involve saddlepoint optimization.