Search Results for author:
Found 69 papers, 46 papers with code
Network Sketching: Exploiting Binary Structure in Deep CNNs
Convolutional neural networks (CNNs) with deep architectures have substantially advanced the state-of-the-art in computer vision tasks.
Physics Inspired Optimization on Semantic Transfer Features: An Alternative Method for Room Layout Estimation
In this paper, we propose an alternative method to estimate room layouts of cluttered indoor scenes.
Decoder Network Over Lightweight Reconstructed Feature for Fast Semantic Style Transfer
Our method decomposes the semantic style transfer problem into feature reconstruction part and feature decoder part.
SnapQuant: A Probabilistic and Nested Parameterization for Binary Networks
During the training phase, we generate binary weights on-the-fly since what we actually maintain is the policy network, and all the binary weights are used in a burn-after-reading style.
A Closed-form Solution to Universal Style Transfer
Although plenty of methods have been proposed, a theoretical analysis of feature transform is still missing.
Deeply-supervised Knowledge Synergy
Convolutional Neural Networks (CNNs) have become deeper and more complicated compared with the pioneering AlexNet.
Efficient Semantic Scene Completion Network with Spatial Group Convolution
We introduce Spatial Group Convolution (SGC) for accelerating the computation of 3D dense prediction tasks.
Ranked #9 on
3D Semantic Scene Completion
on SemanticKITTI
Constrained R-CNN: A general image manipulation detection model
Finally, the coarse localization information guides the model to further learn the finer local features and segment out the tampered region.
Ranked #5 on
Image Manipulation Localization
on COVERAGE
LID 2020: The Learning from Imperfect Data Challenge Results
The purpose of the Learning from Imperfect Data (LID) workshop is to inspire and facilitate the research in developing novel approaches that would harness the imperfect data and improve the data-efficiency during training.
Federated Meta Learning Enhanced Acoustic Radio Cooperative Framework for Ocean of Things Underwater Acoustic Communications
In summary, the proposed ARC/FML for OoT is a promising scheme for information exchange across water and air.
PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds
Such a scheme has two limitations: 1) Storing and running several networks for different tasks are expensive for typical robotic platforms.
Pointly-supervised 3D Scene Parsing with Viewpoint Bottleneck
Semantic understanding of 3D point clouds is important for various robotics applications.
Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing
Multi-task indoor scene understanding is widely considered as an intriguing formulation, as the affinity of different tasks may lead to improved performance.
Ranked #51 on
Semantic Segmentation
on NYU Depth v2
Semi-supervised Implicit Scene Completion from Sparse LiDAR
Recent advances show that semi-supervised implicit representation learning can be achieved through physical constraints like Eikonal equations.
Transferable End-to-end Room Layout Estimation via Implicit Encoding
Here we propose an end-to-end method that directly predicts parametric layouts from an input panorama image.
High-Fidelity Human Avatars From a Single RGB Camera
To cope with the complexity of textures and generate photo-realistic results, we propose a reference-based neural rendering network and exploit a bottom-up sharpening-guided fine-tuning strategy to obtain detailed textures.
SNAKE: Shape-aware Neural 3D Keypoint Field
Detecting 3D keypoints from point clouds is important for shape reconstruction, while this work investigates the dual question: can shape reconstruction benefit 3D keypoint detection?
Model-Driven Based Deep Unfolding Equalizer for Underwater Acoustic OFDM Communications
Each layer of UDNet is designed according to the classical minimum mean square error (MMSE) equalizer.
Language-guided Semantic Style Transfer of 3D Indoor Scenes
We address the new problem of language-guided semantic style transfer of 3D indoor scenes.
Distance-Aware Occlusion Detection with Focused Attention
In this work, (1) we propose a novel three-decoder architecture as the infrastructure for focused attention; 2) we use the generalized intersection box prediction task to effectively guide our model to focus on occlusion-specific regions; 3) our model achieves a new state-of-the-art performance on distance-aware relationship detection.
Human-Object Interaction Detection
Relationship Detection
+1
SOM-Net: Unrolling the Subspace-based Optimization for Solving Full-wave Inverse Scattering Problems
The final output of the SOM-Net is the full predicted induced current, from which the scattered field and the permittivity image can also be deduced analytically.
LATITUDE: Robotic Global Localization with Truncated Dynamic Low-pass Filter in City-scale NeRF
In this paper, we present LATITUDE: Global Localization with Truncated Dynamic Low-pass Filter, which introduces a two-stage localization mechanism in city-scale NeRF.
City-scale Incremental Neural Mapping with Three-layer Sampling and Panoptic Representation
Neural implicit representations are drawing a lot of attention from the robotics community recently, as they are expressive, continuous and compact.
Planning Assembly Sequence with Graph Transformer
In this paper, we present a graph-transformer based framework for the ASP problem which is trained and demonstrated on a self-collected ASP database.
Understanding Embodied Reference with Touch-Line Transformer
Human studies have revealed that objects referred to or pointed to do not lie on the elbow-wrist line, a common misconception; instead, they lie on the so-called virtual touch line.
TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation
As such, we study the challenging problem of task oriented detection, which aims to find objects that best afford an action indicated by verbs like sit comfortably on.
VIBUS: Data-efficient 3D Scene Parsing with VIewpoint Bottleneck and Uncertainty-Spectrum Modeling
In the first stage, we perform self-supervised representation learning on unlabeled points with the proposed Viewpoint Bottleneck loss function.
SC-wLS: Towards Interpretable Feed-forward Camera Re-localization
Visual re-localization aims to recover camera poses in a known environment, which is vital for applications like robotics or augmented reality.
Self-Aligning Depth-regularized Radiance Fields for Asynchronous RGB-D Sequences
It has been shown that learning radiance fields with depth rendering and depth supervision can effectively promote the quality and convergence of view synthesis.
INT2: Interactive Trajectory Prediction at Intersections
One of the most challenging problems in motion forecasting is interactive trajectory prediction, whose goal is to jointly forecasts the future trajectories of interacting agents.
From Semi-supervised to Omni-supervised Room Layout Estimation Using Point Clouds
But adapting this scheme to the state-of-the-art (SOTA) solution for PC-based layout estimation is not straightforward.
ADAPT: Action-aware Driving Caption Transformer
To bridge the gap, we propose an end-to-end transformer-based architecture, ADAPT (Action-aware Driving cAPtion Transformer), which provides user-friendly natural language narrations and reasoning for each decision making step of autonomous vehicular control and action.
STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation
By fitting a bridge-shaped curve to the illumination map distribution, both regions are suppressed and two tasks are bridged naturally.
LODE: Locally Conditioned Eikonal Implicit Scene Completion from Sparse LiDAR
In this paper, we propose a novel Eikonal formulation that conditions the implicit representation on localized shape priors which function as dense boundary value constraints, and demonstrate it works on SemanticKITTI and SemanticPOSS.
DPF: Learning Dense Prediction Fields with Weak Supervision
We showcase the effectiveness of DPFs using two substantially different tasks: high-level semantic parsing and low-level intrinsic image decomposition.
STRAP: Structured Object Affordance Segmentation with Point Supervision
By label affinity, we refer to affordance segmentation as a multi-label prediction problem: A plate can be both holdable and containable.
Delving into Shape-aware Zero-shot Semantic Segmentation
Thanks to the impressive progress of large-scale vision-language pretraining, recent recognition models can classify arbitrary objects in a zero-shot and open-set manner, with a surprisingly high accuracy.
DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection
While this paradigm is natural for image-level or pixel-level prediction, adapting it to the detection problem is challenged by the issue of proposal matching.
Simulate Bumblebee and Extend It to Support LE Coded PHY in BLE version 5
Subsequently, we extend Bumblebee to support LE Coded PHY in BLE version 5 and conduct experiments to verify its performance.
On Pitfalls of Test-Time Adaptation
Test-Time Adaptation (TTA) has recently emerged as a promising approach for tackling the robustness challenge under distribution shifts.
Car-Studio: Learning Car Radiance Fields from Single-View and Endless In-the-wild Images
However, previous studies learned within a sequence of autonomous driving datasets, resulting in unsatisfactory blurring when rotating the car in the simulator.
MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving
We expect this modular design to boost academic progress and industrial deployment of NeRF-based autonomous driving simulation.
ECT: Fine-grained Edge Detection with Learned Cause Tokens
To address these three issues, we propose a two-stage transformer-based network sequentially predicting generic edges and fine-grained edges, which has a global receptive field thanks to the attention mechanism.
3D Implicit Transporter for Temporally Consistent Keypoint Discovery
To address this issue, the Transporter method was introduced for 2D data, which reconstructs the target frame from the source frame to incorporate both spatial and temporal information.
Learning Point-wise Abstaining Penalty for Point Cloud Anomaly Detection
We demonstrate that learning different abstaining penalties, apart from point-wise penalty, for different types of (synthesized) outliers can further improve the performance.
NeRRF: 3D Reconstruction and View Synthesis for Transparent and Specular Objects with Neural Refractive-Reflective Fields
In this paper, we introduce the refractive-reflective field.
PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection
Furthermore, we provide an open-source benchmark library, including dataset and baseline methods that cover 8 anomaly detection paradigms, to facilitate future research and application in this domain.
Ranked #2 on
Anomaly Detection
on PAD Dataset
Prototype-based HyperAdapter for Sample-Efficient Multi-task Tuning
Parameter-efficient fine-tuning (PEFT) has shown its effectiveness in adapting the pre-trained language models to downstream tasks while only updating a small number of parameters.
ASSIST: Interactive Scene Nodes for Scalable and Realistic Indoor Simulation
We present ASSIST, an object-wise neural radiance field as a panoptic representation for compositional and realistic simulation.
SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis
A lifelike talking head requires synchronized coordination of subject identity, lip movements, facial expressions, and head poses.
Active Learning for Abrupt Shifts Change-point Detection via Derivative-Aware Gaussian Processes
We investigate the effectiveness of DACD method in diverse scenarios and show it outperforms other active learning change-point detection approaches.
SlimmeRF: Slimmable Radiance Fields
To this end, we present SlimmeRF, a model that allows for instant test-time trade-offs between model size and accuracy through slimming, thus making the model simultaneously suitable for scenarios with different computing budgets.
Latency-aware Road Anomaly Segmentation in Videos: A Photorealistic Dataset and New Metrics
We believe the latter is valuable as it measures whether an anomaly segmentation algorithm can truly prevent a car from crashing in a temporally informed setting.
Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction
Drawing inspiration from the success of multimodal instruction tuning in visual tasks, we treat the visual-based RL task as a long-horizon vision task and construct a set of multimodal game instructions to incorporate instruction tuning into a decision transformer.
Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning
There is a consensus that instruction fine-tuning of LLMs requires high-quality data, but what are they?
Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agents
Furthermore, to unleash the potential of extensive high-quality digital assets, ChatSim employs a novel multi-camera lighting estimation method to achieve scene-consistent assets' rendering.
Adaptive Surface Normal Constraint for Geometric Estimation from Monocular Images
We introduce a novel approach to learn geometries such as depth and surface normal from images while incorporating geometric context.
Key Patch Proposer: Key Patches Contain Rich Information
In this paper, we introduce a novel algorithm named Key Patch Proposer (KPP) designed to select key patches in an image without additional training.
HyperMoE: Paying Attention to Unselected Experts in Mixture of Experts via Dynamic Transfer
The Mixture of Experts (MoE) for language models has been proven effective in augmenting the capacity of models by dynamically routing each input token to a specific subset of experts for processing.
MonoOcc: Digging into Monocular Semantic Occupancy Prediction
However, existing methods rely on a complex cascaded framework with relatively limited information to restore 3D scenes, including a dependency on supervision solely on the whole network's output, single-frame input, and the utilization of a small backbone.
FastMAC: Stochastic Spectral Sampling of Correspondence Graph
As such, the core of our method is the stochastic spectral sampling of correspondence graph.
SCP-Diff: Photo-Realistic Semantic Image Synthesis with Spatial-Categorical Joint Prior
Semantic image synthesis (SIS) shows good promises for sensor simulation.
P-MapNet: Far-seeing Map Generator Enhanced by both SDMap and HDMap Priors
On the other hand, we exploit a masked autoencoder to capture the prior distribution of HDMap, which can serve as a refinement module to mitigate occlusions and artifacts.
Large Language Models Powered Context-aware Motion Prediction
Traditional methods of motion forecasting primarily encode vector information of maps and historical trajectory data of traffic participants, lacking a comprehensive understanding of overall traffic semantics, which in turn affects the performance of prediction tasks.
Ultraman: Single Image 3D Human Reconstruction with Ultra Speed and Detail
In this paper, we propose a new method called \emph{Ultraman} for fast reconstruction of textured 3D human models from a single image.
SA-GS: Scale-Adaptive Gaussian Splatting for Training-Free Anti-Aliasing
This integration is actually a limiting case of super-sampling, which significantly improves anti-aliasing performance over vanilla Gaussian Splatting.
TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes
However, the exploration of 3D dense captioning in outdoor scenes is hindered by two major challenges: 1) the \textbf{domain gap} between indoor and outdoor scenes, such as dynamics and sparse visual inputs, makes it difficult to directly adapt existing indoor methods; 2) the \textbf{lack of data} with comprehensive box-caption pair annotations specifically tailored for outdoor scenes.
PreAfford: Universal Affordance-Based Pre-Grasping for Diverse Objects and Environments
Robotic manipulation of ungraspable objects with two-finger grippers presents significant challenges due to the paucity of graspable features, while traditional pre-grasping techniques, which rely on repositioning objects and leveraging external aids like table edges, lack the adaptability across object categories and scenes.
Idea-2-3D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal Inputs
The definition of an IDEA is the composition of multimodal inputs including text, image, and 3D models.
