The reviewed record of science sign in
Pith

arxiv: 2503.19012 · v1 · pith:AH7J3LXF · submitted 2025-03-24 · cs.CV

DiffV2IR: Visible-to-Infrared Diffusion Model via Vision-Language Understanding

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:AH7J3LXFrecord.jsonopen to challenge →

classification cs.CV
keywords diffv2irinfraredv2irdatasetmodeltranslationunderstandingvision-language
0
0 comments X
read the original abstract

The task of translating visible-to-infrared images (V2IR) is inherently challenging due to three main obstacles: 1) achieving semantic-aware translation, 2) managing the diverse wavelength spectrum in infrared imagery, and 3) the scarcity of comprehensive infrared datasets. Current leading methods tend to treat V2IR as a conventional image-to-image synthesis challenge, often overlooking these specific issues. To address this, we introduce DiffV2IR, a novel framework for image translation comprising two key elements: a Progressive Learning Module (PLM) and a Vision-Language Understanding Module (VLUM). PLM features an adaptive diffusion model architecture that leverages multi-stage knowledge learning to infrared transition from full-range to target wavelength. To improve V2IR translation, VLUM incorporates unified Vision-Language Understanding. We also collected a large infrared dataset, IR-500K, which includes 500,000 infrared images compiled by various scenes and objects under various environmental conditions. Through the combination of PLM, VLUM, and the extensive IR-500K dataset, DiffV2IR markedly improves the performance of V2IR. Experiments validate DiffV2IR's excellence in producing high-quality translations, establishing its efficacy and broad applicability. The code, dataset, and DiffV2IR model will be available at https://github.com/LidongWang-26/DiffV2IR.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. AnyMatch: Supercharging Universal Multi-Modal Image Matching with Large-Scale Single-View Images

    cs.CV 2026-06 unverdicted novelty 7.0

    AnyMatch synthesizes large-scale geometrically consistent multi-modal image pairs from single-view images, enabling fine-tuned matching networks to achieve substantial gains on benchmarks.

  2. UniTriGen: Unified Triplet Generation of Aligned Visible-Infrared-Label for Few-Shot RGB-T Semantic Segmentation

    cs.CV 2026-05 unverdicted novelty 7.0

    UniTriGen uses unified diffusion in a shared latent space plus lightweight adapters and scene-balanced sampling to produce high-quality aligned VIS-IR-Label triplets from limited paired data, improving few-shot RGB-T ...

  3. SpectraDINO: Bridging the Spectral Gap in Vision Foundation Models via Lightweight Adapters

    cs.CV 2026-05 unverdicted novelty 7.0

    SpectraDINO adapts frozen DINOv2 backbones to multispectral data via per-modality adapters and staged distillation with cosine, contrastive, patch, and neighborhood-structure losses, achieving SOTA on object detection...

  4. T-CLIP: Enabling Thermal Perception for Contrastive Language-Image Pretraining

    cs.CV 2026-05 unverdicted novelty 6.0

    T-CLIP introduces a physics-aware thermal captioning dataset (IR-Cap) and a decoupled dual-LoRA adaptation of CLIP that improves cross-modal retrieval on thermal benchmarks by separating scene-level and object-level t...

  5. MonoIR-RS: Infrared Remote Sensing Vision-Language Learning with CLIP and VLM Adaptation

    cs.CV 2026-07 conditional novelty 5.0

    MonoIR-RS synthesizes 600K infrared remote-sensing images from visible sources, rewrites captions to be IR-aware, and shows that IR-aware fine-tuning improves CLIP retrieval by up to 12.8 points and drives VLM infrare...

  6. AnyMatch: Supercharging Universal Multi-Modal Image Matching with Large-Scale Single-View Images

    cs.CV 2026-06 unverdicted novelty 5.0

    AnyMatch synthesizes geometrically consistent multi-modal training data from single-view images to improve matching networks on benchmarks.