Current video object removal methods suffer from prohibitive latency (minutes per video) and non-causal processing that prevents real-time interaction. We present StreamErase, enabling sub-second latency with up to 26 FPS streaming generation on a single GPU. Our approach first augments a text-to-video model with mask input to generate high-quality videos that erase target objects and synthesize coherent backgrounds, but does not perform inference on the fly. As such, we progressively transfer the erasing capability from a powerful bidirectional foundation model to an efficient unidirectional streaming eraser, enabling long-horizon erasing without sacrificing visual fidelity. Several key challenges arise when generating videos over long, potentially infinite horizons: (1) bridging the domain gap from training on finite length and extrapolating to long horizons, (2) sustaining high quality by preventing error accumulation, and (3) maintaining fast inference, without increasing computational cost as the context grows. To address these challenges, we carefully designed sliding-window causal attention with attention sinks. By incorporating self-rollout with attention sinks and KV cache rolling during training, we simulate inference-time extrapolations with a fixed context window, enabling constant-speed generation of arbitrarily long videos. Finally, we establish a dedicated benchmark, LongErase, for streaming long-video object removal. Our model achieves strong performance compared to existing video object erasing models and generalizes well to real-world video scenarios, uniquely enabling infinite-length streaming. With StreamErase, users can input a mask and see the erasing results unfold in real-time, delivering a truly interactive experience.
Figures & tables
Figure 1: Prior video diffusion erasing models typically operate offline to generate fixed-length sequences in parallel (top left). In contrast, our StreamErase enables streaming long-video generation (bottom left), supporting real-time erasing at 26.06 FPS with 0.87s latency (right).
Figure 2: The model architecture of StreamErase. We concatenate the noisy latents with the original input video and masks, consumed by a video inpainting model. Each DiT block performs cross-attention using the fused features x˙t as Query and eprompt from Region Guidance as Key/Value, producing attention maps that highlight affected regions. We aggregate attention maps from all blocks, which is supervised by the effect erasing loss LEE to focus on the affected area.
Figure 3: Overview of the proposed streaming video erasing framework. Our approach features a three-stage distillation pipeline that transfers erasing capabilities from a bidirectional teacher model to a 1-step causal student model. Each stage utilizes the backbone detailed in Fig. 2 .
Method
FPS
ROSE-Benchmark
VOR-Eval
PSNR↑
SSIM↑
LPIPS↓
FVD↓
PSNR↑
SSIM↑
LPIPS↓
FVD↓
ObjectClear
29.535
0.920
0.076
742.829
22.403
0.787
0.190
1391.858
OmniPaint
27.569
0.910
0.085
809.645
21.511
0.781
0.201
1439.867
Propainter
3.92
27.200
0.915
0.095
171.020
21.975
0.800
0.225
589.012
DiffuEraser
1.93
26.502
0.898
0.128
167.483
21.946
0.802
0.214
559.497
VACE
0.57
20.805
0.694
0.174
254.117
17.677
0.591
0.294
806.476
Table 1: Quantitative results on ROSE and VOR-Eval. The best and second-best results are highlighted in bold and underlined, respectively.
Figure 4: Qualitative comparison between StreamErase and existing approaches on real-world samples. Our model demonstrates superior ability and effectively handles complex object-environment interactions, including shadows, occlusions, and illumination changes.
Method
Evaluation Scores ↑
δDriftQuality↓
Motion Smoothness
Background Consistency
Temporal Flickering
Subject Consistency
Imaging Quality
Short-Video Comparison (5s)
DiffuEraser
0.968
0.917
0.939
0.947
0.614
-
ProPainter
0.972
0.925
0.935
0.951
0.602
-
ROSE
0.971
0.933
0.922
0.955
0.602
-
EffectErase
0.987
0.937
0.937
0.956
0.604
-
Table 2: Quantitative evaluation on LongErase. Comparison on 5-second clips and long-term performance on 30-second videos. The best score is bolded.
Table 7
Figure 5: Impact of Sparse Attention Patterns. Using longer clips (average 486 frames) from the LongErase, we ablate attention sink size and local window size in extrapolation scenarios. Having at least a single sink chunk is crucial, but more provides marginal benefit, while larger window sizes degrade performance as attending to long-past history allows errors to accumulate in context tokens.
Config
LongErase
LPIPS
δDriftQuality
Latency (s)
FPS
Ours base ( c3s1w1 )
0.163
0.05
0.87 ± 0.04
26.06 ± 1.62
+ Remove sink ( c3s0w1 )
0.254
0.27
0.85 ± 0.01
27.28 ± 1.70
+ Chunk Size 1 ( c1s1w1 )
0.319
0.72
0.42 ± 0.03
20.70 ± 2.97
Sliding window
0.181
0.08
0.91 ± 0.15
22.69 ± 3.29
Table 5: Long-video streaming design analysis on LongErase. c3s1w1 achieves the best visual quality and long-term stability.
Figure 6: Visualization of long-video eraseing and Streaming Demo. Our method supports flexible length video erasing while preserving high visual fidelity.
Appendix figures & tables4 assets
Supplementary material from the paper’s appendix.
Appendix
Figure 7: Speed and Quality Tradeoffs with Chunk Sizes and Sampling Steps. We visualize the latency-throughput relationship across varying chunk sizes and sampling steps (left), and video quality (LPIPS) across different sampling steps, using our default setup of c3s1w1 (right).
Figure 8: More qualitative comparison between StreamErase and existing approaches on real-world samples. Our model demonstrates superior ability and effectively handles complex object-environment interactions, including shadows, occlusions, and illumination changes.
Figure 9: Qualitative comparison across training stages.
Figure 10: Qualitative Comparison of Long-Video Erasing.
Video object removal presents a uniquely difficult editing challenge. Because a removal prompt specifies only what to erase rather than what to generate, the model must infer and reconstruct a highly specific occluded background entirely from the surrounding context. Existing training-free methods struggle with this because their editing mechanisms act primarily as localized erasers. They fail to actively synthesize the missing background details and often leave behind ghosting artifacts. To solve this, we propose TripleFlow, a training-free framework that tightly couples erasure and generation. It coordinates a source flow, a residual flow, and a synthesis flow throughout the entire process. By reusing a single target prediction, the residual flow isolates and suppresses the object, while the synthesis flow independently reconstructs the occluded background. Crucially, TripleFlow injects this newly synthesized background back into the editing trajectory at every step. This continuous feedback loop ensures that the generated structures actively guide the removal process, achieving seamless completion that is spatiotemporally consistent with the unedited scene. Extensive evaluations across five challenging benchmarks demonstrate that TripleFlow establishes a new state-of-the-art, significantly outperforming existing baselines in both reconstruction fidelity and temporal consistency.
Songhe Wang, Lifu Wei, Shuolin Xu +2
CSE Department, Penn State University · Department of Computer Science, The University of British Columbia, Canada · Department of Computing, Bournemouth University, United Kingdom +2
Video object removal frequently struggles to simultaneously eliminate target objects and their associated physical effects (e.g., smoke, reflections, light, and ripples) in out-of-domain scenarios due to complex spatiotemporal ambiguities. While existing methods primarily rely on spatial masks, they often fail to capture weakly correlated effects, and the potential of explicit textual guidance remains underexplored. Furthermore, a fundamental optimization conflict exists in removal models between high-level semantic generalization and precise pixel-level background preservation. To address these challenges, we propose GenEraser, a novel framework for generalized and high-fidelity video object and effect removal. First, we introduce a Multi-Conditional Mixture-of-Experts (MC-MoE) paired with Bipartite Text guidance to fully exploit the multimodal priors of Diffusion Transformers, significantly enhancing the identification of complex effects. Second, a Learnable Deep ``CFG'' Fusion mechanism (LD-CFG) is developed to adaptively balance the relative dominance of mask and textual conditions across diverse scenarios. Finally, we propose a Decoupled Expert Architecture, comprising a Locator and a Preserver, to mitigate the inherent trade-off between semantic generalization and pixel alignment. Extensive experiments demonstrate that our GenEraser surpasses recent state-of-the-art approaches, achieving significant quantitative improvements (e.g., 2.16 dB and 1.44 dB on the ROSE Benchmark and VOR-Eval, respectively) while maintaining exceptionally robust generalization in open-world scenarios. https://cyqii.github.io/GenEraser.github.io/
Yuqing Chen, Lin Liu, Haisu Wu +4
Tsinghua University, China · Huawei, China · Southeast University, China +2
Removing undesired concepts from large-scale text-to-image (T2I) and text-to-video (T2V) diffusion models while preserving overall generative quality remains a major challenge, particularly as modern models such as Stable Diffusion v3, Flux, and OpenSora employ flow-matching and transformer-based architectures and extend to long-horizon video generation. Existing concept erasure methods, designed for earlier T2I/T2V models, often fail to generalize to these paradigms. To address this issue, we propose EraseAnything++, a unified framework for concept erasure in both image and video diffusion models with flow-matching objectives. Central to our approach is formulating concept erasure as a constrained multi-objective optimization problem that explicitly balances concept removal with preservation of generative utility. To solve the resulting conflicting objectives, we introduce an efficient utility-preserving unlearning strategy based on implicit gradient surgery. Furthermore, by integrating LoRA-based parameter tuning with attention-level regularization, our method anchors erasure on key visual representations and propagates it consistently across spatial and temporal dimensions. In the video setting, we further enhance consistency through an anchor-and-propagate mechanism that initializes erasure on reference frames and enforces it throughout subsequent transformer layers, thereby mitigating temporal drift. Extensive experiments on both image and video benchmarks demonstrate that EraseAnything++ substantially outperforms prior methods in erasure effectiveness, generative fidelity, and temporal consistency, establishing a new state of the art for concept erasure in next-generation diffusion models.
Zhaoxin Fan, Nanxiang Jiang, Daiheng Gao +2
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, School of Artificial Intelligence, Beihang University. · University of Science and Technology of China.