Wei Shao

Zhe Chen, Weiyun Wang, Yue Cao et al.

We introduce InternVL 2.5, an advanced multimodal large language model (MLLM) series that builds upon InternVL 2.0, maintaining its core model architecture while introducing significant enhancements in training and testing strategies as well as data quality. In this work, we delve into the relationship between model scaling and performance, systematically exploring the performance trends in vision encoders, language models, dataset sizes, and test-time configurations. Through extensive evaluations on a wide range of benchmarks, including multi-discipline reasoning, document understanding, multi-image / video understanding, real-world comprehension, multimodal hallucination detection, visual grounding, multilingual capabilities, and pure language processing, InternVL 2.5 exhibits competitive performance, rivaling leading commercial models such as GPT-4o and Claude-3.5-Sonnet. Notably, our model is the first open-source MLLMs to surpass 70% on the MMMU benchmark, achieving a 3.7-point improvement through Chain-of-Thought (CoT) reasoning and showcasing strong potential for test-time scaling. We hope this model contributes to the open-source community by setting new standards for developing and applying multimodal AI systems. HuggingFace demo see https://huggingface.co/spaces/OpenGVLab/InternVL

Jinguo Zhu, Weiyun Wang, Zhe Chen et al.

We introduce InternVL3, a significant advancement in the InternVL series featuring a native multimodal pre-training paradigm. Rather than adapting a text-only large language model (LLM) into a multimodal large language model (MLLM) that supports visual inputs, InternVL3 jointly acquires multimodal and linguistic capabilities from both diverse multimodal data and pure-text corpora during a single pre-training stage. This unified training paradigm effectively addresses the complexities and alignment challenges commonly encountered in conventional post-hoc training pipelines for MLLMs. To further improve performance and scalability, InternVL3 incorporates variable visual position encoding (V2PE) to support extended multimodal contexts, employs advanced post-training techniques such as supervised fine-tuning (SFT) and mixed preference optimization (MPO), and adopts test-time scaling strategies alongside an optimized training infrastructure. Extensive empirical evaluations demonstrate that InternVL3 delivers superior performance across a wide range of multi-modal tasks. In particular, InternVL3-78B achieves a score of 72.2 on the MMMU benchmark, setting a new state-of-the-art among open-source MLLMs. Its capabilities remain highly competitive with leading proprietary models, including ChatGPT-4o, Claude 3.5 Sonnet, and Gemini 2.5 Pro, while also maintaining strong pure-language proficiency. In pursuit of open-science principles, we will publicly release both the training data and model weights to foster further research and development in next-generation MLLMs.

Yingping Liang, Yutao Hu, Wenqi Shao et al.

Depth completion involves predicting dense depth maps from sparse LiDAR inputs. However, sparse depth annotations from sensors limit the availability of dense supervision, which is necessary for learning detailed geometric features. In this paper, we propose a two-stage knowledge distillation framework that leverages powerful monocular foundation models to provide dense supervision for depth completion. In the first stage, we introduce a pre-training strategy that generates diverse training data from natural images, which distills geometric knowledge to depth completion. Specifically, we simulate LiDAR scans by utilizing monocular depth and mesh reconstruction, thereby creating training data without requiring ground-truth depth. Besides, monocular depth estimation suffers from inherent scale ambiguity in real-world settings. To address this, in the second stage, we employ a scale- and shift-invariant loss (SSI Loss) to learn real-world scales when fine-tuning on real-world datasets. Our two-stage distillation framework enables depth completion models to harness the strengths of monocular foundation models. Experimental results demonstrate that models trained with our two-stage distillation framework achieve state-of-the-art performance, ranking \textbf{first place} on the KITTI benchmark. Code is available at https://github.com/Sharpiless/DMD3C

Junting Chen, Checheng Yu, Xunzhe Zhou et al.

Heterogeneous multi-robot systems (HMRS) have emerged as a powerful approach for tackling complex tasks that single robots cannot manage alone. Current large-language-model-based multi-agent systems (LLM-based MAS) have shown success in areas like software development and operating systems, but applying these systems to robot control presents unique challenges. In particular, the capabilities of each agent in a multi-robot system are inherently tied to the physical composition of the robots, rather than predefined roles. To address this issue, we introduce a novel multi-agent framework designed to enable effective collaboration among heterogeneous robots with varying embodiments and capabilities, along with a new benchmark named Habitat-MAS. One of our key designs is $\textit{Robot Resume}$: Instead of adopting human-designed role play, we propose a self-prompted approach, where agents comprehend robot URDF files and call robot kinematics tools to generate descriptions of their physics capabilities to guide their behavior in task planning and action execution. The Habitat-MAS benchmark is designed to assess how a multi-agent framework handles tasks that require embodiment-aware reasoning, which includes 1) manipulation, 2) perception, 3) navigation, and 4) comprehensive multi-floor object rearrangement. The experimental results indicate that the robot's resume and the hierarchical design of our multi-agent system are essential for the effective operation of the heterogeneous multi-robot system within this intricate problem context.

Yingping Liang, Ying Fu, Yutao Hu et al.

Optical flow estimation is a crucial subfield of computer vision, serving as a foundation for video tasks. However, the real-world robustness is limited by animated synthetic datasets for training. This introduces domain gaps when applied to real-world applications and limits the benefits of scaling up datasets. To address these challenges, we propose \textbf{Flow-Anything}, a large-scale data generation framework designed to learn optical flow estimation from any single-view images in the real world. We employ two effective steps to make data scaling-up promising. First, we convert a single-view image into a 3D representation using advanced monocular depth estimation networks. This allows us to render optical flow and novel view images under a virtual camera. Second, we develop an Object-Independent Volume Rendering module and a Depth-Aware Inpainting module to model the dynamic objects in the 3D representation. These two steps allow us to generate realistic datasets for training from large-scale single-view images, namely \textbf{FA-Flow Dataset}. For the first time, we demonstrate the benefits of generating optical flow training data from large-scale real-world images, outperforming the most advanced unsupervised methods and supervised methods on synthetic datasets. Moreover, our models serve as a foundation model and enhance the performance of various downstream video tasks.

Runjian Chen, Wenqi Shao, Bo Zhang et al.

Deep-learning-based autonomous driving (AD) perception introduces a promising picture for safe and environment-friendly transportation. However, the over-reliance on real labeled data in LiDAR perception limits the scale of on-road attempts. 3D real world data is notoriously time-and-energy-consuming to annotate and lacks corner cases like rare traffic participants. On the contrary, in simulators like CARLA, generating labeled LiDAR point clouds with corner cases is a piece of cake. However, introducing synthetic point clouds to improve real perception is non-trivial. This stems from two challenges: 1) sample efficiency of simulation datasets 2) simulation-to-real gaps. To overcome both challenges, we propose a plug-and-play method called JiSAM , shorthand for Jittering augmentation, domain-aware backbone and memory-based Sectorized AlignMent. In extensive experiments conducted on the famous AD dataset NuScenes, we demonstrate that, with SOTA 3D object detector, JiSAM is able to utilize the simulation data and only labels on 2.5% available real data to achieve comparable performance to models trained on all real data. Additionally, JiSAM achieves more than 15 mAPs on the objects not labeled in the real training set. We will release models and codes.

Yu Li, Yuenan Hou, Yingmei Wei et al.

Multi-modal 3D understanding is a fundamental task in computer vision. Previous multi-modal fusion methods typically employ a single, dense fusion network, struggling to handle the significant heterogeneity and complexity across modalities, leading to suboptimal performance. In this paper, we propose MoE3D, which integrates Mixture of Experts (MoE) into the multi-modal learning framework. The core is that we deploy a set of specialized "expert" networks, each adept at processing a specific modality or a mode of cross-modal interaction. Specifically, the MoE-based transformer is designed to better utilize the complementary information hidden in the visual features. Information aggregation module is put forward to further enhance the fusion performance. Top-1 gating is employed to make one expert process features with expert groups, ensuring high efficiency. We further propose a progressive pre-training strategy to better leverage the semantic and 2D prior, thus equipping the network with good initialization. Our MoE3D achieves competitive performance across four prevalent 3D understanding tasks. Notably, our MoE3D surpasses the top-performing counterpart by 6.1 mIoU on Multi3DRefer.

Yingping Liang, Yutao Hu, Wenqi Shao et al.

Feature matching plays a fundamental role in many computer vision tasks, yet existing methods heavily rely on scarce and clean multi-view image collections, which constrains their generalization to diverse and challenging scenarios. Moreover, conventional feature encoders are typically trained on single-view 2D images, limiting their capacity to capture 3D-aware correspondences. In this paper, we propose a novel two-stage framework that lifts 2D images to 3D space, named as \textbf{Lift to Match (L2M)}, taking full advantage of large-scale and diverse single-view images. To be specific, in the first stage, we learn a 3D-aware feature encoder using a combination of multi-view image synthesis and 3D feature Gaussian representation, which injects 3D geometry knowledge into the encoder. In the second stage, a novel-view rendering strategy, combined with large-scale synthetic data generation from single-view images, is employed to learn a feature decoder for robust feature matching, thus achieving generalization across diverse domains. Extensive experiments demonstrate that our method achieves superior generalization across zero-shot evaluation benchmarks, highlighting the effectiveness of the proposed framework for robust feature matching.

Jiahao Xia, Yutao Hu, Yaolei Qi et al.

Solving medical imaging data scarcity through semantic image generation has attracted significant attention in recent years. However, existing methods primarily focus on generating whole-organ or large-tissue structures, showing limited effectiveness for organs with fine-grained structure. Due to stringent topological consistency, fragile coronary features, and complex 3D morphological heterogeneity in cardiac imaging, accurately reconstructing fine-grained anatomical details of the heart remains a great challenge. To address this problem, in this paper, we propose the Fine-grained Cardiac image Synthesis(FCaS) framework, established on 3D template conditional diffusion model. FCaS achieves precise cardiac structure generation using Template-guided Conditional Diffusion Model (TCDM) through bidirectional mechanisms, which provides the fine-grained topological structure information of target image through the guidance of template. Meanwhile, we design a deformable Mask Generation Module (MGM) to mitigate the scarcity of high-quality and diverse reference mask in the generation process. Furthermore, to alleviate the confusion caused by imprecise synthetic images, we propose a Confidence-aware Adaptive Learning (CAL) strategy to facilitate the pre-training of downstream segmentation tasks. Specifically, we introduce the Skip-Sampling Variance (SSV) estimation to obtain confidence maps, which are subsequently employed to rectify the pre-training on downstream tasks. Experimental results demonstrate that images generated from FCaS achieves state-of-the-art performance in topological consistency and visual quality, which significantly facilitates the downstream tasks as well. Code will be released in the future.