Skip to content

๐Ÿ–ผ๏ธ Image Restoration

๐Ÿงช ICML2025 ยท 5 paper notes

๐Ÿ“Œ Same area in other venues: ๐Ÿ“ท CVPR2026 (135) ยท ๐Ÿ”ฌ ICLR2026 (61) ยท ๐Ÿงช ICML2026 (21) ยท ๐Ÿค– AAAI2026 (10) ยท ๐Ÿง  NeurIPS2025 (26) ยท ๐Ÿ“น ICCV2025 (31)

๐Ÿ”ฅ Top topics: Diffusion Models ร—2

Adaptive Estimation and Learning under Temporal Distribution Shift

Proposes an estimation algorithm based on wavelet soft-thresholding that achieves optimal pointwise estimation error bounds under temporal distribution shift without prior knowledge. It establishes a connection between sequence non-stationarity and sparsity in the wavelet domain, applying it to binary classification and total variation denoising under distribution shift.

ฮต-VAE: Denoising as Visual Decoding

This paper proposes ฮต-VAE, which replaces the single-step deterministic decoder in traditional autoencoders with a diffusion/denoising process to implement "denoising as decoding." Under the same compression rate, the reconstruction quality is improved by 40% and downstream generation quality is enhanced by 22%. Alternatively, it achieves a 2.3ร— inference acceleration by increasing the compression rate while maintaining the same generation quality.

Evaluating Deepfake Detectors in the Wild

A new dataset containing over 500k high-quality deepfake images is constructed. By introducing in-the-wild enhancements such as JPEG compression, resolution reduction, and image restoration, six open-source deepfake detectors are systematically evaluated, revealing that fewer than half achieved an AUC > 60%, with the lowest performance around 50% (random-guess level).

HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration

This work proposes the HarmoniCa framework, which addresses the misalignment between training and inference in existing learning-based feature caching methods through two core designs: Step-Wise Denoising Training (SDT) and Image Error Proxy-Guided Objective (IEPO). It achieves over a 40% reduction in latency (2.07ร— theoretical speedup) without compromising generation quality across 8 different models including PixArt-ฮฑ.

TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representation

TimeDART is proposed to unify autoregressive modeling and denoising diffusion processes within a self-supervised pre-training framework. It captures long-term dynamic evolution via a causal Transformer encoder and fine-grained local patterns through patch-level diffusion denoising, outperforming existing methods on both forecasting and classification tasks.