Related papers: CLEAR: Unlocking Generative Potential for Degraded…
We investigate how to generate multimodal image outputs, such as RGB, depth, and surface normals, with a single generative model. The challenge is to produce outputs that are realistic, and also consistent with each other. Our solution…
Despite the success of Generative Adversarial Networks (GANs) in image synthesis, applying trained GAN models to real image processing remains challenging. Previous methods typically invert a target image back to the latent space either by…
Full-stack multimodal interaction in real-time is a central goal in building intelligent embodied agents capable of natural, dynamic communication. However, existing systems are either limited to unimodal generation or suffer from degraded…
Image degradation is a prevalent issue in various real-world applications, affecting visual quality and downstream processing tasks. In this study, we propose a novel framework that employs a Vision-Language Model (VLM) to automatically…
This paper presents Omni-View, which extends the unified multimodal understanding and generation to 3D scenes based on multiview images, exploring the principle that "generation facilitates understanding". Consisting of understanding model,…
Generative adversarial networks (GANs) have gained considerable attention owing to their ability to reproduce images. However, they can recreate training images faithfully despite image degradation in the form of blur, noise, and…
Humans are able to accurately reason in 3D by gathering multi-view observations of the surrounding world. Inspired by this insight, we introduce a new large-scale benchmark for 3D multi-view visual question answering (3DMV-VQA). This…
Recent large vision-language models (VLMs) remain fundamentally constrained by a persistent dichotomy: understanding and generation are treated as distinct problems, leading to fragmented architectures, cascaded pipelines, and misaligned…
Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…
Multimodal Large Language Models (MLLMs) struggle with precise reasoning for structured visuals like charts and diagrams, as pixel-based perception lacks a mechanism for verification. To address this, we propose to leverage derendering --…
Recent advances in image generation models (IGMs), particularly diffusion-based architectures such as Stable Diffusion (SD), have markedly enhanced the quality and diversity of AI-generated visual content. However, their generative…
Unified multimodal models (UMMs) unify visual understanding and generation within a single architecture. However, conventional training relies on image-text pairs (or sequences) whose captions are typically sparse and miss fine-grained…
Recently, remarkable progress has been made in Unified Multimodal Models (UMMs), which integrate vision-language generation and understanding capabilities within a single framework. However, a significant gap exists where a model's strong…
Single-image super-resolution (SISR) remains challenging due to the inherent difficulty of recovering fine-grained details and preserving perceptual quality from low-resolution inputs. Existing methods often rely on limited image priors,…
Recent advances in human preference alignment have significantly improved multimodal generation and understanding. A key approach is to train reward models that provide supervision signals for preference optimization. However, existing…
This paper proposes a novel approach to regularize the \textit{ill-posed} and \textit{non-linear} blind image deconvolution (blind deblurring) using deep generative networks as priors. We employ two separate generative models --- one…
Perceptual image restoration seeks for high-fidelity images that most likely degrade to given images. For better visual quality, previous work proposed to search for solutions within the natural image manifold, by exploiting the latent…
Implicit degradation modeling-based blind super-resolution (SR) has attracted more increasing attention in the community due to its excellent generalization to complex degradation scenarios and wide application range. How to extract more…
3D vision systems are fundamentally constrained by their reliance on visual overlap: reconstruction methods require it for geometric alignment, while generative models use it to enforce multi-view consistency. This limitation is…
This paper proposes a novel approach to regularize the ill-posed blind image deconvolution (blind image deblurring) problem using deep generative networks. We employ two separate deep generative models - one trained to produce sharp images…