paper-with-me

홈 › Papers

HAVIR: HierArchical Vision to Image Reconstruction using CLIP-Guided Versatile Diffusion

2025-10-03 · Shiyi Zhang, Dong Liang, Hairong Zheng, Yihang Zhou arxiv

The reconstruction of visual information from brain activity fosters interdisciplinary integration between neuroscience and computer vision. However, existing methods still face challenges in accurately recovering highly complex visual stimuli. This difficulty stems from the characteristics of natural scenes: low-level features exhibit heterogeneity, while high-level features show semantic entanglement due to contextual overlaps. Inspired by the hierarchical representation theory of the visual cortex, we propose the HAVIR model, which separates the visual cortex into two hierarchical regions and extracts distinct features from each. Specifically, the Structural Generator extracts structural information from spatial processing voxels and converts it into latent diffusion priors, while the Semantic Extractor converts semantic processing voxels into CLIP embeddings. These components are integrated via the Versatile Diffusion model to synthesize the final image. Experimental results demonstrate that HAVIR enhances both the structural and semantic quality of reconstructions, even in complex scenes, and outperforms existing models.

📄 PDF Abstract BibTeX arXiv:2510.03122

Code (0)

등록된 구현이 없습니다.

Tasks

Image Reconstruction

Similar Papers 제목 키워드 기반

HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention

2023-03-06 · Shijie Geng, Jianbo Yuan, Yu Tian, Yuxiao Chen 외

The success of large-scale contrastive vision-language pretraining (CLIP) has benefited both visual recognition and multimodal content understanding. The concise design brings CLIP the advantage in inference efficiency a…

cross-modal alignment

Interpreting CLIP with Hierarchical Sparse Autoencoders

2025-02-27 · Vladimir Zaigrajew, Hubert Baniecki, Przemyslaw Biecek

Sparse autoencoders (SAEs) are useful for detecting and steering interpretable features in neural networks, with particular potential for understanding complex multimodal representations. Given their ability to uncover i…

HGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical Understanding

2023-11-23 · Peng Xia, Xingtong Yu, Ming Hu, Lie Ju 외

Object categories are typically organized into a multi-granularity taxonomic hierarchy. When classifying categories at different hierarchy levels, traditional uni-modal approaches focus primarily on image features, revea…

Fine-Grained Visual RecognitionGraph Representation LearningRepresentation Learning

CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation

2024-11-21 · Lin Sun, Jiale Cao, Jin Xie, Xiaoheng Jiang 외

Contrastive Language-Image Pre-training (CLIP) exhibits strong zero-shot classification ability on various image-level tasks, leading to the research to adapt CLIP for pixel-level open-vocabulary semantic segmentation wi…

Open Vocabulary Semantic SegmentationOpen-Vocabulary Semantic SegmentationSegmentationSemantic Segmentation+2

TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction

2026-07-05 · Nikos Athanasiou, Ilya A. Petrov, Angela Yao, Shugao Ma 외 arxiv

Vision and vision-language models rely on high-level visual representations that are increasingly used across recognition, retrieval, and multimodal reasoning pipelines. However, recent advances in generative modeling ha…

Multimodal Reasoning