# Addressing Detail Bottlenecks in Latent Diffusion for RGB-to-SWIR Image Translation

arXiv: https://arxiv.org/abs/2606.19961 · HTML: https://mlsanity.com/paper/2606.19961/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 24 of its 30 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 24 of 24)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Rethinking FID: Towards a Better Evaluation Metric for Image Generation](https://mlsanity.com/paper/2401.09603/) (2023)
- [BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models](https://mlsanity.com/paper/2205.07680/) (2022)
- [One-Step Image Translation with Text-to-Image Models](https://mlsanity.com/paper/2403.12036/) (2024)
- [Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2503.18352/) (2025)
- [Edge-guided Multi-domain RGB-to-TIR image Translation for Training Vision Tasks with Challenging Labels](https://mlsanity.com/paper/2301.12689/) (2023)
- [Boosting Latent Diffusion with Perceptual Objectives](https://mlsanity.com/paper/2411.04873/) (2024)
- [RASMD: RGB And SWIR Multispectral Driving Dataset for Robust Perception in Adverse Conditions](https://mlsanity.com/paper/2504.07603/) (2025)
- [Pix2Next: Leveraging Vision Foundation Models for RGB to NIR Image Translation](https://mlsanity.com/paper/2409.16706/) (2024)
- [Increasing the Diversity in RGB-to-Thermal Image Translation for Automotive Applications](https://mlsanity.com/paper/2509.23243/) (2025)

## Abstract (arXiv)

Latent diffusion models (LDMs) enable efficient image-to-image translation but discard fine spatial details during compression, degrading downstream perception tasks. We identify two bottlenecks: the autoencoder, which loses spatial information, and the conditioning pathway, which further degrades the source signal through naive downsampling. We propose two lightweight, backbone-agnostic fixes: a Source-Conditioned Autoencoder (SCAE) that injects high-resolution source features into the decoder via skip connections, and a Learnable Guidance Encoder (LGE) that replaces naive downsampling with a learned conditioning signal. Evaluated on RGB-to-SWIR translation for driving scenes with two denoiser backbones (U-Net and DiT), our approach improves detection mAP by up to 2x over the latent diffusion baseline, with up to 3.4x gains on small objects (COCO-small, <32^2 px^2), while achieving state-of-the-art FID. We further show that FID and detection performance are poorly correlated, motivating multi-axis evaluation. Results generalise zero-shot to the public RASMD benchmark. We will publicly release test data with annotations, all checkpoints, and training code.