The paper introduces Chameleon, a two‑stage training framework for cross‑domain image compositing that separates style and content representations. It first trains a ChameleonEncoder using Joint Hard Contrastive Learning to disentangle style and content, then applies Spatio‑Temporal Attention Gating within a diffusion transformer to stylize the foreground while preserving its identity. The authors also release ChameleonDataset, the first large‑scale training set for cross‑domain compositing, and demonstrate that Chameleon outperforms existing in‑domain, cross‑domain, and commercial models in both plausibility and stylistic fidelity.
arXiv:2606. 26668v1 Announce Type: cross Abstract: Video customization based on Text-to-Video (T2V) models aims to learn specific features from reference data to generate controllable videos.
Recent advances in diffusion models have shown impressive performance in controllable image generation and dense prediction tasks. However, existing approaches typically treat diffusion-based controllable generation and dense prediction as separate tasks, overlooking the potential benefits of jointly modeling the heterogeneous distributions.
The paper introduces a foreground-aware dataset distillation technique that uses a dual-path patch selection strategy. By estimating foreground occupancy with Grounded SAM2, images are routed either to a candidate-crop selection path for sparse foregrounds or a direct transformation path for dominant foregrounds, balancing foreground concentration and background reduction. Experiments on CIFAR-10, CIFAR-100, ImageNette, and ImageWoof show the method surpasses the baseline RDED across multiple architectures and distillation budgets.
arXiv:2509.22650v3 Announce Type: replace Abstract: Most existing approaches to referring segmentation achieve strong performance only through fine-tuning or by composing multiple pre-trained models,...
arXiv:2511. 18050v1 Announce Type: cross Abstract: Diffusion transformers have recently delivered strong text-to-image generation around 1K resolution, but we show that extending them to native 4K across diverse aspect ratios exposes a tightly coupled failure mode spanning positional encoding, VAE compression, and optimization.
arXiv:2507. 02288v2 Announce Type: replace-cross Abstract: Domain Generalization (DG) seeks to develop a versatile model capable of performing effectively on unseen target domains.
The paper introduces Composite Subspace Flow Matching (CSFM), a representation learning method that minimizes variance by inverting a deterministic degradation curriculum across spectral, color, and illumination subspaces. CSFM uses hard temporal style truncation to constrain an encoder, encouraging it to ignore transient style artifacts while preserving persistent content. Experiments on CIFAR-10, CIFAR-100, and STL-10 demonstrate that CSFM achieves competitive discriminative transferability and generative synthesis, outperforming standard optimal transport flows in linear probing and few‑shot classification while maintaining a smooth latent space.
Large-scale text-to-image models are attractive backbones for dense prediction because RGB generation pretraining learns rich semantic, structural, and geometric priors. Existing generative and editing approaches reuse these priors by casting dense prediction as target generation: annotations such as depth, normals, alpha mattes, masks, and heatmaps are encoded into an RGB-trained VAE latent space and decoded back as image-like targets.
arXiv:2603. 22282v2 Announce Type: replace-cross Abstract: We present UniMotion, to our knowledge the first unified framework for simultaneous understanding and generation of human motion, natural language, and RGB images within a single architecture.
arXiv:2605.23891v2 Announce Type: replace Abstract: Mask-free video object insertion has emerged as a challenging task, requiring harmonious integration of reference objects into source videos. Howev...
arXiv:2603. 28762v2 Announce Type: replace-cross Abstract: Modern Text-to-Image (T2I) diffusion models have achieved remarkable semantic alignment, yet they often suffer from a significant lack of variety, converging on a narrow set of visual solutions for any given prompt.
arXiv:2606. 00583v1 Announce Type: cross Abstract: Recent diffusion transformers have demonstrated strong image synthesis capabilities but remain inefficient to train due to weak alignment between generative and discriminative representations.