Search Results for author:
Found 39 papers, 24 papers with code
InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior
3D Gaussians have recently emerged as an efficient representation for novel view synthesis.
SpatialTracker: Tracking Any 2D Pixels in 3D Space
Recovering dense and long-range pixel motion in videos is a challenging problem.
Bridging 3D Gaussian and Mesh for Freeview Video Rendering
To this end, we propose a novel approach, GauMesh, to bridge the 3D Gaussian and Mesh for modeling and rendering the dynamic scenes.
ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding
Transformers have been recently explored for 3D point cloud understanding with impressive progress achieved.
Ranked #5 on
Semantic Segmentation
on S3DIS Area5
Cross-level Attention with Overlapped Windows for Camouflaged Object Detection
In this paper, we propose an overlapped window cross-level attention (OWinCA) to achieve the low-level feature enhancement guided by the highest-level features.
Patched Line Segment Learning for Vector Road Mapping
In our experiments, we demonstrate how an effective representation of a road graph significantly enhances the performance of vector road mapping on established benchmarks, without requiring extensive modifications to the neural network architecture.
NEAT: Distilling 3D Wireframes from Neural Attraction Fields
Instead of leveraging matching-based solutions from 2D wireframes (or line segments) for 3D wireframe reconstruction as done in prior arts, we present NEAT, a rendering-distilling formulation using neural fields to represent 3D line segments with 2D observations, and bipartite matching for perceiving and distilling of a sparse set of 3D global junctions.
Depth and DOF Cues Make A Better Defocus Blur Detector
Our method proposes a depth feature distillation strategy to obtain depth knowledge from a pre-trained monocular depth estimation model and uses a DOF-edge loss to understand the relationship between DOF and depth.
Ranked #1 on
Defocus Blur Detection
on EBD
HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation
This work studies semantic segmentation under the domain generalization setting, where a model is trained only on the source domain and tested on the unseen target domain.
Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver
Motivated by a new and strong observation that this challenge can be remedied by a 3D-space local-grid search scheme in an ideal case, we propose a stage-wise approach, which combines the information flow from 2D-to-3D (3D bounding box proposal generation with a single 2D image) and 3D-to-2D (proposal verification by denoising with 3D-to-2D contexts) in a top-down manner.
Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs
This paper aims to develop an accurate 3D geometry representation of satellite images using satellite-ground image pairs.
Ranked #1 on
Cross-View Image-to-Image Translation
on CVACT
Cross-View Image-to-Image Translation
Generalizable Novel View Synthesis
+2
NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction
This paper studies the challenging two-view 3D reconstruction in a rigorous sparse-view configuration, which is suffering from insufficient correspondences in the input image pairs for camera pose estimation.
Level-S$^2$fM: Structure from Motion on Neural Level Set of Implicit Surfaces
This paper presents a neural incremental Structure-from-Motion (SfM) approach, Level-S$^2$fM, which estimates the camera poses and scene geometry from a set of uncalibrated images by learning coordinate MLPs for the implicit surfaces and the radiance fields from the established keypoint correspondences.
Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning
This article presents Holistically-Attracted Wireframe Parsing (HAWP), a method for geometric analysis of 2D images containing wireframes formed by line segments and junctions.
HoW-3D: Holistic 3D Wireframe Perception from a Single Image
This paper studies the problem of holistic 3D wireframe perception (HoW-3D), a new task of perceiving both the visible 3D wireframes and the invisible ones from single-view 2D images.
Accurate Polygonal Mapping of Buildings in Satellite Imagery
We addressed such an issue by exploiting the hierarchical supervision (of bottom-level vertices, mid-level line segments and the high-level regional masks) and proposed a novel interaction mechanism of feature embedding sourced from different levels of supervision signals to obtain reversible building masks for polygonal mapping of buildings.
Revisiting Document Image Dewarping by Grid Regularization
This paper addresses the problem of document image dewarping, which aims at eliminating the geometric distortion in document images for document digitization.
Ranked #3 on
Local Distortion
on DocUNet
Partial Wasserstein Adversarial Network for Non-rigid Point Set Registration
To handle large point sets, we propose a scalable PDM algorithm by utilizing the efficient partial Wasserstein-1 (PW) discrepancy.
Decoupling Zero-Shot Semantic Segmentation
2) a zero-shot classification task on segments.
Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection
It presents the MonoCon method which learns Monocular Contexts, as auxiliary tasks in training, to help monocular 3D object detection.
Ranked #5 on
Monocular 3D Object Detection
on KITTI Cars Moderate
Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimation
This paper studies the problem of multi-person pose estimation in a bottom-up fashion.
Parsing Table Structures in the Wild
In contrast to existing studies that mainly focus on parsing well-aligned tabular images with simple layouts from scanned PDF documents, we aim to establish a practical table structure parsing system for real-world scenarios where tabular input images are taken or scanned with severe deformation, bending or occlusions.
LUAI Challenge 2021 on Learning to Understand Aerial Images
This report summarizes the results of Learning to Understand Aerial Images (LUAI) 2021 challenge held on ICCV 2021, which focuses on object detection and semantic segmentation in aerial images.
PlaneTR: Structure-Guided Transformers for 3D Plane Recovery
This paper presents a neural network built upon Transformers, namely PlaneTR, to simultaneously detect and reconstruct planes from a single image.
ReDet: A Rotation-equivariant Detector for Aerial Object Detection
More precisely, we incorporate rotation-equivariant networks into the detector to extract rotation-equivariant features, which can accurately predict the orientation and lead to a huge reduction of model size.
Ranked #18 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
Deep Graph Matching under Quadratic Constraint
Recently, deep learning based methods have demonstrated promising results on the graph matching problem, by relying on the descriptive capability of deep features extracted on graph nodes.
Ranked #7 on
Graph Matching
on Willow Object Class
Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges
In this paper, we present a large-scale Dataset of Object deTection in Aerial images (DOTA) and comprehensive baselines for ODAI.
Unmixing Convolutional Features for Crisp Edge Detection
This paper presents a context-aware tracing strategy (CATS) for crisp edge detection with deep edge detectors, based on an observation that the localization ambiguity of deep edge detectors is mainly caused by the mixing phenomenon of convolutional neural networks: feature mixing in edge classification and side mixing during fusing side predictions.
Ranked #2 on
Edge Detection
on MDBD
Zero-Assignment Constraint for Graph Matching with Outliers
Graph matching (GM), as a longstanding problem in computer vision and pattern recognition, still suffers from numerous cluttered outliers in practical applications.
Fisheye Distortion Rectification from Deep Straight Lines
This paper presents a novel line-aware rectification network (LaRecNet) to address the problem of fisheye distortion rectification based on the classical observation that straight lines in 3D space should be still straight in image planes.
Holistically-Attracted Wireframe Parsing
For computing line segment proposals, a novel exact dual representation is proposed which exploits a parsimonious geometric reparameterization for line segments and forms a holistic 4-dimensional attraction field map for an input image.
Ranked #4 on
Line Segment Detection
on York Urban Dataset
Learning Regional Attraction for Line Segment Detection
Given a line segment map, the proposed regional attraction first establishes the relationship between line segments and regions in the image lattice.
Learning to Calibrate Straight Lines for Fisheye Image Rectification
This paper presents a new deep-learning based method to simultaneously calibrate the intrinsic parameters of fisheye lens and rectify the distorted images.
A Functional Representation for Graph Matching
In this paper, we present a functional representation for graph matching (FRGM) that aims to provide more geometric insights on the problem and reduce the space and time complexities of corresponding algorithms.
Learning Attraction Field Representation for Robust Line Segment Detection
In experiments, our method is tested on the WireFrame dataset and the YorkUrban dataset with state-of-the-art performance obtained.
Learning RoI Transformer for Detecting Oriented Objects in Aerial Images
Especially when detecting densely packed objects in aerial images, methods relying on horizontal proposals for common object detection often introduce mismatches between the Region of Interests (RoIs) and objects.
Ranked #48 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
GeoSay: A Geometric Saliency for Extracting Buildings in Remote Sensing Images
More precisely, given an image, the geometric saliency is derived from a mid-level geometric representations based on meaningful junctions that can locally describe geometrical structures of images.
Adaptively Transforming Graph Matching
Due to an efficient Frank-Wolfe method-based optimization strategy, we can handle graphs with hundreds and thousands of nodes within an acceptable amount of time.
Anisotropic-Scale Junction Detection and Matching for Indoor Images
This paper presents a novel approach to junction detection and characterization that exploits the locally anisotropic geometries of a junction and estimates the scales of these geometries using an \emph{a contrario} model.
