Pith. sign in

REVIEW 6 cited by

Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models

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

arxiv 2411.07232 v2 pith:F44OOBPT submitted 2024-11-11 cs.CV cs.AIcs.GRcs.LG

classification cs.CVcs.AIcs.GRcs.LG
keywords objectadd-itimagemodelsaddingbalancediffusiongenerated
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Adding Object into images based on text instructions is a challenging task in semantic image editing, requiring a balance between preserving the original scene and seamlessly integrating the new object in a fitting location. Despite extensive efforts, existing models often struggle with this balance, particularly with finding a natural location for adding an object in complex scenes. We introduce Add-it, a training-free approach that extends diffusion models' attention mechanisms to incorporate information from three key sources: the scene image, the text prompt, and the generated image itself. Our weighted extended-attention mechanism maintains structural consistency and fine details while ensuring natural object placement. Without task-specific fine-tuning, Add-it achieves state-of-the-art results on both real and generated image insertion benchmarks, including our newly constructed "Additing Affordance Benchmark" for evaluating object placement plausibility, outperforming supervised methods. Human evaluations show that Add-it is preferred in over 80% of cases, and it also demonstrates improvements in various automated metrics.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. InsertAnywhere: Geometrically Grounded and Optics-Aware Video Object Insertion

    cs.CV 2025-12 conditional novelty 6.0 of 10

    InsertAnywhere inserts a reference object into arbitrary videos by reconstructing 4D geometry to propagate a user-given placement across frames and fine-tuning video diffusion on ROSE++, a removal-to-insertion dataset...

  2. FreeCus: Free Lunch Subject-driven Customization in Diffusion Transformers

    cs.CV 2025-07 conditional novelty 6.0 of 10

    FreeCus is a training-free method that combines pivotal attention sharing, reversed noise shifting, and MLLM captions to personalize Flux.1 text-to-image generation from a single reference image.

  3. Controllable Coupled Image Generation via Diffusion Models

    cs.CV 2025-06 reject novelty 6.0 of 10

    A cross-attention control method that couples backgrounds across multiple generated images by blending LLM-extracted background and entity prompts with a time-varying weight optimized for background similarity and tex...

  4. FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    FlowMo reduces temporal artifacts in video generation by guiding the denoising process to lower the maximum patch-wise variance of consecutive-frame differences in the latent space.

  5. LMP: Leveraging Motion Prior in Zero-Shot Video Generation with Diffusion Transformer

    cs.CV 2025-05 conditional novelty 6.0 of 10

    LMP transfers motion from a reference video to newly generated videos in text-to-video and image-to-video settings without training, using attention maps in a frozen diffusion transformer.

  6. StorySync: Training-Free Subject Consistency in Text-to-Image Generation via Region Harmonization

    cs.CV 2025-07 unverdicted novelty 5.0 of 10

    A training-free inference-time pipeline uses masked cross-image attention sharing and region harmonization to keep subjects consistent across generated story images.

Pith tools