Related papers: Solving Inverse Problems with FLAIR

Diffusion models have established new state of the art in a multitude of computer vision tasks, including image restoration. Diffusion-based inverse problem solvers generate reconstructions of exceptional visual quality from heavily…

3D Gaussian splatting enables high-quality novel view synthesis (NVS) at real-time frame rates. However, its quality drops sharply as we depart from the training views. Thus, dense captures are needed to match the high-quality expectations…

We propose a novel modular inference approach combining two different generative models -- generative adversarial networks (GAN) and normalizing flows -- to approximate the posterior distribution of physics-based Bayesian inverse problems…

Recent generative models show impressive results in photo-realistic image generation. However, artifacts often inevitably appear in the generated results, leading to downgraded user experience and reduced performance in downstream tasks.…

We present FLARE, a feed-forward model designed to infer high-quality camera poses and 3D geometry from uncalibrated sparse-view images (i.e., as few as 2-8 inputs), which is a challenging yet practical setting in real-world applications.…

Cross-device federated learning is an emerging machine learning (ML) paradigm where a large population of devices collectively train an ML model while the data remains on the devices. This research field has a unique set of practical…

Diffusion models have achieved remarkable success in imaging inverse problems owing to their powerful generative capabilities. However, existing approaches typically rely on models trained for specific degradation types, limiting their…

Leveraging the large generative prior of the flow transformer for tuning-free image editing requires authentic inversion to project the image into the model's domain and a flexible invariance control mechanism to preserve non-target…

Existing approaches to diffusion-based inverse problem solvers frame the signal recovery task as a probabilistic sampling episode, where the solution is drawn from the desired posterior distribution. This framework suffers from several…

Conditional generative models typically demand large annotated training sets to achieve high-quality synthesis. As a result, there has been significant interest in designing models that perform plug-and-play generation, i.e., to use a…

Text-conditioned image generation models have recently shown immense qualitative success using denoising diffusion processes. However, unlike discriminative vision-and-language models, it is a non-trivial task to subject these…

Generative models that can model and predict sequences of future events can, in principle, learn to capture complex real-world phenomena, such as physical interactions. However, a central challenge in video prediction is that the future is…

Diffusion-based image generation models, such as Stable Diffusion or DALL-E 2, are able to learn from given images and generate high-quality samples following the guidance from prompts. For instance, they can be used to create artistic…

We introduce a new paradigm for generative modeling built on Continuous Normalizing Flows (CNFs), allowing us to train CNFs at unprecedented scale. Specifically, we present the notion of Flow Matching (FM), a simulation-free approach for…

As the boosting development of large vision-language models like Contrastive Language-Image Pre-training (CLIP), many CLIP-like methods have shown impressive abilities on visual recognition, especially in low-data regimes scenes. However,…

Generative flow models offer powerful priors learned from large-scale natural images, but directly adapting them to restoration tasks such as motion deblurring causes severe fidelity degradation, as their training objective is inherently…

Diffusion and flow-based generative models have achieved remarkable success in domains such as image synthesis, video generation, and natural language modeling. In this work, we extend these advances to weight space learning by leveraging…

Diffusion models and flow matching have demonstrated remarkable success in text-to-image generation. While many existing alignment methods primarily focus on fine-tuning pre-trained generative models to maximize a given reward function,…

Inverse problems have many applications in science and engineering. In Computer vision, several image restoration tasks such as inpainting, deblurring, and super-resolution can be formally modeled as inverse problems. Recently, methods have…

Normalizing Flows (NFs) learn invertible mappings between the data and a Gaussian distribution. Prior works usually suffer from two limitations. First, they add random noise to training samples or VAE latents as data augmentation,…