Mehdi Noroozi

Ruchika Chavhan, Malcolm Chadwick, Alberto Gil Couto Pimentel Ramos et al.

While large-scale text-to-image diffusion models continue to improve in visual quality, their increasing scale has widened the gap between state-of-the-art models and on-device solutions. To address this gap, we introduce NanoFLUX, a 2.4B text-to-image flow-matching model distilled from 17B FLUX.1-Schnell using a progressive compression pipeline designed to preserve generation quality. Our contributions include: (1) A model compression strategy driven by pruning redundant components in the diffusion transformer, reducing its size from 12B to 2B; (2) A ResNet-based token downsampling mechanism that reduces latency by allowing intermediate blocks to operate on lower-resolution tokens while preserving high-resolution processing elsewhere; (3) A novel text encoder distillation approach that leverages visual signals from early layers of the denoiser during sampling. Empirically, NanoFLUX generates 512 x 512 images in approximately 2.5 seconds on mobile devices, demonstrating the feasibility of high-quality on-device text-to-image generation.

Mohammadreza Salehi, Mehdi Noroozi, Luca Morreale et al.

Instructional video editing applies edits to an input video using only text prompts, enabling intuitive natural-language control. Despite rapid progress, most methods still require fixed-length inputs and substantial compute. Meanwhile, autoregressive video generation enables efficient variable-length synthesis, yet remains under-explored for video editing. We introduce a causal, efficient video editing model that edits variable-length videos frame by frame. For efficiency, we start from a 2D image-to-image (I2I) diffusion model and adapt it to video-to-video (V2V) editing by conditioning the edit at time step t on the model's prediction at t-1. To leverage videos' temporal redundancy, we propose a new I2I diffusion forward process formulation that encourages the model to predict the residual between the target output and the previous prediction. We call this Residual Flow Diffusion Model (RFDM), which focuses the denoising process on changes between consecutive frames. Moreover, we propose a new benchmark that better ranks state-of-the-art methods for editing tasks. Trained on paired video data for global/local style transfer and object removal, RFDM surpasses I2I-based methods and competes with fully spatiotemporal (3D) V2V models, while matching the compute of image models and scaling independently of input video length. More content can be found in: https://smsd75.github.io/RFDM_page/

Mehdi Noroozi

This paper introduces a novel and fully unsupervised framework for conditional GAN training in which labels are automatically obtained from data. We incorporate a clustering network into the standard conditional GAN framework that plays against the discriminator. With the generator, it aims to find a shared structured mapping for associating pseudo-labels with the real and fake images. Our generator outperforms unconditional GANs in terms of FID with significant margins on large scale datasets like ImageNet and LSUN. It also outperforms class conditional GANs trained on human labels on CIFAR10 and CIFAR100 where fine-grained annotations or a large number of samples per class are not available. Additionally, our clustering network exceeds the state-of-the-art on CIFAR100 clustering.

Mohsen Fayyaz, Emad Bahrami, Ali Diba et al.

While state-of-the-art 3D Convolutional Neural Networks (CNN) achieve very good results on action recognition datasets, they are computationally very expensive and require many GFLOPs. While the GFLOPs of a 3D CNN can be decreased by reducing the temporal feature resolution within the network, there is no setting that is optimal for all input clips. In this work, we therefore introduce a differentiable Similarity Guided Sampling (SGS) module, which can be plugged into any existing 3D CNN architecture. SGS empowers 3D CNNs by learning the similarity of temporal features and grouping similar features together. As a result, the temporal feature resolution is not anymore static but it varies for each input video clip. By integrating SGS as an additional layer within current 3D CNNs, we can convert them into much more efficient 3D CNNs with adaptive temporal feature resolutions (ATFR). Our evaluations show that the proposed module improves the state-of-the-art by reducing the computational cost (GFLOPs) by half while preserving or even improving the accuracy. We evaluate our module by adding it to multiple state-of-the-art 3D CNNs on various datasets such as Kinetics-600, Kinetics-400, mini-Kinetics, Something-Something V2, UCF101, and HMDB51.

Mehdi Noroozi, Ananth Vinjimoor, Paolo Favaro et al.

In self-supervised learning, one trains a model to solve a so-called pretext task on a dataset without the need for human annotation. The main objective, however, is to transfer this model to a target domain and task. Currently, the most effective transfer strategy is fine-tuning, which restricts one to use the same model or parts thereof for both pretext and target tasks. In this paper, we present a novel framework for self-supervised learning that overcomes limitations in designing and comparing different tasks, models, and data domains. In particular, our framework decouples the structure of the self-supervised model from the final task-specific fine-tuned model. This allows us to: 1) quantitatively assess previously incompatible models including handcrafted features; 2) show that deeper neural network models can learn better representations from the same pretext task; 3) transfer knowledge learned with a deep model to a shallower one and thus boost its learning. We use this framework to design a novel self-supervised task, which achieves state-of-the-art performance on the common benchmarks in PASCAL VOC 2007, ILSVRC12 and Places by a significant margin. Our learned features shrink the mAP gap between models trained via self-supervised learning and supervised learning from 5.9% to 2.6% in object detection on PASCAL VOC 2007.

Paramanand Chandramouli, Mehdi Noroozi, Paolo Favaro

In this paper, we address the problem of reflection removal and deblurring from a single image captured by a plenoptic camera. We develop a two-stage approach to recover the scene depth and high resolution textures of the reflected and transmitted layers. For depth estimation in the presence of reflections, we train a classifier through convolutional neural networks. For recovering high resolution textures, we assume that the scene is composed of planar regions and perform the reconstruction of each layer by using an explicit form of the plenoptic camera point spread function. The proposed framework also recovers the sharp scene texture with different motion blurs applied to each layer. We demonstrate our method on challenging real and synthetic images.

Mehdi Noroozi, Hamed Pirsiavash, Paolo Favaro

We introduce a novel method for representation learning that uses an artificial supervision signal based on counting visual primitives. This supervision signal is obtained from an equivariance relation, which does not require any manual annotation. We relate transformations of images to transformations of the representations. More specifically, we look for the representation that satisfies such relation rather than the transformations that match a given representation. In this paper, we use two image transformations in the context of counting: scaling and tiling. The first transformation exploits the fact that the number of visual primitives should be invariant to scale. The second transformation allows us to equate the total number of visual primitives in each tile to that in the whole image. These two transformations are combined in one constraint and used to train a neural network with a contrastive loss. The proposed task produces representations that perform on par or exceed the state of the art in transfer learning benchmarks.

Mehdi Noroozi, Paramanand Chandramouli, Paolo Favaro

The task of image deblurring is a very ill-posed problem as both the image and the blur are unknown. Moreover, when pictures are taken in the wild, this task becomes even more challenging due to the blur varying spatially and the occlusions between the object. Due to the complexity of the general image model we propose a novel convolutional network architecture which directly generates the sharp image.This network is built in three stages, and exploits the benefits of pyramid schemes often used in blind deconvolution. One of the main difficulties in training such a network is to design a suitable dataset. While useful data can be obtained by synthetically blurring a collection of images, more realistic data must be collected in the wild. To obtain such data we use a high frame rate video camera and keep one frame as the sharp image and frame average as the corresponding blurred image. We show that this realistic dataset is key in achieving state-of-the-art performance and dealing with occlusions.