Search Results for author:
Found 24 papers, 20 papers with code
Out-of-Distribution Semantic Occupancy Prediction
We introduce OccOoD, a novel framework integrating OoD detection into 3D semantic occupancy prediction, with Voxel-BEV Progressive Fusion (VBPF) leveraging an RWKV-based branch to enhance OoD detection via geometry-semantic fusion.
Panoramic Out-of-Distribution Segmentation
To address these issues, we introduce a new task, Panoramic Out-of-distribution Segmentation (PanOoS), achieving OoS for panoramas.
HierDAMap: Towards Universal Domain Adaptive BEV Mapping via Hierarchical Perspective Priors
However, research on unsupervised domain adaptation for BEV mapping remains limited and cannot perfectly accommodate all BEV mapping tasks.
Resource-Efficient Affordance Grounding with Complementary Depth and Semantic Prompts
This information is rich and multimodal in nature.
Unveiling the Potential of Segment Anything Model 2 for RGB-Thermal Semantic Segmentation with Language Guidance
The perception capability of robotic systems relies on the richness of the dataset.
Ranked #1 on
Thermal Image Segmentation
on PST900
TS-CGNet: Temporal-Spatial Fusion Meets Centerline-Guided Diffusion for BEV Mapping
Specifically, this framework is decoupled into three parts: Local mapping system involves the initial generation of semantic maps using purely visual information; The Temporal-Spatial Aligner Module (TSAM) integrates historical information into mapping generation by applying transformation matrices; The Centerline-Guided Diffusion Model (CGDM) is a prediction module based on the diffusion model.
One-Shot Affordance Grounding of Deformable Objects in Egocentric Organizing Scenes
Deformable object manipulation in robotics presents significant challenges due to uncertainties in component properties, diverse configurations, visual interference, and ambiguous prompts.
Multi-Keypoint Affordance Representation for Functional Dexterous Grasping
Additionally, we present a Keypoint-based Grasp matrix Transformation (KGT) method, ensuring spatial consistency between hand keypoints and object contact points, thus providing a direct link between visual perception and dexterous grasping actions.
GenMapping: Unleashing the Potential of Inverse Perspective Mapping for Robust Online HD Map Construction
The framework is established with a triadic synergy architecture, including principal and dual auxiliary branches.
Learning Granularity-Aware Affordances from Human-Object Interaction for Tool-Based Functional Grasping in Dexterous Robotics
To address this, we propose a granularity-aware affordance feature extraction method for locating functional affordance areas and predicting dexterous coarse gestures.
DTCLMapper: Dual Temporal Consistent Learning for Vectorized HD Map Construction
In this paper, we revisit the temporal fusion of vectorized HD maps, focusing on temporal instance consistency and temporal map consistency learning.
MambaMOS: LiDAR-based 3D Moving Object Segmentation with Motion-aware State Space Model
In this paper, we propose a novel LiDAR-based 3D Moving Object Segmentation with Motion-aware State Space Model, termed MambaMOS.
EchoTrack: Auditory Referring Multi-Object Tracking for Autonomous Driving
This paper introduces the task of Auditory Referring Multi-Object Tracking (AR-MOT), which dynamically tracks specific objects in a video sequence based on audio expressions and appears as a challenging problem in autonomous driving.
LF Tracy: A Unified Single-Pipeline Approach for Salient Object Detection in Light Field Cameras
Research on inter-network data connectivity is scant.
Zero-Shot Structure-Preserving Diffusion Model for High Dynamic Range Tone Mapping
However obtaining paired HDR and high-quality LDR images is difficult posing a challenge to deep learning based tone mapping methods.
S$^3$-MonoDETR: Supervised Shape&Scale-perceptive Deformable Transformer for Monocular 3D Object Detection
These methods typically use visual and depth representations to generate query points on objects, whose quality plays a decisive role in the detection accuracy.
Expression Prompt Collaboration Transformer for Universal Referring Video Object Segmentation
Next, we propose an Expression Alignment (EA) mechanism for audio and text.
Contrast-augmented Diffusion Model with Fine-grained Sequence Alignment for Markup-to-Image Generation
The recently rising markup-to-image generation poses greater challenges as compared to natural image generation, due to its low tolerance for errors as well as the complex sequence and context correlations between markup and rendered image.
PVPUFormer: Probabilistic Visual Prompt Unified Transformer for Interactive Image Segmentation
To tackle this problem, this paper proposes a simple yet effective Probabilistic Visual Prompt Unified Transformer (PVPUFormer) for interactive image segmentation, which allows users to flexibly input diverse visual prompts with the probabilistic prompt encoding and feature post-processing to excavate sufficient and robust prompt features for performance boosting.
SSD-MonoDETR: Supervised Scale-aware Deformable Transformer for Monocular 3D Object Detection
To tackle this problem, this paper proposes a novel "Supervised Scale-aware Deformable Attention" (SSDA) for monocular 3D object detection.
AdaptiveClick: Clicks-aware Transformer with Adaptive Focal Loss for Interactive Image Segmentation
Interactive Image Segmentation (IIS) has emerged as a promising technique for decreasing annotation time.
Bi-Mapper: Holistic BEV Semantic Mapping for Autonomous Driving
At the same time, an Across-Space Loss (ASL) is designed to mitigate the negative impact of geometric distortions.
Energy-efficient Dense DNN Acceleration with Signed Bit-slice Architecture
This paper proposes energy-efficient signed bit-slice architecture which accelerates both high-precision and dense DNNs by exploiting a large number of zero values of signed bit-slices.
STURE: Spatial-Temporal Mutual Representation Learning for Robust Data Association in Online Multi-Object Tracking
The feature difference between current candidate detections and historical tracklets makes the object association much harder.
