Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision
- URL: http://arxiv.org/abs/2504.04903v2
- Date: Tue, 08 Apr 2025 07:26:50 GMT
- Title: Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision
- Authors: Yuandong Pu, Le Zhuo, Kaiwen Zhu, Liangbin Xie, Wenlong Zhang, Xiangyu Chen, Peng Gao, Yu Qiao, Chao Dong, Yihao Liu,
- Abstract summary: Lunima- OmniLV is a universal multimodal multi-task framework for low-level vision.<n>It addresses over 100 sub-tasks across four major categories: image restoration, image enhancement, weak-semantic dense prediction, and stylization.
- Score: 40.27654736294303
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We present Lunima-OmniLV (abbreviated as OmniLV), a universal multimodal multi-task framework for low-level vision that addresses over 100 sub-tasks across four major categories: image restoration, image enhancement, weak-semantic dense prediction, and stylization. OmniLV leverages both textual and visual prompts to offer flexible and user-friendly interactions. Built on Diffusion Transformer (DiT)-based generative priors, our framework supports arbitrary resolutions -- achieving optimal performance at 1K resolution -- while preserving fine-grained details and high fidelity. Through extensive experiments, we demonstrate that separately encoding text and visual instructions, combined with co-training using shallow feature control, is essential to mitigate task ambiguity and enhance multi-task generalization. Our findings also reveal that integrating high-level generative tasks into low-level vision models can compromise detail-sensitive restoration. These insights pave the way for more robust and generalizable low-level vision systems.
Related papers
- Hierarchical Cross-modal Prompt Learning for Vision-Language Models [9.128564580725627]
HiCroPL is a Hierarchical Cross-modal Prompt Learning framework.<n>It routes knowledge flows by leveraging the complementary strengths of text and vision.<n>It achieves state-of-the-art results on 11 benchmarks with significant improvements.
arXiv Detail & Related papers (2025-07-20T14:18:04Z) - Unlocking Compositional Control: Self-Supervision for LVLM-Based Image Generation [42.78181795494584]
generative model designed to significantly advance text-to-image synthesis.<n>Hi-SSLVLM addresses limitations through a unique two-stage self-supervised learning strategy.<n> experiments demonstrate Hi-SSLVLM's superior performance across all fine-grained metrics.
arXiv Detail & Related papers (2025-07-05T20:16:32Z) - SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding [5.976839106353883]
SECOND: Selective and Contrastive Decoding is a novel approach that enables Vision-Language Models to leverage multi-scale visual information with an object-centric manner.<n> SECOND significantly reduces perceptual hallucinations and outperforms a wide range of benchmarks.
arXiv Detail & Related papers (2025-06-10T02:55:38Z) - Instruction-Guided Fusion of Multi-Layer Visual Features in Large Vision-Language Models [50.98559225639266]
We investigate the contributions of visual features from different encoder layers using 18 benchmarks spanning 6 task categories.<n>Our findings reveal that multilayer features provide complementary strengths with varying task dependencies, and uniform fusion leads to suboptimal performance.<n>We propose the instruction-guided vision aggregator, a module that dynamically integrates multi-layer visual features based on textual instructions.
arXiv Detail & Related papers (2024-12-26T05:41:31Z) - Visual Cue Enhancement and Dual Low-Rank Adaptation for Efficient Visual Instruction Fine-Tuning [102.18178065928426]
We propose an efficient fine-tuning framework with two novel approaches: Vision Cue Enhancement (VCE) and Dual Low-Rank Adaptation (Dual-LoRA)<n>VCE enhances the vision projector by integrating multi-level visual cues, improving the model's ability to capture fine-grained visual features.<n> Dual-LoRA introduces a dual low-rank structure for instruction tuning, decoupling learning into skill and task spaces to enable precise control and efficient adaptation across diverse tasks.
arXiv Detail & Related papers (2024-11-19T11:03:09Z) - Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing [150.0380447353081]
We present VITRON, a universal pixel-level vision LLM designed for comprehensive understanding, segmenting, and clusters of both static images and dynamic videos.
Building on top of an LLM, VITRON incorporates encoders for images, videos, and pixel-level regional visuals within its modules, while employing state-of-the-art visual specialists as its backend.
arXiv Detail & Related papers (2024-10-08T08:39:04Z) - Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs [61.143381152739046]
We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach.
Our study uses LLMs and visual instruction tuning as an interface to evaluate various visual representations.
We provide model weights, code, supporting tools, datasets, and detailed instruction-tuning and evaluation recipes.
arXiv Detail & Related papers (2024-06-24T17:59:42Z) - Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models [81.71651422951074]
Chain-of-Spot (CoS) method is a novel approach that enhances feature extraction by focusing on key regions of interest.
This technique allows LVLMs to access more detailed visual information without altering the original image resolution.
Our empirical findings demonstrate a significant improvement in LVLMs' ability to understand and reason about visual content.
arXiv Detail & Related papers (2024-03-19T17:59:52Z) - Enhancing Visual Document Understanding with Contrastive Learning in
Large Visual-Language Models [56.76307866160105]
We propose a contrastive learning framework, termed Document Object COntrastive learning (DoCo)
DoCo leverages an auxiliary multimodal encoder to obtain the features of document objects and align them to the visual features generated by the vision encoder of Large Visual-Language Models (LVLMs)
We demonstrate that the proposed DoCo serves as a plug-and-play pre-training method, which can be employed in the pre-training of various LVLMs without inducing any increase in computational complexity during the inference process.
arXiv Detail & Related papers (2024-02-29T10:17:27Z) - M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action
Recognition [39.92547393649842]
We introduce a novel Multimodal, Multi-task CLIP adapting framework named name to address these challenges.
We demonstrate exceptional performance in supervised learning while maintaining strong generalization in zero-shot scenarios.
arXiv Detail & Related papers (2024-01-22T02:03:31Z) - Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model [83.85856356798531]
VistaLLM is a visual system that addresses coarse- and fine-grained vision-language tasks.
It employs a gradient-aware adaptive sampling technique to represent binary segmentation masks as sequences.
We also introduce a novel task, AttCoSeg, which boosts the model's reasoning and grounding capability over multiple input images.
arXiv Detail & Related papers (2023-12-19T18:53:01Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.