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

• URL: http://arxiv.org/abs/2606.19961v1
• Date: Thu, 18 Jun 2026 08:59:03 GMT
• Title: Addressing Detail Bottlenecks in Latent Diffusion for RGB-to-SWIR Image Translation
• Abstract summary: Latent diffusion models (LDMs) enable efficient image-to-image translation but discard fine details during compression.<n>We identify two bottlenecks: the autoencoder, which loses information, and the conditioning pathway, which further degrades the source signal through naive downsampling.<n>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 (LGE) that replaces naive downsampling with a learned conditioning signal.
• Score: 3.8750462550584044
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• SPLIT: Training-Free AI-Generated and Partially Edited Video Detection via Spatial Patch-Level Incoherence and Temporal Roughness [4.774658730084455]
  We introduce a training-free detector that operates on patch tokens from a frozen vision encoder to detect both fully generated and partially edited videos.<n>SPLIT computes two complementary signals: Two-step Temporal Roughness (TTR) and Local Spatial Motion Incoherence (LSMI)<n>We propose a service-aligned evaluation protocol based on Fake Recall at fixed FPR with real-only threshold calibration and cross-real threshold transfer.
  arXiv  Detail & Related papers  (2026-07-03T02:34:50Z)
• DCCS-Det: Directional Context and Cross-Scale-Aware Detector for Infrared Small Target [4.318503966844226]
  Infrared small target detection (IRSTD) is critical for applications like remote sensing and surveillance.<n>We propose DCCS-Det, a novel detector that incorporates a Dual-stream Saliency Enhancement (DSE) block and a Latent-aware Semantic Extraction and Aggregation (LaSEA) module.<n>Experiments show that DCCS-Det achieves state-of-the-art detection accuracy with competitive efficiency across multiple datasets.
  arXiv  Detail & Related papers  (2026-01-23T03:53:59Z)
• NeRF-Det++: Incorporating Semantic Cues and Perspective-aware Depth Supervision for Indoor Multi-View 3D Detection [72.0098999512727]
  NeRF-Det has achieved impressive performance in indoor multi-view 3D detection by utilizing NeRF to enhance representation learning. We present three corresponding solutions, including semantic enhancement, perspective-aware sampling, and ordinal depth supervision. The resulting algorithm, NeRF-Det++, has exhibited appealing performance in the ScanNetV2 and AR KITScenes datasets.
  arXiv  Detail & Related papers  (2024-02-22T11:48:06Z)
• Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection [46.041193889845474]
  Ray Denoising is an innovative method that enhances detection accuracy by strategically sampling along camera rays to construct hard negative examples. Ray Denoising is designed as a plug-and-play module, compatible with any DETR-style multi-view 3D detectors. It achieves a 1.9% improvement in mean Average Precision (mAP) over the state-of-the-art StreamPETR method on the NuScenes dataset.
  arXiv  Detail & Related papers  (2024-02-06T02:17:44Z)
• Global Context Aggregation Network for Lightweight Saliency Detection of Surface Defects [70.48554424894728]
  We develop a Global Context Aggregation Network (GCANet) for lightweight saliency detection of surface defects on the encoder-decoder structure. First, we introduce a novel transformer encoder on the top layer of the lightweight backbone, which captures global context information through a novel Depth-wise Self-Attention (DSA) module. The experimental results on three public defect datasets demonstrate that the proposed network achieves a better trade-off between accuracy and running efficiency compared with other 17 state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-09-22T06:19:11Z)
• SALISA: Saliency-based Input Sampling for Efficient Video Object Detection [58.22508131162269]
  We propose SALISA, a novel non-uniform SALiency-based Input SAmpling technique for video object detection. We show that SALISA significantly improves the detection of small objects.
  arXiv  Detail & Related papers  (2022-04-05T17:59:51Z)
• Reducing Redundancy in the Bottleneck Representation of the Autoencoders [98.78384185493624]
  Autoencoders are a type of unsupervised neural networks, which can be used to solve various tasks. We propose a scheme to explicitly penalize feature redundancies in the bottleneck representation. We tested our approach across different tasks: dimensionality reduction using three different dataset, image compression using the MNIST dataset, and image denoising using fashion MNIST.
  arXiv  Detail & Related papers  (2022-02-09T18:48:02Z)
• The KFIoU Loss for Rotated Object Detection [115.334070064346]
  In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss. Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU. The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
  arXiv  Detail & Related papers  (2022-01-29T10:54:57Z)
• TRACER: Extreme Attention Guided Salient Object Tracing Network [3.2434811678562676]
  We propose TRACER, which detects salient objects with explicit edges by incorporating attention guided tracing modules. A comparison with 13 existing methods reveals that TRACER achieves state-of-the-art performance on five benchmark datasets.
  arXiv  Detail & Related papers  (2021-12-14T13:20:07Z)
• EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentation [62.210091681352914]
  We study multi-sensor fusion for 3D semantic segmentation for many applications, such as autonomous driving and robotics. In this work, we investigate a collaborative fusion scheme called perception-aware multi-sensor fusion (PMF) We propose a two-stream network to extract features from the two modalities separately. The extracted features are fused by effective residual-based fusion modules.
  arXiv  Detail & Related papers  (2021-06-21T10:47:26Z)
• Dense Label Encoding for Boundary Discontinuity Free Rotation Detection [69.75559390700887]
  This paper explores a relatively less-studied methodology based on classification. We propose new techniques to push its frontier in two aspects. Experiments and visual analysis on large-scale public datasets for aerial images show the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-11-19T05:42:02Z)
• LR-CNN: Local-aware Region CNN for Vehicle Detection in Aerial Imagery [43.91170581467171]
  State-of-the-art object detection approaches have difficulties detecting dense, small targets with arbitrary orientation in large aerial images. We present the Local-aware Region Convolutional Neural Network (LR-CNN), a novel two-stage approach for vehicle detection in aerial imagery.
  arXiv  Detail & Related papers  (2020-05-28T19:57:34Z)

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.