ASTRA disentangles subject identity from pose structure in diffusion transformers via retrieval-augmented pose guidance, asymmetric EURoPE embeddings, and a DSM adapter to improve multi-subject generation.
hub
Adding conditional control to text-to-image diffusion models
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
fields
cs.CV 13roles
background 2polarities
background 2representative citing papers
3D-Fixer performs in-place 3D asset completion from single-view partial point clouds via coarse-to-fine generation with ORFA conditioning, plus a new ARSG-110K dataset, to achieve higher geometric accuracy than MIDI and Gen3DSR while keeping diffusion efficiency.
MultiAnimate adds Identifier Assigner and Identifier Adapter modules to diffusion video models so they can handle multiple characters without identity mix-ups, generalizing from two-character training data to more characters.
A new data pipeline using real photos, entity removal, and image-to-video models plus a cross-view attention loss enables text-driven generation of actors in reference scenes with improved alignment.
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.
GenHSI is a training-free three-stage pipeline that turns a scene image, character image, and complex HSI prompt into long videos with plausible chained interactions by generating atomic actions, 3D keyframes via 2D inpainting plus optimization, and then feeding them to pre-trained video diffusion.
Fine-tuning text-to-video models on sparse low-quality synthetic data for physical camera controls outperforms fine-tuning on photorealistic data.
Ouroboros uses two single-step diffusion models with cycle consistency for forward and inverse rendering, extending intrinsic decomposition to indoor/outdoor scenes with faster inference than multi-step methods.
RealDiffusion uses heat diffusion as a dissipative prior and a region-aware stochastic process inside a training-free physics-informed attention mechanism to improve multi-character coherence while preserving narrative dynamism in sequential image generation.
A reinforcement learning approach adapts general generative models to produce synthetic data that boosts identity recognition accuracy and generalization under privacy constraints.
A framework that combines MLLM-based image enhancement with a medium-aware 3D Gaussian Splatting model to reconstruct and render smoke scenes.
TPGDiff introduces hierarchical triple-prior guidance in a diffusion network, placing degradation priors throughout, structural priors in shallow layers, and semantic priors in deep layers for improved all-in-one image restoration.
MedShift applies flow matching and Schrödinger bridges for class-conditional unpaired translation between synthetic and real skull X-rays, benchmarked on the new X-DigiSkull dataset.
citing papers explorer
-
ASTRA: Enhancing Multi-Subject Generation with Retrieval-Augmented Pose Guidance and Disentangled Position Embedding
ASTRA disentangles subject identity from pose structure in diffusion transformers via retrieval-augmented pose guidance, asymmetric EURoPE embeddings, and a DSM adapter to improve multi-subject generation.
-
3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image
3D-Fixer performs in-place 3D asset completion from single-view partial point clouds via coarse-to-fine generation with ORFA conditioning, plus a new ARSG-110K dataset, to achieve higher geometric accuracy than MIDI and Gen3DSR while keeping diffusion efficiency.
-
MultiAnimate: Pose-Guided Image Animation Made Extensible
MultiAnimate adds Identifier Assigner and Identifier Adapter modules to diffusion video models so they can handle multiple characters without identity mix-ups, generalizing from two-character training data to more characters.
-
Setting the Stage: Text-Driven Scene-Consistent Image Generation
A new data pipeline using real photos, entity removal, and image-to-video models plus a cross-view attention loss enables text-driven generation of actors in reference scenes with improved alignment.
-
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.
-
GenHSI: Controllable Generation of Human-Scene Interaction Videos
GenHSI is a training-free three-stage pipeline that turns a scene image, character image, and complex HSI prompt into long videos with plausible chained interactions by generating atomic actions, 3D keyframes via 2D inpainting plus optimization, and then feeding them to pre-trained video diffusion.
-
Less is More: Data-Efficient Adaptation for Controllable Text-to-Video Generation
Fine-tuning text-to-video models on sparse low-quality synthetic data for physical camera controls outperforms fine-tuning on photorealistic data.
-
Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Rendering
Ouroboros uses two single-step diffusion models with cycle consistency for forward and inverse rendering, extending intrinsic decomposition to indoor/outdoor scenes with faster inference than multi-step methods.
-
RealDiffusion: Physics-informed Attention for Multi-character Storybook Generation
RealDiffusion uses heat diffusion as a dissipative prior and a region-aware stochastic process inside a training-free physics-informed attention mechanism to improve multi-character coherence while preserving narrative dynamism in sequential image generation.
-
Reinforcement-Guided Synthetic Data Generation for Privacy-Sensitive Identity Recognition
A reinforcement learning approach adapts general generative models to produce synthetic data that boosts identity recognition accuracy and generalization under privacy constraints.
-
3D Smoke Scene Reconstruction Guided by Vision Priors from Multimodal Large Language Models
A framework that combines MLLM-based image enhancement with a medium-aware 3D Gaussian Splatting model to reconstruct and render smoke scenes.
-
TPGDiff: Hierarchical Triple-Prior Guided Diffusion for Image Restoration
TPGDiff introduces hierarchical triple-prior guidance in a diffusion network, placing degradation priors throughout, structural priors in shallow layers, and semantic priors in deep layers for improved all-in-one image restoration.
-
MedShift: Implicit Conditional Transport for X-Ray Domain Adaptation
MedShift applies flow matching and Schrödinger bridges for class-conditional unpaired translation between synthetic and real skull X-rays, benchmarked on the new X-DigiSkull dataset.