REVIEW 18 cited by
MiniMax-Remover: Taming Bad Noise Helps Video Object Removal
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
MiniMax-Remover: Taming Bad Noise Helps Video Object Removal
read the original abstract
Recent advances in video diffusion models have driven rapid progress in video editing techniques. However, video object removal, a critical subtask of video editing, remains challenging due to issues such as hallucinated objects and visual artifacts. Furthermore, existing methods often rely on computationally expensive sampling procedures and classifier-free guidance (CFG), resulting in slow inference. To address these limitations, we propose MiniMax-Remover, a novel two-stage video object removal approach. Motivated by the observation that text condition is not best suited for this task, we simplify the pretrained video generation model by removing textual input and cross-attention layers, resulting in a more lightweight and efficient model architecture in the first stage. In the second stage, we distilled our remover on successful videos produced by the stage-1 model and curated by human annotators, using a minimax optimization strategy to further improve editing quality and inference speed. Specifically, the inner maximization identifies adversarial input noise ("bad noise") that makes failure removals, while the outer minimization step trains the model to generate high-quality removal results even under such challenging conditions. As a result, our method achieves a state-of-the-art video object removal results with as few as 6 sampling steps and doesn't rely on CFG, significantly improving inference efficiency. Extensive experiments demonstrate the effectiveness and superiority of MiniMax-Remover compared to existing methods. Codes and Videos are available at: https://minimax-remover.github.io.
Forward citations
Cited by 18 Pith papers
-
JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation
JAVEdit-100k is the first large-scale dataset for instruction-guided joint audio-visual video editing, accompanied by JAVEditBench and the JAVEdit model that outperforms baselines on five of six metrics.
-
PROVE: A Perceptual RemOVal cohErence Benchmark for Visual Media
PROVE proposes RC metrics for perceptual removal coherence and releases PROVE-Bench to better align automatic scores with human judgments on object removal tasks.
-
PROVE: A Perceptual RemOVal cohErence Benchmark for Visual Media
Removal Coherence (RC) metrics, which compare local feature distributions in masked versus background regions via sliding-window MMD, align with human judgments of object-removal quality substantially better than exis...
-
VideoCoF: Unified Video Editing with Temporal Reasoner
VideoCoF adds an explicit reasoning step using edit-region latents in video diffusion models to enable precise mask-free editing and motion alignment with only 50k training pairs.
-
FlexComposer: Unified Video Compositing from Images to Dynamic Footage with Flexible Trajectory Control
A single video-diffusion framework composites both static images and dynamic footage along user-defined trajectories by transporting canonical foreground latents directly into the background latent sequence.
-
From Draft to Draft-Free: One-Step Video Object Removal via Privileged Distillation and Fast Planting
A one-step, draft-free video object removal model trained by distilling a ground-truth-conditioned teacher reaches comparable or better quality than multi-step diffusion methods while running in about 1 second.
-
SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion
SimInsert is a training-free video object insertion technique that decouples the task into single-frame editing and semantic motion description, using image-to-video diffusion models with non-invasive guidance to achi...
-
Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing
Occlusion-aware keyframe selection via structural, cycle-consistent tracking, and vision-language criteria improves diffusion video editing robustness without manual annotations.
-
LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention
LIVEditor-14B applies a new sparse attention method (ISA) that prunes context and uses query-sharpness routing to cut attention latency ~60% with no loss in editing quality on standard benchmarks.
-
CLEAR: Context-Aware Learning with End-to-End Mask-Free Inference for Adaptive Video Subtitle Removal
CLEAR achieves end-to-end mask-free video subtitle removal via dual-encoder self-supervised orthogonality and LoRA-based generation feedback, delivering +6.77 dB PSNR gains and strong zero-shot multilingual performance.
-
Under One Sun: Multi-Object Generative Perception of Materials and Illumination
Factorizing video editing into semantic-token anchoring and motion-restoration pre-training produces strong zero-shot and SOTA open-source instruction-guided video edits without heavy external structural priors.
-
Learning Stochastic Bridges for Video Object Removal via Video-to-Video Translation
A stochastic bridge model treats video object removal as video-to-video translation, starting from the source video rather than Gaussian noise, with adaptive mask modulation and a new benchmark.
-
O-DisCo-Edit: Object Distortion Control for Unified Realistic Video Editing
A video editor trained on randomly distorted objects, then steered by adaptive noise at inference, is claimed to surpass dedicated and unified editors across eight tasks with far less training.
-
GenEraser: Generalizable Video Object Removal via Balanced Text-Mask Guidance and Decoupled Locator-Preserver
GenEraser proposes MC-MoE with bipartite text guidance, LD-CFG fusion, and a decoupled locator-preserver architecture for generalizable video object and effect removal, claiming 2.16 dB and 1.44 dB gains on ROSE and V...
-
Smart-Insertion-V: Photorealistic Video Insertion via a Closed-Loop Feedback Dual-Stream Framework
Smart-Insertion-V is a dual-stream closed-loop framework with Dual-World-View RoPE and a Decoupled Guidance Module that inserts reference objects into videos while achieving stylistic harmony despite domain gaps.
-
Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing
A new keyframe selection framework combines structural, tracking, and semantic criteria to select reliable anchor frames for diffusion-based video editing under occlusion.
-
Tuning-free Instruction-based Video Editing Via Structural Noise Initialization and Guidance
Proposes SNIS and NGM to enable tuning-free instruction-based video editing with improved visual quality and claimed SOTA results.
-
LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention
ISA prunes low-saliency context tokens and routes queries by sharpness to either full or 0-th order Taylor sparse attention, enabling LIVEditor to cut attention latency ~60% while beating prior video editing methods o...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.