Search Results for author:
Found 49 papers, 24 papers with code
Infinite-ID: Identity-preserved Personalization via ID-semantics Decoupling Paradigm
Drawing on recent advancements in diffusion models for text-to-image generation, identity-preserved personalization has made significant progress in accurately capturing specific identities with just a single reference image.
When ControlNet Meets Inexplicit Masks: A Case Study of ControlNet on its Contour-following Ability
Subsequently, to enhance controllability with inexplicit masks, an advanced Shape-aware ControlNet consisting of a deterioration estimator and a shape-prior modulation block is devised.
Trajectory Consistency Distillation: Improved Latent Consistency Distillation by Semi-Linear Consistency Function with Trajectory Mapping
Consequently, we introduce Trajectory Consistency Distillation (TCD), which encompasses trajectory consistency function and strategic stochastic sampling.
HandRefiner: Refining Malformed Hands in Generated Images by Diffusion-based Conditional Inpainting
Given a generated failed image due to malformed hands, we utilize ControlNet modules to re-inject such correct hand information.
One More Step: A Versatile Plug-and-Play Module for Rectifying Diffusion Schedule Flaws and Enhancing Low-Frequency Controls
By integrating a compact network and incorporating an additional simple yet effective step during inference, OMS elevates image fidelity and harmonizes the dichotomy between training and inference, while preserving original model parameters.
Peer is Your Pillar: A Data-unbalanced Conditional GANs for Few-shot Image Generation
Few-shot image generation aims to train generative models using a small number of training images.
Decompose Semantic Shifts for Composed Image Retrieval
Composed image retrieval is a type of image retrieval task where the user provides a reference image as a starting point and specifies a text on how to shift from the starting point to the desired target image.
Autoregressive Omni-Aware Outpainting for Open-Vocabulary 360-Degree Image Generation
A 360-degree (omni-directional) image provides an all-encompassing spherical view of a scene.
PartSeg: Few-shot Part Segmentation via Part-aware Prompt Learning
In this work, we address the task of few-shot part segmentation, which aims to segment the different parts of an unseen object using very few labeled examples.
Cross-modal & Cross-domain Learning for Unsupervised LiDAR Semantic Segmentation
In recent years, cross-modal domain adaptation has been studied on the paired 2D image and 3D LiDAR data to ease the labeling costs for 3D LiDAR semantic segmentation (3DLSS) in the target domain.
Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generation
In this work, we propose Cocktail, a pipeline to mix various modalities into one embedding, amalgamated with a generalized ControlNet (gControlNet), a controllable normalisation (ControlNorm), and a spatial guidance sampling method, to actualize multi-modal and spatially-refined control for text-conditional diffusion models.
All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation
We hypothesize that this selective usage arises from the noise in pseudo-labels generated on unlabeled data.
Null-text Guidance in Diffusion Models is Secretly a Cartoon-style Creator
Specifically, we proposed two disturbance methods, i. e., Rollback disturbance (Back-D) and Image disturbance (Image-D), to construct misalignment between the noisy images used for predicting null-text guidance and text guidance (subsequently referred to as \textbf{null-text noisy image} and \textbf{text noisy image} respectively) in the sampling process.
MMoT: Mixture-of-Modality-Tokens Transformer for Composed Multimodal Conditional Image Synthesis
To this end, we propose to generate images conditioned on the compositions of multimodal control signals, where modalities are imperfectly complementary, i. e., composed multimodal conditional image synthesis (CMCIS).
MagicFusion: Boosting Text-to-Image Generation Performance by Fusing Diffusion Models
The advent of open-source AI communities has produced a cornucopia of powerful text-guided diffusion models that are trained on various datasets.
ESceme: Vision-and-Language Navigation with Episodic Scene Memory
Vision-and-language navigation (VLN) simulates a visual agent that follows natural-language navigation instructions in real-world scenes.
OmniForce: On Human-Centered, Large Model Empowered and Cloud-Edge Collaborative AutoML System
Automated machine learning (AutoML) seeks to build ML models with minimal human effort.
Eliminating Contextual Prior Bias for Semantic Image Editing via Dual-Cycle Diffusion
The proposed model incorporates a Bias Elimination Cycle that consists of both a forward path and an inverted path, each featuring a Structural Consistency Cycle to ensure the preservation of image content during the editing process.
Diff-Font: Diffusion Model for Robust One-Shot Font Generation
Specifically, a large stroke-wise dataset is constructed, and a stroke-wise diffusion model is proposed to preserve the structure and the completion of each generated character.
Unified Discrete Diffusion for Simultaneous Vision-Language Generation
The recently developed discrete diffusion models perform extraordinarily well in the text-to-image task, showing significant promise for handling the multi-modality signals.
3DDesigner: Towards Photorealistic 3D Object Generation and Editing with Text-guided Diffusion Models
Text-guided diffusion models have shown superior performance in image/video generation and editing.
Cross-Modal Contrastive Learning for Robust Reasoning in VQA
For each positive pair, we regard the images from different graphs as negative samples and deduct the version of multi-positive contrastive learning.
Leveraging GAN Priors for Few-Shot Part Segmentation
Overall, this work is an attempt to explore the internal relevance between generation tasks and perception tasks by prompt designing.
FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs
Since data augmentation strategies have largely alleviated the training instability, how to further improve the generative performance of DE-GANs becomes a hotspot.
SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders
In this paper, we explore a potential visual analogue of words, i. e., semantic parts, and we integrate semantic information into the training process of MAE by proposing a Semantic-Guided Masking strategy.
Bypass Network for Semantics Driven Image Paragraph Captioning
Most existing methods model the coherence through the topic transition that dynamically infers a topic vector from preceding sentences.
Recent Advances for Quantum Neural Networks in Generative Learning
Due to the intrinsic probabilistic nature of quantum mechanics, it is reasonable to postulate that quantum generative learning models (QGLMs) may surpass their classical counterparts.
Modeling Image Composition for Complex Scene Generation
Compared to existing CNN-based and Transformer-based generation models that entangled modeling on pixel-level&patch-level and object-level&patch-level respectively, the proposed focal attention predicts the current patch token by only focusing on its highly-related tokens that specified by the spatial layout, thereby achieving disambiguation during training.
Visual Superordinate Abstraction for Robust Concept Learning
Concept learning constructs visual representations that are connected to linguistic semantics, which is fundamental to vision-language tasks.
Neural Maximum A Posteriori Estimation on Unpaired Data for Motion Deblurring
The proposed NeurMAP is an orthogonal approach to existing deblurring neural networks, and is the first framework that enables training image deblurring networks on unpaired datasets.
A Comprehensive Survey on Data-Efficient GANs in Image Generation
Generative Adversarial Networks (GANs) have achieved remarkable achievements in image synthesis.
BatchFormerV2: Exploring Sample Relationships for Dense Representation Learning
Specifically, when applying the proposed module, it employs a two-stream pipeline during training, i. e., either with or without a BatchFormerV2 module, where the batchformer stream can be removed for testing.
Self-Augmented Unpaired Image Dehazing via Density and Depth Decomposition
With estimated scene depth, our method is capable of re-rendering hazy images with different thicknesses which further benefits the training of the dehazing network.
Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition
Technically, given the character segmentation maps predicted by a VR model, we construct a subgraph for each instance, where nodes represent the pixels in it and edges are added between nodes based on their spatial similarity.
Ranked #9 on
Scene Text Recognition
on ICDAR2015
(using extra training data)
Video Frame Interpolation without Temporal Priors
However, in complicated real-world situations, the temporal priors of videos, i. e. frames per second (FPS) and frame exposure time, may vary from different camera sensors.
TAG: Toward Accurate Social Media Content Tagging with a Concept Graph
Although conceptualization has been widely studied in semantics and knowledge representation, it is still challenging to find the most accurate concept phrases to characterize the main idea of a text snippet on the fast-growing social media.
MRI-based Alzheimer's disease prediction via distilling the knowledge in multi-modal data
In this work, we propose a multi-modal multi-instance distillation scheme, which aims to distill the knowledge learned from multi-modal data to an MRI-based network for MCI conversion prediction.
Experimental Quantum Generative Adversarial Networks for Image Generation
For the first time, we experimentally achieve the learning and generation of real-world hand-written digit images on a superconducting quantum processor.
Exposure Trajectory Recovery from Motion Blur
However, the motion information contained in a blurry image has yet to be fully explored and accurately formulated because: (i) the ground truth of dynamic motion is difficult to obtain; (ii) the temporal ordering is destroyed during the exposure; and (iii) the motion estimation from a blurry image is highly ill-posed.
A Systematic Survey of Regularization and Normalization in GANs
Although a handful number of regularization and normalization methods have been proposed for GANs, to the best of our knowledge, there exists no comprehensive survey that primarily focuses on objectives and development of these methods, apart from some in-comprehensive and limited scope studies.
GIANT: Scalable Creation of a Web-scale Ontology
These services will benefit from a highly structured and web-scale ontology of entities, concepts, events, topics and categories.
A User-Centered Concept Mining System for Query and Document Understanding at Tencent
We further present our techniques to tag documents with user-centered concepts and to construct a topic-concept-instance taxonomy, which has helped to improve search as well as news feeds recommendation in Tencent QQ Browser.
Multiple Sclerosis Lesion Inpainting Using Non-Local Partial Convolutions
However, existing methods inpaint lesions based on texture information derived from local surrounding tissue, often leading to inconsistent inpainting and the generation of artifacts such as intensity discrepancy and blurriness.
Evolutionary Generative Adversarial Networks
In this paper, we propose a novel GAN framework called evolutionary generative adversarial networks (E-GAN) for stable GAN training and improved generative performance.
Perceptual Adversarial Networks for Image-to-Image Transformation
The proposed PAN consists of two feed-forward convolutional neural networks (CNNs), the image transformation network T and the discriminative network D. Through combining the generative adversarial loss and the proposed perceptual adversarial loss, these two networks can be trained alternately to solve image-to-image transformation tasks.
Tag Disentangled Generative Adversarial Networks for Object ImageRe-rendering
The whole framework consists of a disentangling network, a generative network, a tag mapping net, and a discriminative network, which are trained jointly based on a given set of images that are complete/partially tagged(i. e., supervised/semi-supervised setting).
