Search Results for author:
Found 92 papers, 54 papers with code
Relative Pose Estimation of Calibrated Cameras with Known SE(3) Invariants
In this paper, we present a complete comprehensive study of the relative pose estimation problem for a calibrated camera constrained by known $\mathrm{SE}(3)$ invariant, which involves 5 minimal problems in total.
Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering
3D Gaussians have recently emerged as a highly efficient representation for 3D reconstruction and rendering.
SCALAR-NeRF: SCAlable LARge-scale Neural Radiance Fields for Scene Reconstruction
We enhance the overlapping regions across different blocks by scaling up the bounding boxes of each local block.
Animate124: Animating One Image to 4D Dynamic Scene
We introduce Animate124 (Animate-one-image-to-4D), the first work to animate a single in-the-wild image into 3D video through textual motion descriptions, an underexplored problem with significant applications.
Rethink Cross-Modal Fusion in Weakly-Supervised Audio-Visual Video Parsing
Existing works on weakly-supervised audio-visual video parsing adopt hybrid attention network (HAN) as the multi-modal embedding to capture the cross-modal context.
Optimizing the Placement of Roadside LiDARs for Autonomous Driving
We define perceptual gain as the increased perceptual capability when a new LiDAR is placed.
Generalized Few-Shot Point Cloud Segmentation Via Geometric Words
Existing fully-supervised point cloud segmentation methods suffer in the dynamic testing environment with emerging new classes.
Towards Robust Few-shot Point Cloud Semantic Segmentation
Few-shot point cloud semantic segmentation aims to train a model to quickly adapt to new unseen classes with only a handful of support set samples.
Robust e-NeRF: NeRF from Sparse & Noisy Events under Non-Uniform Motion
Such promise and potential of event cameras and NeRF inspired recent works to investigate on the reconstruction of NeRF from moving event cameras.
GHuNeRF: Generalizable Human NeRF from a Monocular Video
In view of these limitations, we propose GHuNeRF to learn a generalizable human NeRF model from a monocular video of the human performer.
GeT: Generative Target Structure Debiasing for Domain Adaptation
Despite the competitive performance, these pseudo labeling methods rely heavily on the source domain to generate pseudo labels for the target domain and therefore still suffer considerably from source data bias.
DReg-NeRF: Deep Registration for Neural Radiance Fields
Although Neural Radiance Fields (NeRF) is popular in the computer vision community recently, registering multiple NeRFs has yet to gain much attention.
Weakly-supervised 3D Pose Transfer with Keypoints
The main challenges of 3D pose transfer are: 1) Lack of paired training data with different characters performing the same pose; 2) Disentangling pose and shape information from the target mesh; 3) Difficulty in applying to meshes with different topologies.
NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF
Second, our Repulsive UDF is a novel alternative to the occupancy field used in MCC, significantly improving the quality of 3D object reconstruction.
OD-NeRF: Efficient Training of On-the-Fly Dynamic Neural Radiance Fields
Dynamic neural radiance fields (dynamic NeRFs) have demonstrated impressive results in novel view synthesis on 3D dynamic scenes.
Boosting Long-tailed Object Detection via Step-wise Learning on Smooth-tail Data
Real-world data tends to follow a long-tailed distribution, where the class imbalance results in dominance of the head classes during training.
ConsistentNeRF: Enhancing Neural Radiance Fields with 3D Consistency for Sparse View Synthesis
In this paper, we propose ConsistentNeRF, a method that leverages depth information to regularize both multi-view and single-view 3D consistency among pixels.
Make-A-Protagonist: Generic Video Editing with An Ensemble of Experts
The text-driven image and video diffusion models have achieved unprecedented success in generating realistic and diverse content.
Overcoming the Trade-off Between Accuracy and Plausibility in 3D Hand Shape Reconstruction
However, the reconstructed meshes are prone to artifacts and do not appear as plausible hand shapes.
ScarceNet: Animal Pose Estimation with Scarce Annotations
To this end, we propose the ScarceNet, a pseudo label-based approach to generate artificial labels for the unlabeled images.
NeRF-DS: Neural Radiance Fields for Dynamic Specular Objects
We evaluate our model based on the novel view synthesis quality with a self-collected dataset of different moving specular objects in realistic environments.
DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields
Recent works such as BARF and GARF can bundle adjust camera poses with neural radiance fields (NeRF) which is based on coordinate-MLPs.
ContraNeRF: Generalizable Neural Radiance Fields for Synthetic-to-real Novel View Synthesis via Contrastive Learning
In this work, we first investigate the effects of synthetic data in synthetic-to-real novel view synthesis and surprisingly observe that models trained with synthetic data tend to produce sharper but less accurate volume densities.
AdaSfM: From Coarse Global to Fine Incremental Adaptive Structure from Motion
Despite the impressive results achieved by many existing Structure from Motion (SfM) approaches, there is still a need to improve the robustness, accuracy, and efficiency on large-scale scenes with many outlier matches and sparse view graphs.
Unsupervised Feature Representation Learning for Domain-generalized Cross-domain Image Retrieval
This limitation motivates us to present the first attempt at domain-generalized unsupervised cross-domain image retrieval (DG-UCDIR) aiming at facilitating image retrieval between any two unseen domains in an unsupervised way.
Incremental Neural Implicit Representation with Uncertainty-Filtered Knowledge Distillation
In view of this, we explore the task of incremental learning for NIRs in this work.
Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization
Furthermore, we present a novel style hallucination module (SHM) to generate style-diversified samples that are essential to consistency learning.
Synthetic-to-Real Domain Generalized Semantic Segmentation for 3D Indoor Point Clouds
In addition, we augment the point patterns of the source data and introduce non-parametric multi-prototypes to ameliorate the intra-class variance enlarged by the augmented point patterns.
Motion and Context-Aware Audio-Visual Conditioned Video Prediction
The existing state-of-the-art method for audio-visual conditioned video prediction uses the latent codes of the audio-visual frames from a multimodal stochastic network and a frame encoder to predict the next visual frame.
Open World DETR: Transformer based Open World Object Detection
Open world object detection aims at detecting objects that are absent in the object classes of the training data as unknown objects without explicit supervision.
Minimal Neural Atlas: Parameterizing Complex Surfaces with Minimal Charts and Distortion
Thus, our representation can learn a minimal atlas of 3 charts with distortion-minimal parameterization for surfaces of arbitrary topology, including closed and open surfaces with arbitrary connected components.
Feature Representation Learning for Unsupervised Cross-domain Image Retrieval
Current supervised cross-domain image retrieval methods can achieve excellent performance.
Rethinking IoU-based Optimization for Single-stage 3D Object Detection
Since Intersection-over-Union (IoU) based optimization maintains the consistency of the final IoU prediction metric and losses, it has been widely used in both regression and classification branches of single-stage 2D object detectors.
Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation
Experiments on two synthetic-to-real semantic segmentation benchmarks demonstrate that AdvStyle can significantly improve the model performance on unseen real domains and show that we can achieve the state of the art.
CA-UDA: Class-Aware Unsupervised Domain Adaptation with Optimal Assignment and Pseudo-Label Refinement
However, source domain bias that deteriorates the pseudo-labels can still exist since the shared network of the source and target domains are typically used for the pseudo-label selections.
VRAG: Region Attention Graphs for Content-Based Video Retrieval
In this paper, we introduce Video Region Attention Graph Networks (VRAG) that improves the state-of-the-art of video-level methods.
Ranked #3 on
Video Retrieval
on FIVR-200K
Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning
Incremental few-shot object detection aims at detecting novel classes without forgetting knowledge of the base classes with only a few labeled training data from the novel classes.
Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation
Furthermore, we present a novel style hallucination module (SHM) to generate style-diversified samples that are essential to consistency learning.
REGTR: End-to-end Point Cloud Correspondences with Transformers
Despite recent success in incorporating learning into point cloud registration, many works focus on learning feature descriptors and continue to rely on nearest-neighbor feature matching and outlier filtering through RANSAC to obtain the final set of correspondences for pose estimation.
Weakly Supervised Learning of Keypoints for 6D Object Pose Estimation
Specifically, we assign a set of arbitrarily chosen 3D keypoints to represent each unknown target 3D object and learn a network to detect their 2D projections that comply with the relative camera viewpoints.
Static-Dynamic Co-Teaching for Class-Incremental 3D Object Detection
Deep learning-based approaches have shown remarkable performance in the 3D object detection task.
Novel Class Discovery in Semantic Segmentation
We introduce a new setting of Novel Class Discovery in Semantic Segmentation (NCDSS), which aims at segmenting unlabeled images containing new classes given prior knowledge from a labeled set of disjoint classes.
Coarse-to-fine Animal Pose and Shape Estimation
Most existing animal pose and shape estimation approaches reconstruct animal meshes with a parametric SMAL model.
Learning Iterative Robust Transformation Synchronization
Transformation Synchronization is the problem of recovering absolute transformations from a given set of pairwise relative motions.
Bridging Non Co-occurrence with Unlabeled In-the-wild Data for Incremental Object Detection
In view of this limitation, we consider a more practical setting of complete absence of co-occurrence of the base and novel classes for the object detection task.
Voxel-based Network for Shape Completion by Leveraging Edge Generation
Deep learning technique has yielded significant improvements in point cloud completion with the aim of completing missing object shapes from partial inputs.
Source-Free Open Compound Domain Adaptation in Semantic Segmentation
Second, CPSS can reduce the influence of noisy pseudo-labels and also avoid the model overfitting to the target domain during self-supervised learning, consistently boosting the performance on the target and open domains.
FILTRA: Rethinking Steerable CNN by Filter Transform
It has been an intuitive and widely used technique to construct a steerable filter by augmenting a filter with its transformed copies in the past decades, which is named as filter transform in this paper.
DeepI2P: Image-to-Point Cloud Registration via Deep Classification
This paper presents DeepI2P: a novel approach for cross-modality registration between an image and a point cloud.
Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo
Existing approaches for multi-view multi-person 3D pose estimation explicitly establish cross-view correspondences to group 2D pose detections from multiple camera views and solve for the 3D pose estimation for each person.
Ranked #2 on
3D Multi-Person Pose Estimation
on Campus
Learning Spatial Context with Graph Neural Network for Multi-Person Pose Grouping
More specifically, we design a Geometry-aware Association GNN that utilizes spatial information of the keypoints and learns local affinity from the global context.
From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation
Existing works circumvent this problem with pseudo labels generated from data of other easily accessible domains such as synthetic data.
MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis
In this paper, we propose MINE to perform novel view synthesis and depth estimation via dense 3D reconstruction from a single image.
City-scale Scene Change Detection using Point Clouds
We propose a method for detecting structural changes in a city using images captured from vehicular mounted cameras over traversals at two different times.
Cascaded Refinement Network for Point Cloud Completion with Self-supervision
This is to mitigate the dependence of existing approaches on large amounts of ground truth training data that are often difficult to obtain in real-world applications.
Weakly Supervised Generative Network for Multiple 3D Human Pose Hypotheses
In this paper, we propose a weakly supervised deep generative network to address the inverse problem and circumvent the need for ground truth 2D-to-3D correspondences.
Point Cloud Completion by Learning Shape Priors
Then we learn a mapping to transfer the point features from partial points to that of the complete points by optimizing feature alignment losses.
Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry
In this paper, we depart from the multi-person 3D pose estimation formulation, and instead reformulate it as crowd pose estimation.
Ranked #12 on
3D Multi-Person Pose Estimation
on Panoptic
(using extra training data)
3D Multi-Person Human Pose Estimation
3D Multi-Person Pose Estimation
+2
HDNet: Human Depth Estimation for Multi-Person Camera-Space Localization
Current works on multi-person 3D pose estimation mainly focus on the estimation of the 3D joint locations relative to the root joint and ignore the absolute locations of each pose.
3D Multi-Person Pose Estimation (absolute)
3D Multi-Person Pose Estimation (root-relative)
+3
Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation
We present a novel learning approach to recover the 6D poses and sizes of unseen object instances from an RGB-D image.
Relative Pose Estimation of Calibrated Cameras with Known $\mathrm{SE}(3)$ Invariants
In this paper, we present a complete comprehensive study of the relative pose estimation problem for a calibrated camera constrained by known $\mathrm{SE}(3)$ invariant, which involves 5 minimal problems in total.
Few-shot 3D Point Cloud Semantic Segmentation
These fully supervised approaches heavily rely on large amounts of labeled training data that are difficult to obtain and cannot segment new classes after training.
Few-shot 3D Point Cloud Semantic Segmentation
Segmentation
+1
Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labels
Point cloud analysis has received much attention recently; and segmentation is one of the most important tasks.
Cascaded Refinement Network for Point Cloud Completion
Point clouds are often sparse and incomplete.
RPM-Net: Robust Point Matching using Learned Features
The hard assignments of closest point correspondences based on spatial distances are sensitive to the initial rigid transformation and noisy/outlier points, which often cause ICP to converge to wrong local minima.
Robust 6D Object Pose Estimation by Learning RGB-D Features
Accurate 6D object pose estimation is fundamental to robotic manipulation and grasping.
SESS: Self-Ensembling Semi-Supervised 3D Object Detection
The performance of existing point cloud-based 3D object detection methods heavily relies on large-scale high-quality 3D annotations.
Identifying through Flows for Recovering Latent Representations
Yet, most deep generative models do not address the question of identifiability, and thus fail to deliver on the promise of the recovery of the true latent sources that generate the observations.
Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimation
Although existing CNN-based temporal frameworks attempt to address the sensitivity and drift problems by concurrently processing all input frames in the sequence, the existing state-of-the-art CNN-based framework is limited to 3d pose estimation of a single frame from a sequential input.
Ranked #15 on
Pose Estimation
on Leeds Sports Poses
PS^2-Net: A Locally and Globally Aware Network for Point-Based Semantic Segmentation
In this paper, we present the PS^2-Net -- a locally and globally aware deep learning framework for semantic segmentation on 3D scene-level point clouds.
Degeneracy in Self-Calibration Revisited and a Deep Learning Solution for Uncalibrated SLAM
Self-calibration of camera intrinsics and radial distortion has a long history of research in the computer vision community.
PointAtrousGraph: Deep Hierarchical Encoder-Decoder with Point Atrous Convolution for Unorganized 3D Points
Motivated by the success of encoding multi-scale contextual information for image analysis, we propose our PointAtrousGraph (PAG) - a deep permutation-invariant hierarchical encoder-decoder for efficiently exploiting multi-scale edge features in point clouds.
Robust Point Cloud Based Reconstruction of Large-Scale Outdoor Scenes
Furthermore, we show that by using a Gaussian-Uniform mixture model, our approach degenerates to the formulation of a state-of-the-art approach for robust indoor reconstruction.
Transferable Semi-supervised 3D Object Detection from RGB-D Data
We investigate the direction of training a 3D object detector for new object classes from only 2D bounding box labels of these new classes, while simultaneously transferring information from 3D bounding box labels of the existing classes.
2D3D-MatchNet: Learning to Match Keypoints Across 2D Image and 3D Point Cloud
Large-scale point cloud generated from 3D sensors is more accurate than its image-based counterpart.
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network
We argue that 3D human pose estimation from a monocular input is an inverse problem where multiple feasible solutions can exist.
Monocular 3D Human Pose Estimation
Multi-Hypotheses 3D Human Pose Estimation
Discrete Rotation Equivariance for Point Cloud Recognition
In this paper, we propose a deep learning architecture that achieves discrete $\mathbf{SO}(2)$/$\mathbf{SO}(3)$ rotation equivariance for point cloud recognition.
USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds
In this paper, we propose the USIP detector: an Unsupervised Stable Interest Point detector that can detect highly repeatable and accurately localized keypoints from 3D point clouds under arbitrary transformations without the need for any ground truth training data.
Rolling-Shutter-Aware Differential SfM and Image Rectification
We demonstrate that the dense depth maps recovered from the relative pose of the RS camera can be used in a RS-aware warping for image rectification to recover high-quality Global Shutter (GS) images.
Image-Based Geo-Localization Using Satellite Imagery
The problem of localization on a geo-referenced satellite map given a query ground view image is useful yet remains challenging due to the drastic change in viewpoint.
Baseline Desensitizing In Translation Averaging
Many existing translation averaging algorithms are either sensitive to disparate camera baselines and have to rely on extensive preprocessing to improve the observed Epipolar Geometry graph, or if they are robust against disparate camera baselines, require complicated optimization to minimize the highly nonlinear angular error objective.
3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration
In this paper, we propose the 3DFeat-Net which learns both 3D feature detector and descriptor for point cloud matching using weak supervision.
Ranked #6 on
Point Cloud Registration
on KITTI
CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization
The problem of localization on a geo-referenced aerial/satellite map given a query ground view image remains challenging due to the drastic change in viewpoint that causes traditional image descriptors based matching to fail.
Solving the Perspective-2-Point Problem for Flying-Camera Photo Composition
The user, instead of holding a camera in hand and manually searching for a viewpoint, will interact directly with image contents in the viewfinder through simple gestures, and the flying camera will achieve the desired viewpoint through the autonomous flying capability of the drone.
Convolutional Sequence to Sequence Model for Human Dynamics
Human motion modeling is a classic problem in computer vision and graphics.
PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition
This is largely due to the difficulty in extracting local feature descriptors from a point cloud that can subsequently be encoded into a global descriptor for the retrieval task.
Ranked #10 on
Visual Localization
on Oxford Radar RobotCar (Full-6)
SO-Net: Self-Organizing Network for Point Cloud Analysis
This paper presents SO-Net, a permutation invariant architecture for deep learning with orderless point clouds.
Ranked #3 on
3D Part Segmentation
on IntrA
3D Visual Perception for Self-Driving Cars using a Multi-Camera System: Calibration, Mapping, Localization, and Obstacle Detection
To minimize the number of cameras needed for surround perception, we utilize fisheye cameras.
Sparse to Dense 3D Reconstruction From Rolling Shutter Images
It is well known that the rolling shutter effect in images captured with a moving rolling shutter camera causes inaccuracies to 3D reconstructions.
Line-Sweep: Cross-Ratio For Wide-Baseline Matching and 3D Reconstruction
We propose a simple and useful idea based on cross-ratio constraint for wide-baseline matching and 3D reconstruction.
Relative Pose Estimation for a Multi-Camera System with Known Vertical Direction
In this paper, we present our minimal 4-point and linear 8-point algorithms to estimate the relative pose of a multi-camera system with known vertical directions, i. e. known absolute roll and pitch angles.
Motion Estimation for Self-Driving Cars with a Generalized Camera
By modeling the multicamera system as a generalized camera and applying the non-holonomic motion constraint of a car, we show that this leads to a novel 2-point minimal solution for the generalized essential matrix where the full relative motion including metric scale can be obtained.
