Search Results for author:
Found 34 papers, 11 papers with code
Online,Target-Free LiDAR-Camera Extrinsic Calibration via Cross-Modal Mask Matching
The cornerstone of our framework and toolbox is the cross-modal mask matching (C3M) algorithm, developed based on a state-of-the-art (SoTA) LVM and capable of generating sufficient and reliable matches.
Vision-and-Language Navigation via Causal Learning
In the pursuit of robust and generalizable environment perception and language understanding, the ubiquitous challenge of dataset bias continues to plague vision-and-language navigation (VLN) agents, hindering their performance in unseen environments.
Playing to Vision Foundation Model's Strengths in Stereo Matching
We believe this new paradigm will pave the way for the next generation of stereo matching networks.
HAPNet: Toward Superior RGB-Thermal Scene Parsing via Hybrid, Asymmetric, and Progressive Heterogeneous Feature Fusion
In this study, we take one step toward this new research area by exploring a feasible strategy to fully exploit VFM features for RGB-thermal scene parsing.
Ranked #1 on
Thermal Image Segmentation
on KP day-night
LIX: Implicitly Infusing Spatial Geometric Prior Knowledge into Visual Semantic Segmentation for Autonomous Driving
We introduce the Learning to Infuse "X" (LIX) framework, with novel contributions in both logit distillation and feature distillation aspects.
Causality-based Cross-Modal Representation Learning for Vision-and-Language Navigation
Vision-and-Language Navigation (VLN) has gained significant research interest in recent years due to its potential applications in real-world scenarios.
SNE-RoadSegV2: Advancing Heterogeneous Feature Fusion and Fallibility Awareness for Freespace Detection
Feature-fusion networks with duplex encoders have proven to be an effective technique to solve the freespace detection problem.
CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledge
Inspired by this motivation, we propose CLIPose, a novel 6D pose framework that employs the pre-trained vision-language model to develop better learning of object category information, which can fully leverage abundant semantic knowledge in image and text modalities.
S$^3$M-Net: Joint Learning of Semantic Segmentation and Stereo Matching for Autonomous Driving
Hence, in this article, we introduce S$^3$M-Net, a novel joint learning framework developed to perform semantic segmentation and stereo matching simultaneously.
PICNN: A Pathway towards Interpretable Convolutional Neural Networks
Experimental results have demonstrated that our method PICNN (the combination of standard CNNs with our proposed pathway) exhibits greater interpretability than standard CNNs while achieving higher or comparable discrimination power.
Three-Filters-to-Normal+: Revisiting Discontinuity Discrimination in Depth-to-Normal Translation
This article introduces three-filters-to-normal+ (3F2N+), an extension of our previous work three-filters-to-normal (3F2N), with a specific focus on incorporating discontinuity discrimination capability into surface normal estimators (SNEs).
TransPose: 6D Object Pose Estimation with Geometry-Aware Transformer
To improve robustness to occlusion, we adopt Transformer to perform the exchange of global information, making each local feature contains global information.
InstructDET: Diversifying Referring Object Detection with Generalized Instructions
In order to encompass common detection expressions, we involve emerging vision-language model (VLM) and large language model (LLM) to generate instructions guided by text prompts and object bbxs, as the generalizations of foundation models are effective to produce human-like expressions (e. g., describing object property, category, and relationship).
Dive Deeper into Rectifying Homography for Stereo Camera Online Self-Calibration
Instead, we introduce four new evaluation metrics to quantify the robustness and accuracy of extrinsic parameter estimation, applicable to both single-pair and multi-pair cases.
RoadFormer: Duplex Transformer for RGB-Normal Semantic Road Scene Parsing
Additionally, we release SYN-UDTIRI, the first large-scale road scene parsing dataset that contains over 10, 407 RGB images, dense depth images, and the corresponding pixel-level annotations for both freespace and road defects of different shapes and sizes.
Fine-Grained Spatiotemporal Motion Alignment for Contrastive Video Representation Learning
As the most essential property in a video, motion information is critical to a robust and generalized video representation.
E3CM: Epipolar-Constrained Cascade Correspondence Matching
Accurate and robust correspondence matching is of utmost importance for various 3D computer vision tasks.
Freespace Optical Flow Modeling for Automated Driving
Additionally, our proposed freespace optical flow model boasts a diverse array of applications within the realm of automated driving, providing a geometric constraint in freespace detection, vehicle localization, and more.
LoSh: Long-Short Text Joint Prediction Network for Referring Video Object Segmentation
Referring video object segmentation (RVOS) aims to segment the target instance referred by a given text expression in a video clip.
Ranked #12 on
Referring Expression Segmentation
on Refer-YouTube-VOS (2021 public validation)
(using extra training data)
Referring Expression Segmentation
Referring Video Object Segmentation
+2
PASTS: Progress-Aware Spatio-Temporal Transformer Speaker For Vision-and-Language Navigation
The experimental results demonstrate that PASTS outperforms all existing speaker models and successfully improves the performance of previous VLN models, achieving state-of-the-art performance on the standard Room-to-Room (R2R) dataset.
A Dual Semantic-Aware Recurrent Global-Adaptive Network For Vision-and-Language Navigation
Vision-and-Language Navigation (VLN) is a realistic but challenging task that requires an agent to locate the target region using verbal and visual cues.
D2NT: A High-Performing Depth-to-Normal Translator
Surface normal holds significant importance in visual environmental perception, serving as a source of rich geometric information.
UDTIRI: An Online Open-Source Intelligent Road Inspection Benchmark Suite
To foster advancements in this burgeoning field, we have launched an online open-source benchmark suite, referred to as UDTIRI.
MLANet: Multi-Level Attention Network with Sub-instruction for Continuous Vision-and-Language Navigation
For a better performance in continuous VLN, we design a multi-level instruction understanding procedure and propose a novel model, Multi-Level Attention Network (MLANet).
Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigation
We propose a meta-ability decoupling (MAD) paradigm, which brings together various object navigation methods in an architecture system, allowing them to mutually enhance each other and evolve together.
SIM2E: Benchmarking the Group Equivariant Capability of Correspondence Matching Algorithms
The experimental results demonstrate the importance of group equivariant algorithms for correspondence matching on various sim(2) transformation conditions.
Search for or Navigate to? Dual Adaptive Thinking for Object Navigation
After seeing the target, we remember the target location and navigate to.
Multi-scale Wasserstein Shortest-path Graph Kernels for Graph Classification
To mitigate the two challenges, we propose a novel graph kernel called the Multi-scale Wasserstein Shortest-Path graph kernel (MWSP), at the heart of which is the multi-scale shortest-path node feature map, of which each element denotes the number of occurrences of a shortest path around a node.
Unbiased Directed Object Attention Graph for Object Navigation
Thus, in this paper, we propose a directed object attention (DOA) graph to guide the agent in explicitly learning the attention relationships between objects, thereby reducing the object attention bias.
Hyperspectral Imaging for cherry tomato
Cherry tomato (Solanum Lycopersicum) is popular with consumers over the world due to its special flavor.
Human-vehicle Cooperative Visual Perception for Autonomous Driving under Complex Road and Traffic Scenarios
To enhance the visual perception capability of human-vehicle cooperative driving, this paper proposed a cooperative visual perception model.
Revisiting Perspective Information for Efficient Crowd Counting
Modern crowd counting methods employ deep neural networks to estimate crowd counts via crowd density regressions.
Novel View Synthesis for Large-scale Scene using Adversarial Loss
Novel view synthesis aims to synthesize new images from different viewpoints of given images.
Scale Recovery for Monocular Visual Odometry Using Depth Estimated With Deep Convolutional Neural Fields
Normally, road plane and camera height are specified as reference to recover the scale.
