CLIP (Contrastive Language-Image Pre-training) uses contrastive learning from noise image-text pairs to excel at recognizing a wide array of candidates, yet its focus on broad associations hinders the precision in distinguishing subtle differences among fine-grained items. Conversely, Multimodal Large Language Models (MLLMs) excel at classifying fine-grained categories, thanks to their substantial knowledge from pre-training on web-level corpora. However, the performance of MLLMs declines with an increase in category numbers, primarily due to growing complexity and constraints of limited context window size. To synergize the strengths of both approaches and enhance the few-shot/zero-shot recognition abilities for datasets characterized by extensive and fine-grained vocabularies, this paper introduces RAR, a Retrieving And Ranking augmented method for MLLMs. We initially establish a multi-modal retriever based on CLIP to create and store explicit memory for different categories beyond the immediate context window. During inference, RAR retrieves the top- $k$ similar results from the memory and uses MLLMs to rank and make the final predictions. Our proposed approach not only addresses the inherent limitations in fine-grained recognition but also preserves the model's comprehensive knowledge base, significantly boosting accuracy across a range of vision-language recognition tasks. Notably, our approach demonstrates a significant improvement in performance on 5 fine-grained visual recognition benchmarks, 11 few-shot image recognition datasets, and the 2 object detection datasets under the zero-shot recognition setting.

Creating lyrics and melodies for the vocal track in a symbolic format, known as song composition, demands expert musical knowledge of melody, an advanced understanding of lyrics, and precise alignment between them. Despite achievements in sub-tasks such as lyric generation, lyric-to-melody, and melody-to-lyric, etc, a unified model for song composition has not yet been achieved. In this paper, we introduce SongComposer, a pioneering step towards a unified song composition model that can readily create symbolic lyrics and melodies following instructions. SongComposer is a music-specialized large language model (LLM) that, for the first time, integrates the capability of simultaneously composing lyrics and melodies into LLMs by leveraging three key innovations: 1) a flexible tuple format for word-level alignment of lyrics and melodies, 2) an extended tokenizer vocabulary for song notes, with scalar initialization based on musical knowledge to capture rhythm, and 3) a multi-stage pipeline that captures musical structure, starting with motif-level melody patterns and progressing to phrase-level structure for improved coherence. Extensive experiments demonstrate that SongComposer outperforms advanced LLMs, including GPT-4, in tasks such as lyric-to-melody generation, melody-to-lyric generation, song continuation, and text-to-song creation. Moreover, we will release SongCompose, a large-scale dataset for training, containing paired lyrics and melodies in Chinese and English.

Active real-time interaction with video LLMs introduces a new paradigm for human-computer interaction, where the model not only understands user intent but also responds while continuously processing streaming video on the fly. Unlike offline video LLMs, which analyze the entire video before answering questions, active real-time interaction requires three capabilities: 1) Perception: real-time video monitoring and interaction capturing. 2) Decision: raising proactive interaction in proper situations, 3) Reaction: continuous interaction with users. However, inherent conflicts exist among the desired capabilities. The Decision and Reaction require a contrary Perception scale and grain, and the autoregressive decoding blocks the real-time Perception and Decision during the Reaction. To unify the conflicted capabilities within a harmonious system, we present Dispider, a solution built on a Disentangled Perception, Decision, and Reaction framework. Dispider features a lightweight Proactive Streaming Video Processing module that tracks the video stream and identifies optimal moments for interaction. Once the interaction is triggered, an asynchronous Precise Interaction module provides detailed responses, while the processing module continues to monitor the video in the meantime. Our disentangled and asynchronous design ensures timely, contextually accurate, and computationally efficient responses, making Dispider ideal for active real-time interaction for long-duration video streams. Experiments prove that Dispider outperforms existing methods not only in its superior understanding of video content in conventional video QA settings, but also in proactive response capability and temporal awareness under the streaming setting. The code and model are released at https://github.com/Mark12Ding/Dispider.

The text-to-video (T2V) generation models, offering convenient visual creation, have recently garnered increasing attention. Despite their substantial potential, the generated videos may present artifacts, including structural implausibility, temporal inconsistency, and a lack of motion, often resulting in near-static video. In this work, we have identified a correlation between the disparity of temporal attention maps across different blocks and the occurrence of temporal inconsistencies. Additionally, we have observed that the energy contained within the temporal attention maps is directly related to the magnitude of motion amplitude in the generated videos. Based on these observations, we present ByTheWay, a training-free method to improve the quality of text-to-video generation without introducing additional parameters, augmenting memory or sampling time. Specifically, ByTheWay is composed of two principal components: 1) Temporal Self-Guidance improves the structural plausibility and temporal consistency of generated videos by reducing the disparity between the temporal attention maps across various decoder blocks. 2) Fourier-based Motion Enhancement enhances the magnitude and richness of motion by amplifying the energy of the map. Extensive experiments demonstrate that ByTheWay significantly improves the quality of text-to-video generation with negligible additional cost. Our code is available at: https://github.com/Bujiazi/ByTheWay.

Temporal Awareness—the ability to reason dynamically based on the timestamp when a question is raised—is the key distinction between offline and online video LLMs. Unlike offline models, which rely on complete videos for static, post hoc analysis, online models process video streams incrementally and dynamically adapt their responses based on the timestamp at which the question is posed. Despite its significance, temporal awareness has not been adequately evaluated in existing benchmarks. To fill this gap, we present OVO-Bench (Online-VideO-Benchmark), a novel video benchmark that emphasizes the importance of timestamps for advanced online video understanding capability benchmarking. OVO-Bench evaluates the ability of video LLMs to reason and respond to events occurring at specific timestamps under three distinct scenarios: (1) Backward tracing: trace back to past events to answer the question. (2) Real-time understanding: understand and respond to events as they unfold at the current timestamp. (3) Forward active responding: delay the response until sufficient future information becomes available to answer the question accurately. OVO-Bench comprises 12 tasks, featuring 644 unique videos and approximately human-curated 2,800 fine-grained meta-annotations with precise timestamps. We combine automated generation pipelines with human curation. With these high-quality samples, we further developed an evaluation pipeline to systematically query video LLMs along the video timeline. Evaluations of eleven Video-LLMs reveal that, despite advancements on traditional benchmarks, current models struggle with on-line video understanding, showing a significant gap compared to human agents. We hope OVO-Bench will drive progress in video LLMs and inspire future research in online video reasoning. Our benchmark and code can be accessed at https://github.com/JoeLeelyf/OVO-Bench.

In large vision-language models (LVLMs), images serve as inputs that carry a wealth of information. As the idiom "A picture is worth a thousand words" implies, representing a single image in current LVLMs can require hundreds or even thousands of tokens, which thereby severely impacting the efficiency. Previous approaches have attempted to reduce the number of image tokens either before or within the early layers of LVLMs. However, these strategies inevitably result in the loss of crucial image information. To address this challenge, we conduct an empirical study revealing that all visual tokens are necessary for LVLMs in the shallow layers, and token redundancy progressively increases in the deeper layers. To this end, we propose PyramidDrop, a visual redundancy reduction strategy for LVLMs to boost their efficiency in both training and inference with neglectable performance loss. Specifically, we partition the LVLM into several stages and drop part of the image tokens at the end of each stage with a pre-defined ratio. The dropping is based on a lightweight similarity calculation with a negligible time overhead. Extensive experiments demonstrate that PyramidDrop can achieve over 40% training time reduction and 55% inference FLOPs acceleration on leading LVLMs like LLaVA-NeXT, maintaining comparable multi-modal performance. Besides, PyramidDrop can also serve as a plug-and-play strategy to accelerate inference in a free way, with better performance and lower inference cost than counterparts. Our code is available at https://github.com/Cooperx521/PyramidDrop.

The Segment Anything Model 2 (SAM 2) has emerged as a powerful foundation model for object segmentation in both images and videos, paving the way for various downstream video applications. The crucial design of SAM 2 for video segmentation is its memory module, which prompts object-aware memories from previous frames for current frame prediction. However, its greedy-selection memory design suffers from the "error accumulation" problem, where an errored or missed mask will cascade and influence the segmentation of the subsequent frames, which limits the performance of SAM 2 toward complex long-term videos. To this end, we introduce SAM2Long, an improved training-free video object segmentation strategy, which considers the segmentation uncertainty within each frame and chooses the video-level optimal results from multiple segmentation pathways in a constrained tree search manner. In practice, we maintain a fixed number of segmentation pathways throughout the video. For each frame, multiple masks are proposed based on the existing pathways, creating various candidate branches. We then select the same fixed number of branches with higher cumulative scores as the new pathways for the next frame. After processing the final frame, the pathway with the highest cumulative score is chosen as the final segmentation result. Benefiting from its heuristic search design, SAM2Long is robust toward occlusions and object reappearances, and can effectively segment and track objects for complex long-term videos. Notably, SAM2Long achieves an average improvement of 3.0 points across all 24 head-to-head comparisons, with gains of up to 5.3 points in J&F on long-term video object segmentation benchmarks such as SA-V and LVOS. The code is released at https://github.com/Mark12Ding/SAM2Long.

The Instruction Following (IF) ability measures how well Multi-modal Large Language Models (MLLMs) understand exactly what users are telling them and whether they are doing it right. Existing multimodal instruction following training data is scarce, the benchmarks are simple with atomic instructions, and the evaluation strategies are imprecise for tasks demanding exact output constraints. To address this, we present MM-IFEngine, an effective pipeline to generate high-quality image-instruction pairs. Our MM-IFEngine pipeline yields large-scale, diverse, and high-quality training data MM-IFInstruct-23k, which is suitable for Supervised Fine-Tuning (SFT) and extended as MM-IFDPO-23k for Direct Preference Optimization (DPO). We further introduce MM-IFEval, a challenging and diverse multi-modal instruction-following benchmark that includes (1) both compose-level constraints for output responses and perception-level constraints tied to the input images, and (2) a comprehensive evaluation pipeline incorporating both rule-based assessment and judge model. We conduct SFT and DPO experiments and demonstrate that fine-tuning MLLMs on MM-IFInstruct-23k and MM-IFDPO-23k achieves notable gains on various IF benchmarks, such as MM-IFEval (+10.2$\%$), MIA (+7.6$\%$), and IFEval (+12.3$\%$). We have fully open-sourced the datasets (both SFT and DPO), evaluation code and training scripts at https://github.com/SYuan03/MM-IFEngine.

Recent advancements in image relighting models, driven by large-scale datasets and pre-trained diffusion models, have enabled the imposition of consistent lighting. However, video relighting still lags, primarily due to the excessive training costs and the scarcity of diverse, high-quality video relighting datasets. A simple application of image relighting models on a frame-by-frame basis leads to several issues: lighting source inconsistency and relighted appearance inconsistency, resulting in flickers in the generated videos. In this work, we propose Light-A-Video, a training-free approach to achieve temporally smooth video relighting. Adapted from image relighting models, Light-A-Video introduces two key techniques to enhance lighting consistency. First, we design a Consistent Light Attention (CLA) module, which enhances cross-frame interactions within the self-attention layers of the image relight model to stabilize the generation of the background lighting source. Second, leveraging the physical principle of light transport independence, we apply linear blending between the source video's appearance and the relighted appearance, using a Progressive Light Fusion (PLF) strategy to ensure smooth temporal transitions in illumination. Experiments show that Light-A-Video improves the temporal consistency of relighted video while maintaining the relighted image quality, ensuring coherent lighting transitions across frames. Project page: https://bujiazi.github.io/light-a-video.github.io/.

Motion-based controllable video generation offers the potential for creating captivating visual content. Existing methods typically necessitate model training to encode particular motion cues or incorporate fine-tuning to inject certain motion patterns, resulting in limited flexibility and generalization. In this work, we propose MotionClone, a training-free framework that enables motion cloning from reference videos to versatile motion-controlled video generation, including text-to-video and image-to-video. Based on the observation that the dominant components in temporal-attention maps drive motion synthesis, while the rest mainly capture noisy or very subtle motions, MotionClone utilizes sparse temporal attention weights as motion representations for motion guidance, facilitating diverse motion transfer across varying scenarios. Meanwhile, MotionClone allows for the direct extraction of motion representation through a single denoising step, bypassing the cumbersome inversion processes and thus promoting both efficiency and flexibility. Extensive experiments demonstrate that MotionClone exhibits proficiency in both global camera motion and local object motion, with notable superiority in terms of motion fidelity, textual alignment, and temporal consistency.

Visual preference alignment involves training Large Vision-Language Models (LVLMs) to predict human preferences between visual inputs. This is typically achieved by using labeled datasets of chosen/rejected pairs and employing optimization algorithms like direct preference optimization (DPO). Existing visual alignment methods, primarily designed for single-image scenarios, struggle to effectively handle the complexity of multi-image tasks due to the scarcity of diverse training data and the high cost of annotating chosen/rejected pairs. We present Multi-Image Augmented Direct Preference Optimization (MIA-DPO), a visual preference alignment approach that effectively handles multi-image inputs. MIA-DPO mitigates the scarcity of diverse multi-image training data by extending single-image data with unrelated images arranged in grid collages or pic-in-pic formats, significantly reducing the costs associated with multi-image data annotations. Our observation reveals that attention values of LVLMs vary considerably across different images. We use attention values to identify and filter out rejected responses the model may have mistakenly focused on. Our attention-aware selection for constructing the chosen/rejected pairs without relying on (i) human annotation, (ii) extra data, and (iii) external models or APIs. MIA-DPO is compatible with various architectures and outperforms existing methods on five multi-image benchmarks, achieving an average performance boost of 3.0% on LLaVA-v1.5 and 4.3% on the recent InternLM-XC2.5. Moreover, MIA-DPO has a minimal effect on the model's ability to understand single images.

In this paper, we propose MLLM-DataEngine, a novel closed-loop system that bridges data generation, model training, and evaluation. Within each loop iteration, the MLLM-DataEngine first analyzes the weakness of the model based on the evaluation results, then generates a proper incremental dataset for the next training iteration, and enhances the model capability iteratively. Compared with previous instruction fine-tuning dataset collection methods which are separate from the benchmarking, MLLM-DataEngine shows better targeting and can improve MLLMs’s capabilities more effectively. Firstly, we propose an Adaptive Bad-case Sampling module, which can effectively analyze model weakness based on the benchmarking results and adjust the generation of incremental datasets flexibly. Secondly, in order to ensure high-quality data for specific capability types, the most representative in-context examples and abundant information are provided to GPT-4, which helps GPT-4 fully comprehend the model’s weakness and further guarantees high-quality generated data. Through extensive experiments, we find MLLM-DataEngine could boost the MLLMs capability in a targeted and automatic manner without human participants. We hope MLLM-DataEngine could be a general solution for the following MLLMs data curation. Code, data, and model are available at https://github.com/opendatalab/MLLM-DataEngine.

Text-to-song generation, the task of creating vocals and accompaniment from textual inputs, poses significant challenges due to domain complexity and data scarcity. Existing approaches often employ multi-stage generation procedures, leading to cumbersome training and inference pipelines, as well as suboptimal overall generation quality due to error accumulation across stages. In this paper, we propose SongGen, a fully open-source, single-stage auto-regressive transformer designed for controllable song generation. The proposed model facilitates fine-grained control over diverse musical attributes, including lyrics and textual descriptions of instrumentation, genre, mood, and timbre, while also offering an optional three-second reference clip for voice cloning. Within a unified auto-regressive framework, SongGen supports two output modes: mixed mode, which generates a mixture of vocals and accompaniment directly, and dual-track mode, which synthesizes them separately for greater flexibility in downstream applications. We explore diverse token pattern strategies for each mode, leading to notable improvements and valuable insights. Furthermore, we design an automated data preprocessing pipeline with effective quality control. To foster community engagement and future research, we will release our model weights, training code, annotated data, and preprocessing pipeline. The code is available at https://github.com/LiuZH-19/SongGen.

While Rotary Position Embedding (RoPE) and its variants are widely adopted for their long-context capabilities, the extension of the 1D RoPE to video, with its complex spatio-temporal structure, remains an open challenge. This work first introduces a comprehensive analysis that identifies four key characteristics essential for the effective adaptation of RoPE to video, which have not been fully considered in prior work. As part of our analysis, we introduce a challenging V-NIAH-D (Visual Needle-In-A-Haystack with Distractors) task, which adds periodic distractors into V-NIAH. The V-NIAH-D task demonstrates that previous RoPE variants, lacking appropriate temporal dimension allocation, are easily misled by distractors. Based on our analysis, we introduce VideoRoPE, with a 3D structure designed to preserve spatio-temporal relationships. VideoRoPE features low-frequency temporal allocation to mitigate periodic oscillations, a diagonal layout to maintain spatial symmetry, and adjustable temporal spacing to decouple temporal and spatial indexing. VideoRoPE consistently surpasses previous RoPE variants, across diverse downstream tasks such as long video retrieval, video understanding, and video hallucination. Our code and model weights will be publicly released.

Text-to-image (T2I) diffusion/flow models have drawn considerable attention recently due to their remarkable ability to deliver flexible visual creations. Still, high-resolution image synthesis presents formidable challenges due to the scarcity and complexity of high-resolution content. Recent approaches have investigated training-free strategies to enable high-resolution image synthesis with pre-trained models. However, these techniques often struggle with generating high-quality visuals and tend to exhibit artifacts or low-fidelity details, as they typically rely solely on the endpoint of the low-resolution sampling trajectory while neglecting intermediate states that are critical for preserving structure and synthesizing finer detail. To this end, we present HiFlow, a training-free and model-agnostic framework to unlock the resolution potential of pre-trained flow models. Specifically, HiFlow establishes a virtual reference flow within the high-resolution space that effectively captures the characteristics of low-resolution flow information, offering guidance for high-resolution generation through three key aspects: initialization alignment for low-frequency consistency, direction alignment for structure preservation, and acceleration alignment for detail fidelity. By leveraging such flow-aligned guidance, HiFlow substantially elevates the quality of high-resolution image synthesis of T2I models and demonstrates versatility across their personalized variants. Extensive experiments validate HiFlow's capability in achieving superior high-resolution image quality over state-of-the-art methods.

Recent self-supervised learning (SSL) methods have demonstrated impressive results in learning visual representations from unlabeled remote sensing (RS) images. However, most RS images predominantly consist of scenographic scenes containing multiple ground objects without explicit foreground targets, which limits the performance of existing SSL methods that focus on foreground targets. This raises the question: Is there a method that can automatically aggregate similar objects within scenographic RS images, thereby enabling models to differentiate knowledge embedded in various geospatial patterns for improved feature representation? In this work, we present the pattern integration and enhancement vision transformer (PIEViT), a novel SSL framework designed specifically for RS imagery. PIEViT utilizes a teacher-student architecture to address both image-level and patch-level tasks. It employs a proposed, geospatial pattern cohesion (GPC) module to explore the natural clustering of patches, enhancing the differentiation of individual features. A feature integration projection (FIP) module is employed to further refine masked token reconstruction using geospatially clustered patches. We validated PIEViT across multiple downstream tasks, including object detection, semantic segmentation, and change detection. Experiments demonstrated that PIEViT enhances the representation of internal patch features, providing significant improvements over existing self-supervised baselines. It achieves excellent results in object detection, land cover classification, and change detection, underscoring its robustness, generalization, and transferability for RS image interpretation tasks.

The integration of visual encoders and large language models (LLMs) has driven recent progress in multimodal large language models (MLLMs). However, the scarcity of high-quality instruction-tuning data for vision-language tasks remains a challenge. The current leading paradigm, such as LLaVA, relies on language-only GPT-4 to generate data, which requires pre-annotated image captions and detection bounding boxes, suffering from understanding image details. A practical solution to this problem would be to utilize the available multimodal large language models to generate instruction data for vision-language tasks. However, it's worth noting that the currently accessible MLLMs are not as powerful as their LLM counterparts, as they tend to produce inadequate responses and generate false information. As a solution for addressing the current issue, this paper proposes the Visual Instruction Generation and Correction (VIGC) framework that enables multimodal large language models to generate instruction-tuning data and progressively enhance its quality on-the-fly. Specifically, Visual Instruction Generation (VIG) guides the vision-language model to generate diverse instruction-tuning data. To ensure generation quality, Visual Instruction Correction (VIC) adopts an iterative update mechanism to correct any inaccuracies in data produced by VIG, effectively reducing the risk of hallucination. Leveraging the diverse, high-quality data generated by VIGC, we finetune mainstream models and validate data quality based on various evaluations. Experimental results demonstrate that VIGC not only compensates for the shortcomings of language-only data generation methods, but also effectively enhances the benchmark performance. The models, datasets, and code are available at https://opendatalab.github.io/VIGC

Contrastive Language-Image Pre-training (CLIP) plays an essential role in extracting valuable content information from images across diverse tasks. It aligns textual and visual modalities to comprehend the entire image, including all the details, even those irrelevant to specific tasks. How-ever, for a finer understanding and controlled editing of images, it becomes crucial to focus on specific regions of interest, which can be indicated as points, masks, or boxes by humans or perception models. To fulfill the require we introduce Alpha-CLIp, an enhanced version of CLIP with an auxiliary alpha channel to suggest attentive regions and fine-tuned with constructed millions of RGBA region-text pairs. Alpha-CLIP not only preserves the visual recognition ability of CLIP but also enables precise control over the emphasis of image contents. It demonstrates effectiveness in various tasks, including but not limited to open-world recognition, multimodal large language models, and conditional 2D / 3D generation. It has a strong potential to serve as a versatile tool for image-related tasks. Our project is with codes and models available is linked to https://aleafy.github.io/alpha-clip/.

Hallucination, posed as a pervasive challenge of multi-modal large language models (MLLMs), has significantly impeded their real-world usage that demands precise judgment. Existing methods mitigate this issue with either training with specific designed data or inferencing with external knowledge from other sources, incurring inevitable additional costs. In this paper, we present OPERA, a novel MLLM decoding method grounded in an Over-trust Penalty and a Retrospection-Allocation strategy, serving as a nearly free lunch to alleviate the hallucination issue without additional data, knowledge, or training. Our approach begins with an interesting observation that, most hallucinations are closely tied to the knowledge aggregation patterns manifested in the self-attention matrix, i.e., MLLMs tend to generate new tokens by focusing on a few summary tokens, but not all the previous tokens. Such partial overtrust inclination results in the neglecting of image tokens and describes the image content with hallucination. Based on the observation, OPERA introduces a penalty term on the model logits during the beam-search decoding to mitigate the over-trust issue, along with a rollback strategy that retrospects the presence of summary tokens in the previously generated tokens, and re-allocate the token selection if necessary. With extensive experiments, OPERA shows significant hallucination-mitigating performance on different MLLMs and metrics, proving its effectiveness and generality. Our code is at: https://github.com/shikiw/OPERA.

To serve the intricate and varied demands of image editing, precise and flexible manipulation in image content is indispensable. Recently, Drag-based editing methods have gained impressive performance. However, these methods predominantly center on point dragging, resulting in two noteworthy drawbacks, namely “miss tracking ”, where dif-ficulties arise in accurately tracking the predetermined han-dle points, and “ambiguous tracking”, where tracked points are potentially positioned in wrong regions that closely re-semble the handle points. To address the above issues, we propose FreeDrag, a feature dragging methodology designed to free the burden on point tracking. The Free-Drag incorporates two key designs, i.e., template feature via adaptive updating and line search with backtracking, the former improves the stability against drastic content change by elaborately controlling the feature updating scale after each dragging, while the latter alleviates the misguidance from similar points by actively restricting the search area in a line. These two technologies together contribute to a more stable semantic dragging with higher efficiency. Comprehensive experimental results substantiate that our approach significantly outperforms pre-existing methodologies, offering reliable point-based editing even in various complex scenarios.

Extracting water bodies using C-band synthetic aperture radar (SAR) images has high reliability. However, the limited backscatter sensitivity of SAR data makes it difficult to differentiate between water and other features such as roads, building shadows, and more. To tackle these issues, we have implemented several strategies: Firstly, we have augmented our input data by incorporating polarized VV and VH data, as well as additional modalities such as DTM, DSM, and land use information. Through rigorous ablation studies, we have validated the efficacy of these data modalities, even in the presence of potential inaccuracies. Secondly, we have constructed a Siamese network for feature extraction and fusion across multiple modalities. Experimental results reveal that our proposed framework surpasses traditional feature extraction methods, yielding a 0.8% increase in F1 score. Finally, we have employed techniques such as stochastic multi-scale training, two-stage training, and model ensemble to further enhance performance. Notably, our method secured the second position in the 2024 IEEE GRSS Data Fusion Contest (DFC) Track 1 test phase, achieving an F1 score of 79.170%.

We present the ShareGPT4Video series, aiming to facilitate the video understanding of large video-language models (LVLMs) and the video generation of text-to-video models (T2VMs) via dense and precise captions. The series comprises: 1) ShareGPT4Video, 40K GPT4V annotated dense captions of videos with various lengths and sources, developed through carefully designed data filtering and annotating strategy. 2) ShareCaptioner-Video, an efficient and capable captioning model for arbitrary videos, with 4.8M high-quality aesthetic videos annotated by it. 3) ShareGPT4Video-8B, a simple yet superb LVLM that reached SOTA performance on three advancing video benchmarks. To achieve this, taking aside the non-scalable costly human annotators, we find using GPT4V to caption video with a naive multi-frame or frame-concatenation input strategy leads to less detailed and sometimes temporal-confused results. We argue the challenge of designing a high-quality video captioning strategy lies in three aspects: 1) Inter-frame precise temporal change understanding. 2) Intra-frame detailed content description. 3) Frame-number scalability for arbitrary-length videos. To this end, we meticulously designed a differential video captioning strategy, which is stable, scalable, and efficient for generating captions for videos with arbitrary resolution, aspect ratios, and length. Based on it, we construct ShareGPT4Video, which contains 40K high-quality videos spanning a wide range of categories, and the resulting captions encompass rich world knowledge, object attributes, camera movements, and crucially, detailed and precise temporal descriptions of events. Based on ShareGPT4Video, we further develop ShareCaptioner-Video, a superior captioner capable of efficiently generating high-quality captions for arbitrary videos. We annotated 4.8M aesthetically appealing videos by it and verified their effectiveness on a 10-second text2video generation task. For video understanding, we verified the effectiveness of ShareGPT4Video on several current LVLM architectures and presented our superb new LVLM ShareGPT4Video-8B. All the models, strategies, and annotations will be open-sourced and we hope this project can serve as a pivotal resource for advancing both the LVLMs and T2VMs community.

Large vision-language models (LVLMs) have recently achieved rapid progress, sparking numerous studies to evaluate their multi-modal capabilities. However, we dig into current evaluation works and identify two primary issues: 1) Visual content is unnecessary for many samples. The answers can be directly inferred from the questions and options, or the world knowledge embedded in LLMs. This phenomenon is prevalent across current benchmarks. For instance, GeminiPro achieves 42.7% on the MMMU benchmark without any visual input, and outperforms the random choice baseline across six benchmarks near 24% on average. 2) Unintentional data leakage exists in LLM and LVLM training. LLM and LVLM could still answer some visual-necessary questions without visual content, indicating the memorizing of these samples within large-scale training data. For example, Sphinx-X-MoE gets 43.6% on MMMU without accessing images, surpassing its LLM backbone with 17.9%. Both problems lead to misjudgments of actual multi-modal gains and potentially misguide the study of LVLM. To this end, we present MMStar, an elite vision-indispensable multi-modal benchmark comprising 1,500 samples meticulously selected by humans. MMStar benchmarks 6 core capabilities and 18 detailed axes, aiming to evaluate LVLMs' multi-modal capacities with carefully balanced and purified samples. These samples are first roughly selected from current benchmarks with an automated pipeline, human review is then involved to ensure each curated sample exhibits visual dependency, minimal data leakage, and requires advanced multi-modal capabilities. Moreover, two metrics are developed to measure data leakage and actual performance gain in multi-modal training. We evaluate 16 leading LVLMs on MMStar to assess their multi-modal capabilities, and on 7 benchmarks with the proposed metrics to investigate their data leakage and actual multi-modal gain.

The Large Vision-Language Model (LVLM) field has seen significant advancements, yet its progression has been hindered by challenges in comprehending fine-grained visual content due to limited resolution. Recent efforts have aimed to enhance the high-resolution understanding capabilities of LVLMs, yet they remain capped at approximately 1500 $\times$ 1500 pixels and constrained to a relatively narrow resolution range. This paper represents InternLM-XComposer2-4KHD, a groundbreaking exploration into elevating LVLM resolution capabilities up to 4K HD (3840 × 1600) and beyond. Concurrently, considering the ultra-high resolution may not be necessary in all scenarios, it supports a wide range of diverse resolutions from 336 pixels to 4K standard, significantly broadening its scope of applicability. Specifically, this research advances the patch division paradigm by introducing a novel extension: dynamic resolution with automatic patch configuration. It maintains the training image aspect ratios while automatically varying patch counts and configuring layouts based on a pre-trained Vision Transformer (ViT) (336 $\times$ 336), leading to dynamic training resolution from 336 pixels to 4K standard. Our research demonstrates that scaling training resolution up to 4K HD leads to consistent performance enhancements without hitting the ceiling of potential improvements. InternLM-XComposer2-4KHD shows superb capability that matches or even surpasses GPT-4V and Gemini Pro in 10 of the 16 benchmarks.

Generating natural and meaningful responses to communicate with multi-modal human inputs is a fundamental capability of Large Vision-Language Models (LVLMs). While current open-source LVLMs demonstrate promising performance in simplified scenarios such as single-turn single-image input, they fall short in real-world conversation scenarios such as following instructions in a long context history with multi-turn and multi-images. Existing LVLM benchmarks primarily focus on single-choice questions or short-form responses, which do not adequately assess the capabilities of LVLMs in real-world human-AI interaction applications. Therefore, we introduce MMDU, a comprehensive benchmark, and MMDU-45k, a large-scale instruction tuning dataset, designed to evaluate and improve LVLMs' abilities in multi-turn and multi-image conversations. We employ the clustering algorithm to find the relevant images and textual descriptions from the open-source Wikipedia and construct the question-answer pairs by human annotators with the assistance of the GPT-4o model.MMDU has a maximum of 18k image+text tokens, 20 images, and 27 turns, which is at least 5x longer than previous benchmarks and poses challenges to current LVLMs. Our in-depth analysis of 15 representative LVLMs using MMDU reveals that open-source LVLMs lag behind closed-source counterparts due to limited conversational instruction tuning data.We demonstrate that fine-tuning open-source LVLMs on MMDU-45k significantly address this gap, generating longer and more accurate conversations, and improving scores on MMDU and existing benchmarks (MMStar: +1.1%, MathVista: +1.5%, ChartQA: +1.2%). Our contributions pave the way for bridging the gap between current LVLM models and real-world application demands. The links to MMDU, and MMDU-45k are available in the supplementary material.

Understanding documents with rich layouts and multi-modal components is a long-standing and practical task. Recent Large Vision-Language Models (LVLMs) have made remarkable strides in various tasks, particularly in single-page document understanding (DU). However, their abilities on long-context DU remain an open problem. This work presents MMLONGBENCH-DOC, a long-context, multi- modal benchmark comprising 1,082 expert-annotated questions. Distinct from previous datasets, it is constructed upon 135 lengthy PDF-formatted documents with an average of 47.5 pages and 21,214 textual tokens. Towards comprehensive evaluation, answers to these questions rely on pieces of evidence from (1) different sources (text, image, chart, table, and layout structure) and (2) various locations (i.e., page number). Moreover, 33.7\% of the questions are cross-page questions requiring evidence across multiple pages. 20.6\% of the questions are designed to be unanswerable for detecting potential hallucinations. Experiments on 14 LVLMs demonstrate that long-context DU greatly challenges current models. Notably, the best-performing model, GPT-4o, achieves an F1 score of only 44.9\%, while the second-best, GPT-4V, scores 30.5\%. Furthermore, 12 LVLMs (all except GPT-4o and GPT-4V) even present worse performance than their LLM counterparts which are fed with lossy-parsed OCR documents. These results validate the necessity of future research toward more capable long-context LVLMs.

This paper presents VideoStreaming, an advanced vision-language large model (VLLM) for video understanding, that capably understands arbitrary-length video with a constant number of video tokens streamingly encoded and adaptively selected. The challenge of video understanding in the vision language area mainly lies in the significant computational burden caused by the great number of tokens extracted from long videos. Previous works rely on sparse sampling or frame compression to reduce tokens. However, such approaches either disregard temporal information in a long time span or sacrifice spatial details, resulting in flawed compression. To address these limitations, our VideoStreaming has two core designs: Memory-Propagated Streaming Encoding and Adaptive Memory Selection. The Memory-Propagated Streaming Encoding architecture segments long videos into short clips and sequentially encodes each clip with a propagated memory. In each iteration, we utilize the encoded results of the preceding clip as historical memory, which is integrated with the current clip to distill a condensed representation that encapsulates the video content up to the current timestamp. This method not only incorporates long-term temporal dynamics into the streaming encoding process but also yields a fixed-length memory as a global representation for arbitrarily long videos. After the encoding process, the Adaptive Memory Selection strategy selects a constant number of question-related memories from all the historical memories, and feeds them into the LLM to generate informative responses. The question-related selection reduces redundancy within the memories, enabling efficient and precise video understanding. Meanwhile, the disentangled video extraction and reasoning design allows the LLM to answer different questions about a video by directly selecting corresponding memories, without the need to encode the whole video for each question. Through extensive experiments, our model achieves superior performance and higher efficiency on long video benchmarks, showcasing precise temporal comprehension for detailed question answering.

Understanding and modeling the 3D scene from a single image is a practical problem. A recent advance proposes a panoptic 3D scene reconstruction task that performs both 3D reconstruction and 3D panoptic segmentation from a single image. Although having made substantial progress, recent works only focus on top-down approaches that fill 2D instances into 3D voxels according to estimated depth, which hinders their performance by two ambiguities. (1) instance-channel ambiguity: The variable ids of instances in each scene lead to ambiguity during filling voxel channels with 2D information, confusing the following 3D refinement. (2) voxel-reconstruction ambiguity: 2D-to-3D lifting with estimated single view depth only propagates 2D information onto the surface of 3D regions, leading to ambiguity during the reconstruction of regions behind the frontal view surface. In this paper, we propose BUOL, a Bottom-Up framework with Occupancy-aware Lifting to address the two issues for panoptic 3D scene reconstruction from a single image. For instance-channel ambiguity, a bottom-up framework lifts 2D information to 3D voxels based on deterministic semantic assignments rather than arbitrary instance id assignments. The 3D voxels are then refined and grouped into 3D instances according to the predicted 2D instance centers. For voxel-reconstruction ambiguity, the estimated multi-plane occupancy is leveraged together with depth to fill the whole regions of things and stuff. Our method shows a tremendous performance advantage over state-of-the-art methods on synthetic dataset 3D-Front and real-world dataset Matterport3D. Code and models will be released.

Recent advances in detecting arbitrary objects in the real world are trained and evaluated on object detection datasets with a relatively restricted vocabulary. To facilitate the development of more general visual object detection, we propose V3Det, a vast vocabulary visual detection dataset with precisely annotated bounding boxes on massive images. V3Det has several appealing properties: 1) Vast Vocabulary: It contains bounding boxes of objects from 13,204 categories on real-world images, which is 10 times larger than the existing large vocabulary object detection dataset, e.g., LVIS. 2) Hierarchical Category Organization: The vast vocabulary of V3Det is organized by a hierarchical category tree which annotates the inclusion relationship among categories, encouraging the exploration of category relationships in vast and open vocabulary object detection. 3) Rich Annotations: V3Det comprises precisely annotated objects in 243k images and professional descriptions of each category written by human experts and a powerful chatbot. By offering a vast exploration space, V3Det enables extensive benchmarks on both vast and open vocabulary object detection, leading to new observations, practices, and insights for future research. It has the potential to serve as a cornerstone dataset for developing more general visual perception systems. V3Det is available at https://v3det.openxlab.org.cn/.

The diversity of building architecture styles of global cities situated on various landforms, the degraded optical imagery affected by clouds and shadows, and the significant inter-class imbalance of roof types pose challenges for designing a robust and accurate building roof instance segmentor. To address these issues, we propose an effective framework to fulfill semantic interpretation of individual buildings with high-resolution optical satellite imagery. Specifically, the leveraged domain adapted pretraining strategy and composite dual-backbone greatly facilitates the discriminative feature learning. Moreover, new data augmentation pipeline, stochastic weight averaging (SWA) training and instance segmentation based model ensemble in testing are utilized to acquire additional performance boost. Experiment results show that our approach ranks in the first place of the 2023 IEEE GRSS Data Fusion Contest (DFC) Track 1 test phase (mAP50:50.6%). Note-worthily, we have also explored the potential of multimodal data fusion with both optical satellite imagery and SAR data.

Unifying the correlative single-view satellite image building extraction and height estimation tasks indicates a promising way to share representations and acquire generalist model for large-scale urban 3D reconstruction. However, the common spatial misalignment between building footprints and stereo-reconstructed nDSM height labels incurs degraded performance on both tasks. To address this issue, we propose a Height-hierarchy Guided Dual-decoder Network (HGDNet) to estimate building height. Under the guidance of synthesized discrete height-hierarchy nDSM, auxiliary height-hierarchical building extraction branch enhance the height estimation branch with implicit constraints, yielding an accuracy improvement of more than 6% on the DFC 2023 track2 dataset. Additional two-stage cascade architecture is adopted to achieve more accurate building extraction. Experiments on the DFC 2023 Track 2 dataset shows the superiority of the proposed method in building height estimation (δ1:0.8012), instance extraction (AP50:0.7730), and the final average score 0.7871 ranks in the first place in test phase.

3D content creation from a single image is a long-standing yet highly desirable task. Recent advances introduce 2D diffusion priors, yielding reasonable results. However, existing methods are not hyper-realistic enough for post-generation usage, as users cannot view, render and edit the resulting 3D content from a full range. To address these challenges, we introduce HyperDreamer with several key designs and appealing properties: 1) Full-range viewable: 360° mesh modeling with high-resolution textures enables the creation of visually compelling 3D models from a full range of observation points. 2) Full-range renderable: Fine-grained semantic segmentation and data-driven priors are incorporated as guidance to learn reasonable albedo, roughness, and specular properties of the materials, enabling semantic-aware arbitrary material estimation. 3) Full-range editable: For a generated model or their own data, users can interactively select any region via a few clicks and efficiently edit the texture with text-based guidance. Extensive experiments demonstrate the effectiveness of HyperDreamer in modeling region-aware materials with high-resolution textures and enabling user-friendly editing. We believe that HyperDreamer holds promise for advancing 3D content creation and finding applications in various domains.