REVIEW 13 cited by
Insert Anything: Image Insertion via In-Context Editing in DiT
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
Insert Anything: Image Insertion via In-Context Editing in DiT
read the original abstract
This work presents Insert Anything, a unified framework for reference-based image insertion that seamlessly integrates objects from reference images into target scenes under flexible, user-specified control guidance. Instead of training separate models for individual tasks, our approach is trained once on our new AnyInsertion dataset--comprising 120K prompt-image pairs covering diverse tasks such as person, object, and garment insertion--and effortlessly generalizes to a wide range of insertion scenarios. Such a challenging setting requires capturing both identity features and fine-grained details, while allowing versatile local adaptations in style, color, and texture. To this end, we propose to leverage the multimodal attention of the Diffusion Transformer (DiT) to support both mask- and text-guided editing. Furthermore, we introduce an in-context editing mechanism that treats the reference image as contextual information, employing two prompting strategies to harmonize the inserted elements with the target scene while faithfully preserving their distinctive features. Extensive experiments on AnyInsertion, DreamBooth, and VTON-HD benchmarks demonstrate that our method consistently outperforms existing alternatives, underscoring its great potential in real-world applications such as creative content generation, virtual try-on, and scene composition.
Forward citations
Cited by 13 Pith papers
-
BFS: Back-to-Front Layered Image Synthesis via Knowledge Transfer
BFS is a dual-branch diffusion model with bidirectional knowledge transfer that synthesizes coherent foreground layers with visual effects using a two-stage training scheme on unlayered data.
-
UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models
UniGeo unifies geometric guidance across three levels in video models to reduce geometric drift and improve consistency in camera-controllable image editing.
-
Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification
Rule-VLN is the first large-scale benchmark injecting 177 regulatory categories into an urban environment, and the proposed SNRM module equips pre-trained VLN agents with zero-shot semantic reasoning and detour planni...
-
Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer
Durian introduces a dual-reference diffusion model trained via self-reconstruction on video frames to enable cross-identity attribute transfer in portrait animations, supporting multi-attribute composition and interpolation.
-
Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification
Rule-VLN injects 177 regulatory signs into Touchdown-scale urban graphs; SNRM’s VLM perception plus mental-map detours cuts constraint violations ~19% and raises task completion ~6% zero-shot.
-
ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning
ICDepth adapts text-to-video diffusion transformers for video depth estimation via in-context conditioning, achieving SOTA results on benchmarks with 6-13x less training data than prior generative methods.
-
UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models
UniGeo adds unified geometric guidance at three levels in video models to reduce geometric drift and improve structural fidelity in camera-controllable image editing.
-
Is This Edit Correct? A Multi-Dimensional Benchmark for Reasoning-Aware Image Editing
SOTA diffusion image editors score poorly on implicit physical, environmental, cultural, causal, and referential constraints, which a lightweight reasoning-guided post-edit can partially fix.
-
CatalogStitch: Dimension-Aware and Occlusion-Preserving Object Compositing for Catalog Image Generation
CatalogStitch provides dimension-aware mask computation and occlusion-aware hybrid restoration to automate corrections in generative object compositing for catalog images.
-
HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images
HiFi-Inpaint delivers state-of-the-art detail-preserving human-product images by adding Shared Enhancement Attention and Detail-Aware Loss to reference-based inpainting on a new 40K dataset.
-
Insert In Style: A Zero-Shot Generative Framework for Harmonious Cross-Domain Object Composition
Insert In Style is a zero-shot framework that disentangles identity, style, and composition via multi-stage training, masked attention, and prior preservation to enable harmonious cross-domain object insertion in images.
-
ModaFlow: Modality-Aware Flow Matching for High-Fidelity Virtual Try-On
ModaFlow is a modality-aware flow matching framework for virtual try-on that uses visual embeddings for structural guidance, text embeddings with adaptive CFG, regularization losses, and stochastic mask sampling to ac...
-
UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models
UniGeo improves camera-controllable image editing by injecting point cloud geometry into a video diffusion model at the representation, architecture, and loss levels, achieving state-of-the-art geometric consistency o...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.