Related papers: NextFlow: Unified Sequential Modeling Activates Mu…
Unified multimodal models are envisioned to bridge the gap between understanding and generation. Yet, to achieve competitive performance, state-of-the-art models adopt largely decoupled understanding and generation components. This design,…
We introduce OmniFlow, a novel generative model designed for any-to-any generation tasks such as text-to-image, text-to-audio, and audio-to-image synthesis. OmniFlow advances the rectified flow (RF) framework used in text-to-image models to…
Flow-matching models deliver state-of-the-art fidelity in image and video generation, but the inherent sequential denoising process renders them slower. Existing acceleration methods like distillation, trajectory truncation, and consistency…
Image processing, including image restoration, image enhancement, etc., involves generating a high-quality clean image from a degraded input. Deep learning-based methods have shown superior performance for various image processing tasks in…
Learning permutations is fundamental to sorting, ranking, and matching, but existing differentiable methods based on entropy-regularized Sinkhorn produce a single softened solution and collapse under ambiguity. We present PermFlow, a…
We introduce ContinualFlow, a principled framework for targeted unlearning in generative models via Flow Matching. Our method leverages an energy-based reweighting loss to softly subtract undesired regions of the data distribution without…
Few-step generation has been a long-standing goal, with recent one-step generation methods exemplified by MeanFlow achieving remarkable results. Existing research on MeanFlow primarily focuses on class-to-image generation. However, an…
Image fusion is a fundamental and important task in computer vision, aiming to combine complementary information from different modalities to fuse images. In recent years, diffusion models have made significant developments in the field of…
Autoregressive (AR) modeling has achieved remarkable success in natural language processing by enabling models to generate text with coherence and contextual understanding through next token prediction. Recently, in image generation, VAR…
Recent unified models for joint understanding and generation have significantly advanced visual generation capabilities. However, their focus on conventional tasks like text-to-video generation has left the temporal reasoning potential of…
Despite the progress of learning-based methods for 6D object pose estimation, the trade-off between accuracy and scalability for novel objects still exists. Specifically, previous methods for novel objects do not make good use of the target…
We present a method, Neural Radiance Flow (NeRFlow),to learn a 4D spatial-temporal representation of a dynamic scene from a set of RGB images. Key to our approach is the use of a neural implicit representation that learns to capture the 3D…
We introduce OneCAT, a unified multimodal model that seamlessly integrates understanding, generation, and editing within a novel, pure decoder-only transformer architecture. Our framework uniquely eliminates the need for external components…
Image-to-3D generation faces inherent semantic ambiguity under occlusion, where partial observation alone is often insufficient to determine object category. In this work, we formalize text-driven amodal 3D generation, where text prompts…
Automatic black-and-white image sequence colorization while preserving character and object identity (ID) is a complex task with significant market demand, such as in cartoon or comic series colorization. Despite advancements in visual…
Existing rectified flow models are based on linear trajectories between data and noise distributions. This linearity enforces zero curvature, which can inadvertently force the image generation process through low-probability regions of the…
Optical flow is an indispensable building block for various important computer vision tasks, including motion estimation, object tracking, and disparity measurement. In this work, we propose TransFlow, a pure transformer architecture for…
Image inpainting techniques have shown significant improvements by using deep neural networks recently. However, most of them may either fail to reconstruct reasonable structures or restore fine-grained textures. In order to solve this…
We propose a novel approach to image generation by decomposing an image into a structured sequence, where each element in the sequence shares the same spatial resolution but differs in the number of unique tokens used, capturing different…
We present Liquid, an auto-regressive generation paradigm that seamlessly integrates visual comprehension and generation by tokenizing images into discrete codes and learning these code embeddings alongside text tokens within a shared…