Guidance Watermarking for Diffusion Models

This paper introduces a novel watermarking method for diffusion models. It is based on guiding the diffusion process using the gradient computed from any off-the-shelf watermark decoder. The gradient computation encompasses different image augmentations, increasing robustness to attacks against which the decoder was not originally robust, without retraining or fine-tuning. Our method effectively convert any \textit{post-hoc} watermarking scheme into an in-generation embedding along the diffusion process. We show that this approach is complementary to watermarking techniques modifying the variational autoencoder at the end of the diffusion process. We validate the methods on different diffusion models and detectors. The watermarking guidance does not significantly alter the generated image for a given seed and prompt, preserving both the diversity and quality of generation.

Bézier Meets Diffusion: Robust Generation Across Domains for Medical Image Segmentation

Training robust learning algorithms across different medical imaging modalities is challenging due to the large domain gap. Unsupervised domain adaptation (UDA) mitigates this problem by using annotated images from the source domain and unlabeled images from the target domain to train the deep models. Existing approaches often rely on GAN-based style transfer, but these methods struggle to capture cross-domain mappings in regions with high variability. In this paper, we propose a unified framework, B\'ezier Meets Diffusion, for cross-domain image generation. First, we introduce a B\'ezier-curve-based style transfer strategy that effectively reduces the domain gap between source and target domains. The transferred source images enable the training of a more robust segmentation model across domains. Thereafter, using pseudo-labels generated by this segmentation model on the target domain, we train a conditional diffusion model (CDM) to synthesize high-quality, labeled target-domain images. To mitigate the impact of noisy pseudo-labels, we further develop an uncertainty-guided score matching method that improves the robustness of CDM training. Extensive experiments on public datasets demonstrate that our approach generates realistic labeled images, significantly augmenting the target domain and improving segmentation performance.

CCNeXt: An Effective Self-Supervised Stereo Depth Estimation Approach

Depth Estimation plays a crucial role in recent applications in robotics, autonomous vehicles, and augmented reality. These scenarios commonly operate under constraints imposed by computational power. Stereo image pairs offer an effective solution for depth estimation since it only needs to estimate the disparity of pixels in image pairs to determine the depth in a known rectified system. Due to the difficulty in acquiring reliable ground-truth depth data across diverse scenarios, self-supervised techniques emerge as a solution, particularly when large unlabeled datasets are available. We propose a novel self-supervised convolutional approach that outperforms existing state-of-the-art Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) while balancing computational cost. The proposed CCNeXt architecture employs a modern CNN feature extractor with a novel windowed epipolar cross-attention module in the encoder, complemented by a comprehensive redesign of the depth estimation decoder. Our experiments demonstrate that CCNeXt achieves competitive metrics on the KITTI Eigen Split test data while being 10.18$\times$ faster than the current best model and achieves state-of-the-art results in all metrics in the KITTI Eigen Split Improved Ground Truth and Driving Stereo datasets when compared to recently proposed techniques. To ensure complete reproducibility, our project is accessible at \href{https://github.com/alelopes/CCNext}{\texttt{https://github.com/alelopes/CCNext}}.

Zero-Effort Image-to-Music Generation: An Interpretable RAG-based VLM Approach

Recently, Image-to-Music (I2M) generation has garnered significant attention, with potential applications in fields such as gaming, advertising, and multi-modal art creation. However, due to the ambiguous and subjective nature of I2M tasks, most end-to-end methods lack interpretability, leaving users puzzled about the generation results. Even methods based on emotion mapping face controversy, as emotion represents only a singular aspect of art. Additionally, most learning-based methods require substantial computational resources and large datasets for training, hindering accessibility for common users. To address these challenges, we propose the first Vision Language Model (VLM)-based I2M framework that offers high interpretability and low computational cost. Specifically, we utilize ABC notation to bridge the text and music modalities, enabling the VLM to generate music using natural language. We then apply multi-modal Retrieval-Augmented Generation (RAG) and self-refinement techniques to allow the VLM to produce high-quality music without external training. Furthermore, we leverage the generated motivations in text and the attention maps from the VLM to provide explanations for the generated results in both text and image modalities. To validate our method, we conduct both human studies and machine evaluations, where our method outperforms others in terms of music quality and music-image consistency, indicating promising results. Our code is available at https://github.com/RS2002/Image2Music .

Deep Learning-Based Cross-Anatomy CT Synthesis Using Adapted nnResU-Net with Anatomical Feature Prioritized Loss

We present a patch-based 3D nnUNet adaptation for MR to CT and CBCT to CT image translation using the multicenter SynthRAD2025 dataset, covering head and neck (HN), thorax (TH), and abdomen (AB) regions. Our approach leverages two main network configurations: a standard UNet and a residual UNet, both adapted from nnUNet for image synthesis. The Anatomical Feature-Prioritized (AFP) loss was introduced, which compares multilayer features extracted from a compact segmentation network trained on TotalSegmentator labels, enhancing reconstruction of clinically relevant structures. Input volumes were normalized per-case using zscore normalization for MRIs, and clipping plus dataset level zscore normalization for CBCT and CT. Training used 3D patches tailored to each anatomical region without additional data augmentation. Models were trained for 1000 and 1500 epochs, with AFP fine-tuning performed for 500 epochs using a combined L1+AFP objective. During inference, overlapping patches were aggregated via mean averaging with step size of 0.3, and postprocessing included reverse zscore normalization. Both network configurations were applied across all regions, allowing consistent model design while capturing local adaptations through residual learning and AFP loss. Qualitative and quantitative evaluation revealed that residual networks combined with AFP yielded sharper reconstructions and improved anatomical fidelity, particularly for bone structures in MR to CT and lesions in CBCT to CT, while L1only networks achieved slightly better intensity-based metrics. This methodology provides a stable solution for cross modality medical image synthesis, demonstrating the effectiveness of combining the automatic nnUNet pipeline with residual learning and anatomically guided feature losses.

RAPID^3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer

Diffusion Transformers (DiTs) excel at visual generation yet remain hampered by slow sampling. Existing training-free accelerators - step reduction, feature caching, and sparse attention - enhance inference speed but typically rely on a uniform heuristic or a manually designed adaptive strategy for all images, leaving quality on the table. Alternatively, dynamic neural networks offer per-image adaptive acceleration, but their high fine-tuning costs limit broader applicability. To address these limitations, we introduce RAPID3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformers, a framework that delivers image-wise acceleration with zero updates to the base generator. Specifically, three lightweight policy heads - Step-Skip, Cache-Reuse, and Sparse-Attention - observe the current denoising state and independently decide their corresponding speed-up at each timestep. All policy parameters are trained online via Group Relative Policy Optimization (GRPO) while the generator remains frozen. Meanwhile, an adversarially learned discriminator augments the reward signal, discouraging reward hacking by boosting returns only when generated samples stay close to the original model's distribution. Across state-of-the-art DiT backbones, including Stable Diffusion 3 and FLUX, RAPID3 achieves nearly 3x faster sampling with competitive generation quality.

EfficientDepth: A Fast and Detail-Preserving Monocular Depth Estimation Model

Monocular depth estimation (MDE) plays a pivotal role in various computer vision applications, such as robotics, augmented reality, and autonomous driving. Despite recent advancements, existing methods often fail to meet key requirements for 3D reconstruction and view synthesis, including geometric consistency, fine details, robustness to real-world challenges like reflective surfaces, and efficiency for edge devices. To address these challenges, we introduce a novel MDE system, called EfficientDepth, which combines a transformer architecture with a lightweight convolutional decoder, as well as a bimodal density head that allows the network to estimate detailed depth maps. We train our model on a combination of labeled synthetic and real images, as well as pseudo-labeled real images, generated using a high-performing MDE method. Furthermore, we employ a multi-stage optimization strategy to improve training efficiency and produce models that emphasize geometric consistency and fine detail. Finally, in addition to commonly used objectives, we introduce a loss function based on LPIPS to encourage the network to produce detailed depth maps. Experimental results demonstrate that EfficientDepth achieves performance comparable to or better than existing state-of-the-art models, with significantly reduced computational resources.

No-Reference Image Contrast Assessment with Customized EfficientNet-B0

Image contrast was a fundamental factor in visual perception and played a vital role in overall image quality. However, most no reference image quality assessment NR IQA models struggled to accurately evaluate contrast distortions under diverse real world conditions. In this study, we proposed a deep learning based framework for blind contrast quality assessment by customizing and fine-tuning three pre trained architectures, EfficientNet B0, ResNet18, and MobileNetV2, for perceptual Mean Opinion Score, along with an additional model built on a Siamese network, which indicated a limited ability to capture perceptual contrast distortions. Each model is modified with a contrast-aware regression head and trained end to end using targeted data augmentations on two benchmark datasets, CID2013 and CCID2014, containing synthetic and authentic contrast distortions. Performance is evaluated using Pearson Linear Correlation Coefficient and Spearman Rank Order Correlation Coefficient, which assess the alignment between predicted and human rated scores. Among these three models, our customized EfficientNet B0 model achieved state-of-the-art performance with PLCC = 0.9286 and SRCC = 0.9178 on CCID2014 and PLCC = 0.9581 and SRCC = 0.9369 on CID2013, surpassing traditional methods and outperforming other deep baselines. These results highlighted the models robustness and effectiveness in capturing perceptual contrast distortion. Overall, the proposed method demonstrated that contrast aware adaptation of lightweight pre trained networks can yield a high performing, scalable solution for no reference contrast quality assessment suitable for real time and resource constrained applications.

RACap: Relation-Aware Prompting for Lightweight Retrieval-Augmented Image Captioning

Recent retrieval-augmented image captioning methods incorporate external knowledge to compensate for the limitations in comprehending complex scenes. However, current approaches face challenges in relation modeling: (1) the representation of semantic prompts is too coarse-grained to capture fine-grained relationships; (2) these methods lack explicit modeling of image objects and their semantic relationships. To address these limitations, we propose RACap, a relation-aware retrieval-augmented model for image captioning, which not only mines structured relation semantics from retrieval captions, but also identifies heterogeneous objects from the image. RACap effectively retrieves structured relation features that contain heterogeneous visual information to enhance the semantic consistency and relational expressiveness. Experimental results show that RACap, with only 10.8M trainable parameters, achieves superior performance compared to previous lightweight captioning models.

DistillMatch: Leveraging Knowledge Distillation from Vision Foundation Model for Multimodal Image Matching

Multimodal image matching seeks pixel-level correspondences between images of different modalities, crucial for cross-modal perception, fusion and analysis. However, the significant appearance differences between modalities make this task challenging. Due to the scarcity of high-quality annotated datasets, existing deep learning methods that extract modality-common features for matching perform poorly and lack adaptability to diverse scenarios. Vision Foundation Model (VFM), trained on large-scale data, yields generalizable and robust feature representations adapted to data and tasks of various modalities, including multimodal matching. Thus, we propose DistillMatch, a multimodal image matching method using knowledge distillation from VFM. DistillMatch employs knowledge distillation to build a lightweight student model that extracts high-level semantic features from VFM (including DINOv2 and DINOv3) to assist matching across modalities. To retain modality-specific information, it extracts and injects modality category information into the other modality's features, which enhances the model's understanding of cross-modal correlations. Furthermore, we design V2I-GAN to boost the model's generalization by translating visible to pseudo-infrared images for data augmentation. Experiments show that DistillMatch outperforms existing algorithms on public datasets.