Search Results for author:
Found 48 papers, 28 papers with code
MVD-HuGaS: Human Gaussians from a Single Image via 3D Human Multi-view Diffusion Prior
We first generate multi-view images from the single reference image with an enhanced multi-view diffusion model, which is well fine-tuned on high-quality 3D human datasets to incorporate 3D geometry priors and human structure priors.
Surface-SOS: Self-Supervised Object Segmentation via Neural Surface Representation
To make better use of the above information, we propose Surface representation based Self-supervised Object Segmentation (Surface-SOS), a new framework to segment objects for each view by 3D surface representation from multi-view images of a scene.
Few Exemplar-Based General Medical Image Segmentation via Domain-Aware Selective Adaptation
Medical image segmentation poses challenges due to domain gaps, data modality variations, and dependency on domain knowledge or experts, especially for low- and middle-income countries (LMICs).
Bridge the Points: Graph-based Few-shot Segment Anything Semantically
Another subsequent Point-Mask Clustering module aligns the granularity of masks and selected points as a directed graph, based on mask coverage over points.
Ranked #2 on
Few-Shot Semantic Segmentation
on COCO-20i (5-shot)
Disentangled Generation and Aggregation for Robust Radiance Fields
To this end, we propose the Disentangled Triplane Generation module to introduce global feature context and smoothness into triplane learning, which mitigates errors caused by local updating.
Surface-Centric Modeling for High-Fidelity Generalizable Neural Surface Reconstruction
To this end, we propose SuRF, a new Surface-centric framework that incorporates a new Region sparsification based on a matching Field, achieving good trade-offs between performance, efficiency and scalability.
Frame Interpolation with Consecutive Brownian Bridge Diffusion
To address this problem, we propose our unique solution: Frame Interpolation with Consecutive Brownian Bridge Diffusion.
Dynamic in Static: Hybrid Visual Correspondence for Self-Supervised Video Object Segmentation
To achieve this objective, we present a unified self-supervised approach to learn visual representations of static-dynamic feature similarity.
360+x: A Panoptic Multi-modal Scene Understanding Dataset
While many existing datasets focus on scene understanding from a certain perspective (e. g. egocentric or third-person views), our dataset offers a panoptic perspective (i. e. multiple viewpoints with multiple data modalities).
PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling
To facilitate the development of these fields, in this paper, we present PKU-DyMVHumans, a versatile human-centric dataset for high-fidelity reconstruction and rendering of dynamic human scenarios from dense multi-view videos.
Show from Tell: Audio-Visual Modelling in Clinical Settings
Auditory and visual signals usually present together and correlate with each other, not only in natural environments but also in clinical settings.
CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentation
However, most state-of-the-art methods use the freeze strategy for stability, which compromises the model's plasticity. In contrast, releasing parameter training for plasticity could lead to the best performance for all categories, but this requires discriminative feature representation. Therefore, we prioritize the model's plasticity and propose the Contrast inter- and intra-class representations for Incremental Segmentation (CoinSeg), which pursues discriminative representations for flexible parameter tuning.
Speed Co-Augmentation for Unsupervised Audio-Visual Pre-training
This work aims to improve unsupervised audio-visual pre-training.
Multi-view Self-supervised Disentanglement for General Image Denoising
It is understandable as the model is designed to learn paired mapping (e. g. from a noisy image to its clean version).
Ranked #1 on
Denoising
on CBSD68 sigm75
FreMIM: Fourier Transform Meets Masked Image Modeling for Medical Image Segmentation
The research community has witnessed the powerful potential of self-supervised Masked Image Modeling (MIM), which enables the models capable of learning visual representation from unlabeled data.
Med-Tuning: A New Parameter-Efficient Tuning Framework for Medical Volumetric Segmentation
Thus, it is of increasing importance to fine-tune pre-trained models for medical volumetric segmentation tasks in a both effective and parameter-efficient manner.
Revisiting Implicit Neural Representations in Low-Level Vision
Implicit Neural Representation (INR) has been emerging in computer vision in recent years.
Disentangled Pre-training for Image Matting
The pre-training task is designed in a similar manner as image matting, where random trimap and alpha matte are generated to achieve an image disentanglement objective.
CL-MVSNet: Unsupervised Multi-View Stereo with Dual-Level Contrastive Learning
On the one hand, we present an image-level contrastive branch to guide the model to acquire more context awareness, thus leading to more complete depth estimation in indistinguishable regions.
Diffuse3D: Wide-Angle 3D Photography via Bilateral Diffusion
To address the above issues, we propose Diffuse3D which employs a pre-trained diffusion model for global synthesis, while amending the model to activate depth-aware inference.
Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental Segmentation
Our MicroSeg is based on the assumption that background regions with strong objectness possibly belong to those concepts in the historical or future stages.
Class-Incremental Semantic Segmentation
Continual Learning
+1
Anatomy-Aware Contrastive Representation Learning for Fetal Ultrasound
The proposed approach is demonstrated for automated fetal ultrasound imaging tasks, enabling the positive pairs from the same or different ultrasound scans that are anatomically similar to be pulled together and thus improving the representation learning.
Revitalizing CNN Attention via Transformers in Self-Supervised Visual Representation Learning
Motivated by the transformers that explore visual attention effectively in recognition scenarios, we propose a CNN Attention REvitalization (CARE) framework to train attentive CNN encoders guided by transformers in SSL.
Quantised Transforming Auto-Encoders: Achieving Equivariance to Arbitrary Transformations in Deep Networks
In this work we investigate how to achieve equivariance to input transformations in deep networks, purely from data, without being given a model of those transformations.
Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning
Motivated by the transformers that explore visual attention effectively in recognition scenarios, we propose a CNN Attention REvitalization (CARE) framework to train attentive CNN encoders guided by transformers in SSL.
Facial Anatomical Landmark Detection using Regularized Transfer Learning with Application to Fetal Alcohol Syndrome Recognition
This imaging application is characterized by large variations in data appearance and limited availability of labeled data.
Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation
More importantly, our approach can be readily applied to bounding box supervised instance segmentation task or other weakly supervised semantic segmentation tasks, with state-of-the-art or comparable performance among almot all weakly supervised tasks on PASCAL VOC or COCO dataset.
Box-supervised Instance Segmentation
Graph Neural Network
+4
Scene Context-Aware Salient Object Detection
To our knowledge, such high-level semantic contextual information of image scenes is under-explored for saliency detection in the literature.
Cross-Task Representation Learning for Anatomical Landmark Detection
The main idea of the proposed method is to retain the feature representations of the source model on the target task data, and to leverage them as an additional source of supervisory signals for regularizing the target model learning, thereby improving its performance under limited training samples.
Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics
Specifically, given an unlabeled video clip, we compute a series of spatio-temporal statistical summaries, such as the spatial location and dominant direction of the largest motion, the spatial location and dominant color of the largest color diversity along the temporal axis, etc.
Self-Supervised Ultrasound to MRI Fetal Brain Image Synthesis
To regularise the anatomical structures between US and MRI during synthesis, we further propose an adversarial structural constraint.
Self-supervised Contrastive Video-Speech Representation Learning for Ultrasound
For this case, we assume that there is a high correlation between the ultrasound video and the corresponding narrative speech audio of the sonographer.
Self-supervised Video Representation Learning by Pace Prediction
This paper addresses the problem of self-supervised video representation learning from a new perspective -- by video pace prediction.
Referring Image Segmentation by Generative Adversarial Learning
To this end, we propose to train the referring image segmentation model in a generative adversarial fashion, which well addresses the distribution similarity problem.
Laplacian Denoising Autoencoder
This can be naturally generalized to span multiple scales with a Laplacian pyramid representation of the input data.
Unified Image and Video Saliency Modeling
We evaluate our method on the video saliency datasets DHF1K, Hollywood-2 and UCF-Sports, and the image saliency datasets SALICON and MIT300.
Self-supervised Representation Learning for Ultrasound Video
Therefore, there is significant interest in learning representations from unlabelled raw data.
Anatomy-Aware Self-supervised Fetal MRI Synthesis from Unpaired Ultrasound Images
The feasibility of the approach to produce realistic looking MR images is demonstrated quantitatively and with a qualitative evaluation compared to real fetal MR images.
Geometry-Aware Distillation for Indoor Semantic Segmentation
It has been shown that jointly reasoning the 2D appearance and 3D information from RGB-D domains is beneficial to indoor scene semantic segmentation.
Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics
We conduct extensive experiments with C3D to validate the effectiveness of our proposed approach.
Ranked #47 on
Self-Supervised Action Recognition
on HMDB51
When AWGN-based Denoiser Meets Real Noises
In this paper, we propose a novel approach to boost the performance of a real image denoiser which is trained only with synthetic pixel-independent noise data dominated by AWGN.
Ranked #2 on
Denoising
on Darmstadt Noise Dataset
Connecting Image Denoising and High-Level Vision Tasks via Deep Learning
Second we propose a deep neural network solution that cascades two modules for image denoising and various high-level tasks, respectively, and use the joint loss for updating only the denoising network via back-propagation.
Task-driven Webpage Saliency
Inspired by the observation that given a specific task, human attention is strongly correlated with certain semantic components on a webpage (e. g., images, buttons and input boxes), our network explicitly disentangles saliency prediction into two independent sub-tasks: task-specific attention shift prediction and task-free saliency prediction.
Look Deeper into Depth: Monocular Depth Estimation with Semantic Booster and Attention-Driven Loss
Monocular depth estimation benefits greatly from learning based techniques.
Delving Into Salient Object Subitizing and Detection
Experiments show that the proposed multi-task network outperforms existing multi-task architectures, and the auxiliary subitizing network provides strong guidance to salient object detection by reducing false positives and producing coherent saliency maps.
3D Hand Pose Tracking and Estimation Using Stereo Matching
This paper demonstrates that the performance of the state-of-the art tracking/estimation algorithms can be maintained with most stereo matching algorithms on the proposed benchmark, as long as the hand segmentation is correct.
