Beyond Model Design: Data-Centric Training and Self-Ensemble for Gaussian Color Image Denoising

• URL: http://arxiv.org/abs/2604.11468v1
• Date: Mon, 13 Apr 2026 13:42:13 GMT
• Title: Beyond Model Design: Data-Centric Training and Self-Ensemble for Gaussian Color Image Denoising
• Abstract summary: This paper presents our solution to the NTIRE 2026 Image Denoising Challenge (Gaussian color image denoising at fixed noise level $= 50$)<n>We revisit the performance boundary of the mature Restormer architecture from two complementary directions: stronger data-centric training and more complete Test-Time capability release.<n>On the challenge validation set of 100 images, our final submission achieves 30.762 dB PSNR and 0.861 SSIM, improving over the public Restormer $!=!50$ pretrained baseline by up to 3.366 dB PSNR.
• Score: 7.344881114730842
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper presents our solution to the NTIRE 2026 Image Denoising Challenge (Gaussian color image denoising at fixed noise level $σ= 50$). Rather than proposing a new restoration backbone, we revisit the performance boundary of the mature Restormer architecture from two complementary directions: stronger data-centric training and more complete Test-Time capability release. Starting from the public Restormer $σ\!=\!50$ baseline, we expand the standard multi-dataset training recipe with larger and more diverse public image corpora and organize optimization into two stages. At inference, we apply $\times 8$ geometric self-ensemble to further release model capacity. A TLC-style local inference wrapper is retained for implementation consistency; however, systematic ablation reveals its quantitative contribution to be negligible in this setting. On the challenge validation set of 100 images, our final submission achieves 30.762 dB PSNR and 0.861 SSIM, improving over the public Restormer $σ\!=\!50$ pretrained baseline by up to 3.366 dB PSNR. Ablation studies show that the dominant gain originates from the expanded training corpus and the two-stage optimization schedule, and self-ensemble provides marginal but consistent improvement.

Related papers

• A Multi-View and Confusion-Guided Ensemble Framework for Robust Synthetic Image Attribution [0.6768558752130311]
  We present a multi-view and confusion-guided ensemble framework for the Synthetic Image Attribution Challenge of the DLMMDD Workshop at ICANN 2026.<n>Our approach integrates multiple complementary architectures, including FFT-ConvNeXt, DINOv2, CLIP, and Xception, to capture diverse attribution cues from frequency, semantic, and forensic perspectives.<n>We analyze the confusion patterns of the ensemble model and observe severe ambiguity between Stable Diffusion 3 and Stable Diffusion 3.5.
  arXiv  Detail & Related papers  (2026-09-10T07:54:25Z)
• Sharpening the Ensemble: An SSIM-Aligned Residual Refiner for Brain-MRI Inpainting Post-Processing [0.5626158829476339]
  Brain-MRI inpainting replaces a masked region of a scan with synthesized, anatomically plausible healthy tissue.<n>On the BraTS local-synthesis benchmark, which ranks submissions on the structural similarity index (SSIM), the peak signal-to-noise ratio, and the mean squared error (MSE) jointly, the strongest recent models are accurate.<n>We address this in post-processing, forming a deep ensemble of the two co-first-place 2025 models and training a lightweight residual refiner on the ensemble's own outputs.
  arXiv  Detail & Related papers  (2026-09-03T15:13:59Z)
• Ask, Solve, Generate: Self-Evolving Unified Multimodal Understanding and Generation via Self-Consistency Rewards [52.42920996842378]
  Most unified large multimodal models (LMMs) that support both visual understanding and image generation rely on curated post-training supervision.<n>We propose a self-evolving training framework with three internal roles: a Proposer that generates visual questions, a solver that answers and evaluates them, and a Generator that synthesizes images.<n>For image generation, we design a multi-scale internal evaluation scheme that combines question-answer fidelity scoring with cycle-consistent captioning.
  arXiv  Detail & Related papers  (2026-06-25T17:59:57Z)
• MARBLE: Multi-Aspect Reward Balance for Diffusion RL [71.6241143519038]
  Reinforcement learning has become the dominant approach for aligning diffusion models with human preferences.<n>Existing practice deal with multiple rewards by training one specialist model per reward.<n>We propose MARBLE, a gradient-space optimization framework that maintains independent advantage estimators for each reward.
  arXiv  Detail & Related papers  (2026-05-07T16:20:42Z)
• Image Tokenizer Needs Post-Training [76.91832192778732]
  We propose a novel tokenizer training scheme, focusing on improving latent space construction and decoding respectively.<n>Specifically, we propose a plug-and-play tokenizer training scheme, which significantly enhances the robustness of tokenizer.<n>We further optimize the tokenizer decoder regarding a well-trained generative model to mitigate the distribution difference between generated and reconstructed tokens.
  arXiv  Detail & Related papers  (2025-09-15T21:38:03Z)
• Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think [63.25744258438214]
  REPA and its variants effectively mitigate training challenges in diffusion models by incorporating external visual representations from pretrained models.<n>We argue that the external alignment, which is absent during the entire denoising inference process, falls short of fully harnessing the potential of discriminative representations.<n>We propose Representation Entanglement for Generation (REG), which entangles low-level image latents with a single high-level class token from pretrained foundation models for denoising.
  arXiv  Detail & Related papers  (2025-07-02T08:29:18Z)
• Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards [52.90573877727541]
  reinforcement learning (RL) has been considered for diffusion model fine-tuning.<n>RL's effectiveness is limited by the challenge of sparse reward.<n>$textB2text-DiffuRL$ is compatible with existing optimization algorithms.
  arXiv  Detail & Related papers  (2025-03-14T09:45:19Z)
• You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs [13.133574069588896]
  YOSO is a novel generative model designed for rapid, scalable, and high-fidelity one-step image synthesis with high training stability and mode coverage.<n>We show that our method can serve as a one-step generation model training from scratch with competitive performance.<n>In particular, we show that the YOSO-PixArt-$alpha$ can generate images in one step trained on 512 resolution, with the capability of adapting to 1024 resolution without extra explicit training, requiring only 10 A800 days for fine-tuning.
  arXiv  Detail & Related papers  (2024-03-19T17:34:27Z)
• Compensation Sampling for Improved Convergence in Diffusion Models [12.311434647047427]
  Diffusion models achieve remarkable quality in image generation, but at a cost. Iterative denoising requires many time steps to produce high fidelity images. We argue that the denoising process is crucially limited by an accumulation of the reconstruction error due to an initial inaccurate reconstruction of the target data.
  arXiv  Detail & Related papers  (2023-12-11T10:39:01Z)
• ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models [59.90959789767886]
  We show that optimizing consistency training loss minimizes the Wasserstein distance between target and generated distributions. By incorporating a discriminator into the consistency training framework, our method achieves improved FID scores on CIFAR10 and ImageNet 64$times$64 and LSUN Cat 256$times$256 datasets.
  arXiv  Detail & Related papers  (2023-11-23T16:49:06Z)
• Denoising Diffusion Probabilistic Models for Robust Image Super-Resolution in the Wild [2.190237353315235]
  This paper introduces SR3+, a diffusion-based model for blind super-resolution, establishing a new state-of-the-art. We advocate self-supervised training with a combination of composite, parameterized degradations for self-supervised training, and noise-conditioing augmentation during training and testing. With these innovations, a large-scale convolutional architecture, and large-scale datasets, SR3+ greatly outperforms SR3.
  arXiv  Detail & Related papers  (2023-02-15T18:56:06Z)

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.