FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching

• URL: http://arxiv.org/abs/2605.09003v2
• Date: Tue, 12 May 2026 06:32:46 GMT
• Title: FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching
• Abstract summary: diffusion-based object removal models indiscriminately denoise all tokens across all timesteps, ignoring that removal usually involves small foreground regions.<n>We propose a latent discriminator to implement Region-aware Adversarial Distillation (RAD), yielding a highly efficient few-step model named FlashClear.<n> Furthermore, tailored to few-step diffusion models, we propose FPAC (Foreground-Prioritized Asymmetric Attention and Caching), a training-free acceleration strategy.
• Score: 37.33145382932306
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, diffusion-based object removal models have achieved impressive results in eliminating objects and their associated visual effects. However, they indiscriminately denoise all tokens across all timesteps, ignoring that removal usually involves small foreground regions. This strategy introduces substantial computational overhead and prolonged inference times. To overcome this computational burden, we propose a latent discriminator to implement Region-aware Adversarial Distillation (RAD), yielding a highly efficient few-step model named FlashClear. Furthermore, tailored to few-step diffusion models, we propose FPAC (Foreground-Prioritized Asymmetric Attention and Caching), a training-free acceleration strategy. Extensive experiments demonstrate that our framework provides massive acceleration while maintaining or exceeding the performance of our base model, ObjectClear. Notably, on the OBER benchmark, our FlashClear achieves up to 8.26$\times$ and 122$\times$ speedup over ObjectClear and OmniPaint, respectively, while maintaining high visual quality and fidelity.

Related papers

• TurboClear: One-Step Object-Effect Removal via Region-Calibrated Distribution Matching and Fusion [40.189383154480154]
  We propose TurboClear, a one-step SDXL-based object-effect removal model.<n>During training, we design Region-Calibrated Distribution Matching (RDM) for region-aware distillation to preserve the teacher model's asymmetric edit-and-preserve behavior.<n>Experiments show that TurboClear significantly improves inference efficiency while maintaining competitive visual quality.
  arXiv  Detail & Related papers  (2026-08-02T14:56:13Z)
• OSOR: One-Step Diffusion Inpainting for Effect-Aware Object Removal [12.847574328137341]
  We present OSOR (One-Step Object Removal), which simultaneously achieves efficient, effect-aware, and mask-robust object removal.<n> OSOR introduces: (1) an occupancy-guided discriminator for precise boundary supervision, enabling stable single-step diffusion training; (2) an alpha head that leverages knowledge from pretrained diffusion models to predict appropriate removal regions with minimal overhead; and (3) a semantic-anchored verification pipeline (SAVP) that filters noisy instruction-based triplets to produce effect-aware supervision at scale.
  arXiv  Detail & Related papers  (2026-06-26T13:53:50Z)
• Motion-Aware Caching for Efficient Autoregressive Video Generation [73.27762884730272]
  MotionCache exploits inter-frame differences as a lightweight proxy for pixel-level motion characteristics.<n>Experiments on state-of-the-art models like SkyReels-V2 and MAGI-1 demonstrate that MotionCache achieves significant speedups.
  arXiv  Detail & Related papers  (2026-05-03T05:49:27Z)
• $D^3$-RSMDE: 40$\times$ Faster and High-Fidelity Remote Sensing Monocular Depth Estimation [72.9912717963138]
  Real-time, high-fidelity monocular depth estimation from remote sensing imagery is crucial for numerous applications.<n>Although using Vision Transformer (ViT) backbones for dense prediction is fast, they often exhibit poor perceptual quality.<n>We propose Depth Detail Diffusion for Remote Sensing Monocular Depth Estimation ($D3$-RSMDE) to overcome these limitations.<n>$D3$-RSMDE achieves a notable 11.85% reduction in the Learned Perceptual Image Patch Similarity (LPIPS) perceptual metric.
  arXiv  Detail & Related papers  (2026-03-17T10:50:36Z)
• TGM-VLA: Task-Guided Mixup for Sampling-Efficient and Robust Robotic Manipulation [42.52624620346963]
  We propose a novel holistic framework that significantly improves both model performance and training efficiency.<n>First, we redesign and optimize the sampling strategy, reducing memory consumption by 80% and accelerating training speed by 5x.<n>Second, we augment the model with a color inversion projection branch--a simple yet effective module that resolves the ambiguity of dark objects.
  arXiv  Detail & Related papers  (2026-02-28T12:16:20Z)
• Denoising as Path Planning: Training-Free Acceleration of Diffusion Models with DPCache [8.614492355393578]
  We propose DPCache, a training-free acceleration framework that formulates diffusion acceleration as a global path planning problem.<n> DPCache employs dynamic programming to select an optimal sequence of key timesteps that minimizes the total path cost while preserving trajectory fidelity.<n>Experiments on DiT, FLUX, and HunyuanVideo demonstrate that DPCache achieves strong acceleration with minimal quality loss.
  arXiv  Detail & Related papers  (2026-02-26T06:13:33Z)
• Lightning Fast Caching-based Parallel Denoising Prediction for Accelerating Talking Head Generation [50.04968365065964]
  Diffusion-based talking head models generate high-quality, photorealistic videos but suffer from slow inference.<n>We introduce Lightning-fast Caching-based Parallel denoising prediction (LightningCP)<n>We also propose Decoupled Foreground Attention (DFA) to further accelerate attention computations.
  arXiv  Detail & Related papers  (2025-08-25T02:58:39Z)
• Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping [13.846838416902575]
  A key bottleneck stems from the proliferation of visual tokens required for fine-grained image understanding.<n>We propose Skip-Vision, a unified framework addressing both training and inference inefficiencies in vision-language models.<n> Experimental results demonstrate that Skip-Vision reduces training time by up to 35%, inference FLOPs by 75%, and latency by 45%.
  arXiv  Detail & Related papers  (2025-03-26T04:16:48Z)
• Efficient Diffusion Model for Image Restoration by Residual Shifting [63.02725947015132]
  This study proposes a novel and efficient diffusion model for image restoration. Our method avoids the need for post-acceleration during inference, thereby avoiding the associated performance deterioration. Our method achieves superior or comparable performance to current state-of-the-art methods on three classical IR tasks.
  arXiv  Detail & Related papers  (2024-03-12T05:06:07Z)
• DeepCache: Accelerating Diffusion Models for Free [65.02607075556742]
  DeepCache is a training-free paradigm that accelerates diffusion models from the perspective of model architecture. DeepCache capitalizes on the inherent temporal redundancy observed in the sequential denoising steps of diffusion models. Under the same throughput, DeepCache effectively achieves comparable or even marginally improved results with DDIM or PLMS.
  arXiv  Detail & Related papers  (2023-12-01T17:01:06Z)

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.