Search Results for author:
Found 40 papers, 26 papers with code
Improving Referring Image Segmentation using Vision-Aware Text Features
Our method involves using CLIP to derive a CLIP Prior that integrates an object-centric visual heatmap with text description, which can be used as the initial query in DETR-based architecture for the segmentation task.
Self-supervised Video Object Segmentation with Distillation Learning of Deformable Attention
This is enabled by deformable attention mechanism, where the keys and values capturing the memory of a video sequence in the attention module have flexible locations updated across frames.
Ranked #8 on
Unsupervised Video Object Segmentation
on DAVIS 2016 val
(using extra training data)
Leveraging Open-Vocabulary Diffusion to Camouflaged Instance Segmentation
Such cross-domain representations are desirable in segmenting camouflaged objects where visual cues are subtle to distinguish the objects from the background, especially in segmenting novel objects which are not seen in training.
DiverseDream: Diverse Text-to-3D Synthesis with Augmented Text Embedding
Text-to-3D synthesis has recently emerged as a new approach to sampling 3D models by adopting pretrained text-to-image models as guiding visual priors.
Advances in 3D Neural Stylization: A Survey
Building on such taxonomy, our survey first revisits the background of neural stylization on 2D images, and then provides in-depth discussions on recent neural stylization methods for 3D data, where we also provide a mini-benchmark on artistic stylization methods.
Test-Time Augmentation for 3D Point Cloud Classification and Segmentation
We are inspired by the recent revolution of learning implicit representation and point cloud upsampling, which can produce high-quality 3D surface reconstruction and proximity-to-surface, respectively.
Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset Updates
Specifically, to insert a new foreground object represented by a set of multi-view images into a background radiance field, we use a text-to-image diffusion model to learn and generate combined images that fuse the object of interest into the given background across views.
Locally Stylized Neural Radiance Fields
In this work, we propose a stylization framework for NeRF based on local style transfer.
GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo Labelers
Furthermore, we demonstrate the robustness of our approach, where we can adapt various state-of-the-art fully supervised methods to the weak supervision task by using our pseudo labels for training.
Conditional 360-degree Image Synthesis for Immersive Indoor Scene Decoration
We use this object layout to condition a generative adversarial network to synthesize images of an input scene.
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution
Existing 3D instance segmentation methods are predominated by the bottom-up design -- manually fine-tuned algorithm to group points into clusters followed by a refinement network.
Ranked #2 on
3D Instance Segmentation
on STPLS3D
PointInverter: Point Cloud Reconstruction and Editing via a Generative Model with Shape Priors
In this paper, we propose a new method for mapping a 3D point cloud to the latent space of a 3D generative adversarial network.
Single-Image HDR Reconstruction by Multi-Exposure Generation
In this work, we propose a weakly supervised learning method that inverts the physical image formation process for HDR reconstruction via learning to generate multiple exposures from a single image.
Self-Supervised Learning with Multi-View Rendering for 3D Point Cloud Analysis
Inspired by the success of deep learning in the image domain, we devise a novel pre-training technique for better model initialization by utilizing the multi-view rendering of the 3D data.
Time-of-Day Neural Style Transfer for Architectural Photographs
Architectural photography is a genre of photography that focuses on capturing a building or structure in the foreground with dramatic lighting in the background.
Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments
To the best of our knowledge, our work is the first to explore transductive few-shot video classification.
POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples
In this work, we propose to use out-of-distribution samples, i. e., unlabeled samples coming from outside the target classes, to improve few-shot learning.
RFNet-4D++: Joint Object Reconstruction and Flow Estimation from 4D Point Clouds with Cross-Attention Spatio-Temporal Features
The key insight is simultaneously performing both tasks via learning of spatial and temporal features from a sequence of point clouds can leverage individual tasks, leading to improved overall performance.
Ranked #1 on
3D Human Reconstruction
on Dynamic FAUST
3D-UCaps: 3D Capsules Unet for Volumetric Image Segmentation
Medical image segmentation has been so far achieving promising results with Convolutional Neural Networks (CNNs).
Point-Unet: A Context-aware Point-based Neural Network for Volumetric Segmentation
In this paper, we propose Point-Unet, a novel method that incorporates the efficiency of deep learning with 3D point clouds into volumetric segmentation.
RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learning
3D point clouds deep learning is a promising field of research that allows a neural network to learn features of point clouds directly, making it a robust tool for solving 3D scene understanding tasks.
SS-3DCapsNet: Self-supervised 3D Capsule Networks for Medical Segmentation on Less Labeled Data
Capsule network is a recent new deep network architecture that has been applied successfully for medical image segmentation tasks.
TISE: Bag of Metrics for Text-to-Image Synthesis Evaluation
Our study outlines several issues in the current evaluation pipeline: (i) for image quality assessment, a commonly used metric, e. g., Inception Score (IS), is often either miscalibrated for the single-object case or misused for the multi-object case; (ii) for text relevance and object accuracy assessment, there is an overfitting phenomenon in the existing R-precision (RP) and Semantic Object Accuracy (SOA) metrics, respectively; (iii) for multi-object case, many vital factors for evaluation, e. g., object fidelity, positional alignment, counting alignment, are largely dismissed; (iv) the ranking of the methods based on current metrics is highly inconsistent with real images.
POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples NeurIPS 2021
In this work, we propose to use out-of-distribution samples, i. e., unlabeled samples coming from outside the target classes, to improve few-shot learning.
HyperInverter: Improving StyleGAN Inversion via Hypernetwork
In the first phase, we train an encoder to map the input image to StyleGAN2 $\mathcal{W}$-space, which was proven to have excellent editability but lower reconstruction quality.
Neural Scene Decoration from a Single Photograph
In this paper, we introduce a new problem of domain-specific indoor scene image synthesis, namely neural scene decoration.
Network Pruning That Matters: A Case Study on Retraining Variants
Our results emphasize the cruciality of the learning rate schedule in pruned network retraining - a detail often overlooked by practitioners during the implementation of network pruning.
Ranked #10 on
Network Pruning
on ImageNet
Point-set Distances for Learning Representations of 3D Point Clouds
From this study, we propose to use sliced Wasserstein distance and its variants for learning representations of 3D point clouds.
Minimal Adversarial Examples for Deep Learning on 3D Point Clouds
With recent developments of convolutional neural networks, deep learning for 3D point clouds has shown significant progress in various 3D scene understanding tasks, e. g., object recognition, semantic segmentation.
Global Context Aware Convolutions for 3D Point Cloud Understanding
We found that a key reason is that compared to point coordinates, rotation-invariant features consumed by point cloud convolution are not as distinctive.
LCD: Learned Cross-Domain Descriptors for 2D-3D Matching
In this work, we present a novel method to learn a local cross-domain descriptor for 2D image and 3D point cloud matching.
Rotation Invariant Convolutions for 3D Point Clouds Deep Learning
Our core idea is to use low-level rotation invariant geometric features such as distances and angles to design a convolution operator for point cloud learning.
ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics
Deep learning with 3D data has progressed significantly since the introduction of convolutional neural networks that can handle point order ambiguity in point cloud data.
Ranked #8 on
3D Semantic Segmentation
on DALES
Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data
From our comprehensive benchmark, we show that our dataset poses great challenges to existing point cloud classification techniques as objects from real-world scans are often cluttered with background and/or are partial due to occlusions.
JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds with Multi-Task Pointwise Networks and Multi-Value Conditional Random Fields
Deep learning techniques have become the to-go models for most vision-related tasks on 2D images.
Ranked #2 on
3D Instance Segmentation
on SceneNN
3D Instance Segmentation
3D Semantic Instance Segmentation
+3
Real-time Progressive 3D Semantic Segmentation for Indoor Scene
The widespread adoption of autonomous systems such as drones and assistant robots has created a need for real-time high-quality semantic scene segmentation.
Pointwise Convolutional Neural Networks
Deep learning with 3D data such as reconstructed point clouds and CAD models has received great research interests recently.
Calibration of depth cameras using denoised depth images
Depth sensing devices have created various new applications in scientific and commercial research with the advent of Microsoft Kinect and PMD (Photon Mixing Device) cameras.
A Robust 3D-2D Interactive Tool for Scene Segmentation and Annotation
Recent advances of 3D acquisition devices have enabled large-scale acquisition of 3D scene data.
A Field Model for Repairing 3D Shapes
The proposed method was evaluated on both artificial data and real data obtained from reconstruction of practical scenes.
