Retrieval-guided Cross-view Image Synthesis

• URL: http://arxiv.org/abs/2411.19510v2
• Date: Sat, 25 Jan 2025 06:32:40 GMT
• Title: Retrieval-guided Cross-view Image Synthesis
• Authors: Hongji Yang, Yiru Li, Yingying Zhu,
• Abstract summary: Cross-view image synthesis presents significant challenges in establishing reliable correspondences.<n>We propose a retrieval-guided framework that reimagines how retrieval techniques can facilitate effective cross-view image synthesis.<n>Our work bridges information retrieval and synthesis tasks, offering insights into how retrieval techniques can address complex cross-domain synthesis challenges.
• Score: 3.7477511412024573
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Information retrieval techniques have demonstrated exceptional capabilities in identifying semantic similarities across diverse domains through robust feature representations. However, their potential in guiding synthesis tasks, particularly cross-view image synthesis, remains underexplored. Cross-view image synthesis presents significant challenges in establishing reliable correspondences between drastically different viewpoints. To address this, we propose a novel retrieval-guided framework that reimagines how retrieval techniques can facilitate effective cross-view image synthesis. Unlike existing methods that rely on auxiliary information, such as semantic segmentation maps or preprocessing modules, our retrieval-guided framework captures semantic similarities across different viewpoints, trained through contrastive learning to create a smooth embedding space. Furthermore, a novel fusion mechanism leverages these embeddings to guide image synthesis while learning and encoding both view-invariant and view-specific features. To further advance this area, we introduce VIGOR-GEN, a new urban-focused dataset with complex viewpoint variations in real-world scenarios. Extensive experiments demonstrate that our retrieval-guided approach significantly outperforms existing methods on the CVUSA, CVACT and VIGOR-GEN datasets, particularly in retrieval accuracy (R@1) and synthesis quality (FID). Our work bridges information retrieval and synthesis tasks, offering insights into how retrieval techniques can address complex cross-domain synthesis challenges.

Related papers

• Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learning [58.73625654718187]
  Generalized zero-shot learning aims to recognize both seen and unseen classes with the help of semantic information that is shared among different classes. Existing approaches fine-tune the visual backbone by seen-class data to obtain semantic-related visual features. This paper proposes a novel visual and semantic prompt collaboration framework, which utilizes prompt tuning techniques for efficient feature adaptation.
  arXiv  Detail & Related papers  (2025-03-29T10:17:57Z)
• A Multimodal Approach Combining Structural and Cross-domain Textual Guidance for Weakly Supervised OCT Segmentation [12.948027961485536]
  We propose a novel Weakly Supervised Semantic (WSSS) approach that integrates structural guidance with text-driven strategies to generate high-quality pseudo labels. Our method achieves state-of-the-art performance, highlighting its potential to improve diagnostic accuracy and efficiency in medical imaging.
  arXiv  Detail & Related papers  (2024-11-19T16:20:27Z)
• Where Do We Stand with Implicit Neural Representations? A Technical and Performance Survey [16.89460694470542]
  Implicit Neural Representations (INRs) have emerged as a paradigm in knowledge representation. INRs leverage multilayer perceptrons (MLPs) to model data as continuous implicit functions. This survey introduces a clear taxonomy that categorises them into four key areas: activation functions, position encoding, combined strategies, and network structure.
  arXiv  Detail & Related papers  (2024-11-06T06:14:24Z)
• Trustworthy Image Semantic Communication with GenAI: Explainablity, Controllability, and Efficiency [59.15544887307901]
  Image semantic communication (ISC) has garnered significant attention for its potential to achieve high efficiency in visual content transmission. Existing ISC systems based on joint source-channel coding face challenges in interpretability, operability, and compatibility. We propose a novel trustworthy ISC framework that employs Generative Artificial Intelligence (GenAI) for multiple downstream inference tasks.
  arXiv  Detail & Related papers  (2024-08-07T14:32:36Z)
• Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery [51.73680703579997]
  We present a neural radiance field method for urban-scale semantic and building-level instance segmentation from aerial images. objects in urban aerial images exhibit substantial variations in size, including buildings, cars, and roads. We introduce a scale-adaptive semantic label fusion strategy that enhances the segmentation of objects of varying sizes. We then introduce a novel cross-view instance label grouping strategy to mitigate the multi-view inconsistency problem in the 2D instance labels.
  arXiv  Detail & Related papers  (2024-03-18T14:15:39Z)
• RetriBooru: Leakage-Free Retrieval of Conditions from Reference Images for Subject-Driven Generation [30.143033020296183]
  Diffusion-based methods have demonstrated capabilities in generating a diverse array of high-quality images. We propose a multi-level, same-identity dataset RetriBooru, which groups anime characters by both face and cloth identities. We introduce a new concept composition task, where the conditioning encoder learns to retrieve different concepts from several reference images.
  arXiv  Detail & Related papers  (2023-12-05T06:04:16Z)
• Multimodal Relation Extraction with Cross-Modal Retrieval and Synthesis [89.04041100520881]
  This research proposes to retrieve textual and visual evidence based on the object, sentence, and whole image. We develop a novel approach to synthesize the object-level, image-level, and sentence-level information for better reasoning between the same and different modalities.
  arXiv  Detail & Related papers  (2023-05-25T15:26:13Z)
• Adapt and Align to Improve Zero-Shot Sketch-Based Image Retrieval [85.39613457282107]
  Cross-domain nature of sketch-based image retrieval is challenging. We present an effective Adapt and Align'' approach to address the key challenges. Inspired by recent advances in image-text foundation models (e.g., CLIP) on zero-shot scenarios, we explicitly align the learned image embedding with a more semantic text embedding to achieve the desired knowledge transfer from seen to unseen classes.
  arXiv  Detail & Related papers  (2023-05-09T03:10:15Z)
• Progressive Multi-view Human Mesh Recovery with Self-Supervision [68.60019434498703]
  Existing solutions typically suffer from poor generalization performance to new settings. We propose a novel simulation-based training pipeline for multi-view human mesh recovery.
  arXiv  Detail & Related papers  (2022-12-10T06:28:29Z)
• Autoencoder for Synthetic to Real Generalization: From Simple to More Complex Scenes [13.618797548020462]
  We focus on autoencoder architectures and aim at learning latent space representations that are invariant to inductive biases caused by the domain shift between simulated and real images. We present approaches to increase generalizability and improve the preservation of the semantics to real datasets of increasing visual complexity.
  arXiv  Detail & Related papers  (2022-04-01T12:23:41Z)
• Cross-View Panorama Image Synthesis [68.35351563852335]
  PanoGAN is a novel adversarial feedback GAN framework named. PanoGAN enables high-quality panorama image generation with more convincing details than state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-03-22T15:59:44Z)
• Two-stage Visual Cues Enhancement Network for Referring Image Segmentation [89.49412325699537]
  Referring Image (RIS) aims at segmenting the target object from an image referred by one given natural language expression. In this paper, we tackle this problem by devising a Two-stage Visual cues enhancement Network (TV-Net) Through the two-stage enhancement, our proposed TV-Net enjoys better performances in learning fine-grained matching behaviors between the natural language expression and image.
  arXiv  Detail & Related papers  (2021-10-09T02:53:39Z)
• City-Scale Visual Place Recognition with Deep Local Features Based on Multi-Scale Ordered VLAD Pooling [5.274399407597545]
  We present a fully-automated system for place recognition at a city-scale based on content-based image retrieval. Firstly, we take a comprehensive analysis of visual place recognition and sketch out the unique challenges of the task. Next, we propose yet a simple pooling approach on top of convolutional neural network activations to embed the spatial information into the image representation vector.
  arXiv  Detail & Related papers  (2020-09-19T15:21:59Z)
• Synthetic Convolutional Features for Improved Semantic Segmentation [139.5772851285601]
  We suggest to generate intermediate convolutional features and propose the first synthesis approach that is catered to such intermediate convolutional features. This allows us to generate new features from label masks and include them successfully into the training procedure. Experimental results and analysis on two challenging datasets Cityscapes and ADE20K show that our generated feature improves performance on segmentation tasks.
  arXiv  Detail & Related papers  (2020-09-18T14:12:50Z)
• Bowtie Networks: Generative Modeling for Joint Few-Shot Recognition and Novel-View Synthesis [39.53519330457627]
  We propose a novel task of joint few-shot recognition and novel-view synthesis. We aim to simultaneously learn an object classifier and generate images of that type of object from new viewpoints. We focus on the interaction and cooperation between a generative model and a discriminative model.
  arXiv  Detail & Related papers  (2020-08-16T19:40:56Z)
• Example-Guided Image Synthesis across Arbitrary Scenes using Masked Spatial-Channel Attention and Self-Supervision [83.33283892171562]
  Example-guided image synthesis has recently been attempted to synthesize an image from a semantic label map and an exemplary image. In this paper, we tackle a more challenging and general task, where the exemplar is an arbitrary scene image that is semantically different from the given label map. We propose an end-to-end network for joint global and local feature alignment and synthesis.
  arXiv  Detail & Related papers  (2020-04-18T18:17:40Z)
• Hierarchy Composition GAN for High-fidelity Image Synthesis [57.32311953820988]
  This paper presents an innovative Hierarchical Composition GAN (HIC-GAN) HIC-GAN incorporates image synthesis in geometry and appearance domains into an end-to-end trainable network. Experiments on scene text image synthesis, portrait editing and indoor rendering tasks show that the proposed HIC-GAN achieves superior synthesis performance qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2019-05-12T11:11:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.