SC-Diff: Semantically Calibrated Diffusion for Visible-to-Infrared Image Translation

• URL: http://arxiv.org/abs/2608.08555v1
• Date: Sun, 09 Aug 2026 07:57:40 GMT
• Title: SC-Diff: Semantically Calibrated Diffusion for Visible-to-Infrared Image Translation
• Abstract summary: Visible-to-infrared image translation provides a practical way to expand infrared training data using abundant visible images.<n>Existing diffusion-based methods typically use semantic priors only as external conditions.<n>We propose SC-Diff, a semantically latent diffusion framework that uses semantic priors for both conditional guidance and internal self-attention calibration.
• Score: 52.62632888060867
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visible-to-infrared image translation provides a practical way to expand infrared training data using abundant visible images. Diffusion models are promising for this task because of their strong generative performance. However, existing diffusion-based methods typically use semantic priors only as external conditions, without explicitly regulating token interactions within the denoising network. Consequently, they struggle to preserve object locations, shapes, and semantic layouts required for reliable annotation reuse. We propose SC-Diff, a semantically calibrated latent diffusion framework that uses semantic priors for both conditional guidance and internal self-attention calibration. A pretrained SAM3 model with predefined text prompts first extracts category-specific semantic masks from visible images. These masks are merged into a semantic map and fused with the visible image as the input condition. The same map is converted into token-level semantic labels to calibrate self-attention in the denoising network. Based on these labels, we introduce Semantic-Guided Self-Attention Calibration (SGSC), which adaptively applies positive biases to query-key pairs of the same category. The query-wise calibration strength depends on the dispersion of attention across semantic categories and the attention assigned to the query's own category. The original attention scores further modulate the bias, giving greater calibration to same-category keys with stronger responses. This soft calibration reduces cross-category interference while retaining global contextual interactions, thereby improving semantic consistency in generated infrared images. Extensive experiments show that SC-Diff improves perceptual quality and produces more effective synthetic training data for downstream infrared object detection.

Related papers

• Concept-based Visual Counterfactual Explanations with Diffusion Models [6.539386622516073]
  C-VCE builds the classifier directly into the generative model via a concept bottleneck layer.<n>Our model lets users toggle on/off semantic concepts during sampling, then adjusts minimally relevant image regions.<n>On benchmarks such as CelebA, C-VCE matches or improves flip rates while producing counterfactuals that are visually closer to the input.
  arXiv  Detail & Related papers  (2026-05-05T15:32:50Z)
• SGDFuse: SAM-Guided Diffusion for High-Fidelity Infrared and Visible Image Fusion [65.80051636480836]
  This paper proposes a conditional diffusion model guided by the Segment Anything Model (SAM) to achieve high-fidelity and semantically-aware image fusion.<n>The framework operates in a two-stage process: it first performs a preliminary fusion of multi-modal features, and then utilizes the semantic masks as a condition to drive the diffusion model's coarse-to-fine denoising generation.<n>Extensive experiments demonstrate that SGDFuse achieves state-of-the-art performance in both subjective and objective evaluations.
  arXiv  Detail & Related papers  (2025-08-07T10:58:52Z)
• FreSca: Scaling in Frequency Space Enhances Diffusion Models [55.75504192166779]
  This paper explores frequency-based control within latent diffusion models.<n>We introduce FreSca, a novel framework that decomposes noise difference into low- and high-frequency components.<n>FreSca operates without any model retraining or architectural change, offering model- and task-agnostic control.
  arXiv  Detail & Related papers  (2025-04-02T22:03:11Z)
• CAM-Seg: A Continuous-valued Embedding Approach for Semantic Image Generation [11.170848285659572]
  Autoencoder accuracy on segmentation mask using quantized embeddings is 8% lower than continuous-valued embeddings.<n>We propose a continuous-valued embedding framework for semantic segmentation.<n>Our approach eliminates the need for discrete latent representations while preserving fine-grained semantic details.
  arXiv  Detail & Related papers  (2025-03-19T18:06:54Z)
• Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation [54.96563068182733]
  We propose Modality Adaptation with text-to-image Diffusion Models (MADM) for semantic segmentation task. MADM utilizes text-to-image diffusion models pre-trained on extensive image-text pairs to enhance the model's cross-modality capabilities. We show that MADM achieves state-of-the-art adaptation performance across various modality tasks, including images to depth, infrared, and event modalities.
  arXiv  Detail & Related papers  (2024-10-29T03:49:40Z)
• Spatial Action Unit Cues for Interpretable Deep Facial Expression Recognition [55.97779732051921]
  State-of-the-art classifiers for facial expression recognition (FER) lack interpretability, an important feature for end-users. A new learning strategy is proposed to explicitly incorporate AU cues into classifier training, allowing to train deep interpretable models. Our new strategy is generic, and can be applied to any deep CNN- or transformer-based classifier without requiring any architectural change or significant additional training time.
  arXiv  Detail & Related papers  (2024-10-01T10:42:55Z)
• ASCNet: Asymmetric Sampling Correction Network for Infrared Image Destriping [25.816984064145906]
  We propose a novel infrared image destriping method called Asymmetric Sampling Correction Network (ASCNet)<n>Our ASCNet consists of three core elements: Residual Haar Discrete Wavelet Transform (RHDWT), Pixel Shuffle (PS), and Column Non-uniformity Correction Module (CNCM)
  arXiv  Detail & Related papers  (2024-01-28T06:23:55Z)
• Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting [133.55037976429088]
  We investigate the adversarial robustness of vision transformers equipped with BERT pretraining (e.g., BEiT, MAE) A surprising observation is that MAE has significantly worse adversarial robustness than other BERT pretraining methods. We propose a simple yet effective way to boost the adversarial robustness of MAE.
  arXiv  Detail & Related papers  (2023-08-20T16:27:17Z)
• Location-Aware Self-Supervised Transformers [74.76585889813207]
  We propose to pretrain networks for semantic segmentation by predicting the relative location of image parts. We control the difficulty of the task by masking a subset of the reference patch features visible to those of the query. Our experiments show that this location-aware pretraining leads to representations that transfer competitively to several challenging semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2022-12-05T16:24:29Z)
• Uncertain Label Correction via Auxiliary Action Unit Graphs for Facial Expression Recognition [46.99756911719854]
  We achieve uncertain label correction of facial expressions using auxiliary action unit (AU) graphs, called ULC-AG. Experiments show that our ULC-AG achieves 89.31% and 61.57% accuracy on RAF-DB and AffectNet datasets, respectively.
  arXiv  Detail & Related papers  (2022-04-23T11:09:43Z)

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.