CharGen: High Accurate Character-Level Visual Text Generation Model with MultiModal Encoder

Recently, significant advancements have been made in diffusion-based visual text generation models. Although the effectiveness of these methods in visual text rendering is rapidly improving, they still encounter challenges such as inaccurate characters and strokes when rendering complex visual text. In this paper, we propose CharGen, a highly accurate character-level visual text generation and editing model. Specifically, CharGen employs a character-level multimodal encoder that not only extracts character-level text embeddings but also encodes glyph images character by character. This enables it to capture fine-grained cross-modality features more effectively. Additionally, we introduce a new perceptual loss in CharGen to enhance character shape supervision and address the issue of inaccurate strokes in generated text. It is worth mentioning that CharGen can be integrated into existing diffusion models to generate visual text with high accuracy. CharGen significantly improves text rendering accuracy, outperforming recent methods in public benchmarks such as AnyText-benchmark and MARIO-Eval, with improvements of more than 8% and 6%, respectively. Notably, CharGen achieved a 5.5% increase in accuracy on Chinese test sets.

InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models

Boosted by Multi-modal Large Language Models (MLLMs), text-guided universal segmentation models for the image and video domains have made rapid progress recently. However, these methods are often developed separately for specific domains, overlooking the similarities in task settings and solutions across these two areas. In this paper, we define the union of referring segmentation and reasoning segmentation at both the image and video levels as Instructed Visual Segmentation (IVS). Correspondingly, we propose InstructSeg, an end-to-end segmentation pipeline equipped with MLLMs for IVS. Specifically, we employ an object-aware video perceiver to extract temporal and object information from reference frames, facilitating comprehensive video understanding. Additionally, we introduce vision-guided multi-granularity text fusion to better integrate global and detailed text information with fine-grained visual guidance. By leveraging multi-task and end-to-end training, InstructSeg demonstrates superior performance across diverse image and video segmentation tasks, surpassing both segmentation specialists and MLLM-based methods with a single model. Our code is available at https://github.com/congvvc/InstructSeg.

Mr. DETR: Instructive Multi-Route Training for Detection Transformers

Existing methods enhance the training of detection transformers by incorporating an auxiliary one-to-many assignment. In this work, we treat the model as a multi-task framework, simultaneously performing one-to-one and one-to-many predictions. We investigate the roles of each component in the transformer decoder across these two training targets, including self-attention, cross-attention, and feed-forward network. Our empirical results demonstrate that any independent component in the decoder can effectively learn both targets simultaneously, even when other components are shared. This finding leads us to propose a multi-route training mechanism, featuring a primary route for one-to-one prediction and two auxiliary training routes for one-to-many prediction. We enhance the training mechanism with a novel instructive self-attention that dynamically and flexibly guides object queries for one-to-many prediction. The auxiliary routes are removed during inference, ensuring no impact on model architecture or inference cost. We conduct extensive experiments on various baselines, achieving consistent improvements as shown in Figure 1.

DriveMM: All-in-One Large Multimodal Model for Autonomous Driving

Large Multimodal Models (LMMs) have demonstrated exceptional comprehension and interpretation capabilities in Autonomous Driving (AD) by incorporating large language models. Despite the advancements, current data-driven AD approaches tend to concentrate on a single dataset and specific tasks, neglecting their overall capabilities and ability to generalize. To bridge these gaps, we propose DriveMM, a general large multimodal model designed to process diverse data inputs, such as images and multi-view videos, while performing a broad spectrum of AD tasks, including perception, prediction, and planning. Initially, the model undergoes curriculum pre-training to process varied visual signals and perform basic visual comprehension and perception tasks. Subsequently, we augment and standardize various AD-related datasets to fine-tune the model, resulting in an all-in-one LMM for autonomous driving. To assess the general capabilities and generalization ability, we conduct evaluations on six public benchmarks and undertake zero-shot transfer on an unseen dataset, where DriveMM achieves state-of-the-art performance across all tasks. We hope DriveMM as a promising solution for future end-toend autonomous driving applications in the real world.

LinVT: Empower Your Image-level Large Language Model to Understand Videos

Large Language Models (LLMs) have been widely used in various tasks, motivating us to develop an LLM-based assistant for videos. Instead of training from scratch, we propose a module to transform arbitrary well-trained image-based LLMs into video-LLMs (after being trained on video data). To better adapt image-LLMs for processing videos, we introduce two design principles: linear transformation to preserve the original visual-language alignment and representative information condensation from redundant video content. Guided by these principles, we propose a plug-and-play Linear Video Tokenizer(LinVT), which enables existing image-LLMs to understand videos. We benchmark LinVT with six recent visual LLMs: Aquila, Blip-3, InternVL2, Mipha, Molmo and Qwen2-VL, showcasing the high compatibility of LinVT. LinVT-based LLMs achieve state-of-the-art performance across various video benchmarks, illustrating the effectiveness of LinVT in multi-modal video understanding.

RFSR: Improving ISR Diffusion Models via Reward Feedback Learning

Generative diffusion models (DM) have been extensively utilized in image super-resolution (ISR). Most of the existing methods adopt the denoising loss from DDPMs for model optimization. We posit that introducing reward feedback learning to finetune the existing models can further improve the quality of the generated images. In this paper, we propose a timestep-aware training strategy with reward feedback learning. Specifically, in the initial denoising stages of ISR diffusion, we apply low-frequency constraints to super-resolution (SR) images to maintain structural stability. In the later denoising stages, we use reward feedback learning to improve the perceptual and aesthetic quality of the SR images. In addition, we incorporate Gram-KL regularization to alleviate stylization caused by reward hacking. Our method can be integrated into any diffusion-based ISR model in a plug-and-play manner. Experiments show that ISR diffusion models, when fine-tuned with our method, significantly improve the perceptual and aesthetic quality of SR images, achieving excellent subjective results. Code: https://github.com/sxpro/RFSR

TASR: Timestep-Aware Diffusion Model for Image Super-Resolution

Diffusion models have recently achieved outstanding results in the field of image super-resolution. These methods typically inject low-resolution (LR) images via ControlNet.In this paper, we first explore the temporal dynamics of information infusion through ControlNet, revealing that the input from LR images predominantly influences the initial stages of the denoising process. Leveraging this insight, we introduce a novel timestep-aware diffusion model that adaptively integrates features from both ControlNet and the pre-trained Stable Diffusion (SD). Our method enhances the transmission of LR information in the early stages of diffusion to guarantee image fidelity and stimulates the generation ability of the SD model itself more in the later stages to enhance the detail of generated images. To train this method, we propose a timestep-aware training strategy that adopts distinct losses at varying timesteps and acts on disparate modules. Experiments on benchmark datasets demonstrate the effectiveness of our method. Code: https://github.com/SleepyLin/TASR

HyperSeg: Towards Universal Visual Segmentation with Large Language Model

This paper aims to address universal segmentation for image and video perception with the strong reasoning ability empowered by Visual Large Language Models (VLLMs). Despite significant progress in current unified segmentation methods, limitations in adaptation to both image and video scenarios, as well as the complex reasoning segmentation, make it difficult for them to handle various challenging instructions and achieve an accurate understanding of fine-grained vision-language correlations. We propose HyperSeg, the first VLLM-based universal segmentation model for pixel-level image and video perception, encompassing generic segmentation tasks and more complex reasoning perception tasks requiring powerful reasoning abilities and world knowledge. Besides, to fully leverage the recognition capabilities of VLLMs and the fine-grained visual information, HyperSeg incorporates hybrid entity recognition and fine-grained visual perceiver modules for various segmentation tasks. Combined with the temporal adapter, HyperSeg achieves a comprehensive understanding of temporal information. Experimental results validate the effectiveness of our insights in resolving universal image and video segmentation tasks, including the more complex reasoning perception tasks. Our code is available.

360-Degree Video Super Resolution and Quality Enhancement Challenge: Methods and Results

Omnidirectional (360-degree) video is rapidly gaining popularity due to advancements in immersive technologies like virtual reality (VR) and extended reality (XR). However, real-time streaming of such videos, especially in live mobile scenarios like unmanned aerial vehicles (UAVs), is challenged by limited bandwidth and strict latency constraints. Traditional methods, such as compression and adaptive resolution, help but often compromise video quality and introduce artifacts that degrade the viewer experience. Additionally, the unique spherical geometry of 360-degree video presents challenges not encountered in traditional 2D video. To address these issues, we initiated the 360-degree Video Super Resolution and Quality Enhancement Challenge. This competition encourages participants to develop efficient machine learning solutions to enhance the quality of low-bitrate compressed 360-degree videos, with two tracks focusing on 2x and 4x super-resolution (SR). In this paper, we outline the challenge framework, detailing the two competition tracks and highlighting the SR solutions proposed by the top-performing models. We assess these models within a unified framework, considering quality enhancement, bitrate gain, and computational efficiency. This challenge aims to drive innovation in real-time 360-degree video streaming, improving the quality and accessibility of immersive visual experiences.

Temporal-Enhanced Multimodal Transformer for Referring Multi-Object Tracking and Segmentation

Referring multi-object tracking (RMOT) is an emerging cross-modal task that aims to locate an arbitrary number of target objects and maintain their identities referred by a language expression in a video. This intricate task involves the reasoning of linguistic and visual modalities, along with the temporal association of target objects. However, the seminal work employs only loose feature fusion and overlooks the utilization of long-term information on tracked objects. In this study, we introduce a compact Transformer-based method, termed TenRMOT. We conduct feature fusion at both encoding and decoding stages to fully exploit the advantages of Transformer architecture. Specifically, we incrementally perform cross-modal fusion layer-by-layer during the encoding phase. In the decoding phase, we utilize language-guided queries to probe memory features for accurate prediction of the desired objects. Moreover, we introduce a query update module that explicitly leverages temporal prior information of the tracked objects to enhance the consistency of their trajectories. In addition, we introduce a novel task called Referring Multi-Object Tracking and Segmentation (RMOTS) and construct a new dataset named Ref-KITTI Segmentation. Our dataset consists of 18 videos with 818 expressions, and each expression averages 10.7 masks, which poses a greater challenge compared to the typical single mask in most existing referring video segmentation datasets. TenRMOT demonstrates superior performance on both the referring multi-object tracking and the segmentation tasks.