Personalizing 3D scenes from a single reference image enables intuitive user-guided editing, which requires achieving both multi-view consistency across perspectives and referential consistency with the input image. However, these goals are particularly challenging due to the viewpoint bias caused by the limited perspective provided in a single image. Lacking the mechanisms to effectively expand reference information beyond the original view, existing methods of image-conditioned 3DGS personalization often suffer from this viewpoint bias and struggle to produce consistent results. Therefore, in this paper, we present Consistent Personalization for 3D Gaussian Splatting (CP-GS), a framework that progressively propagates the single-view reference appearance to novel perspectives. In particular, CP-GS integrates pre-trained image-to-3D generation and iterative LoRA fine-tuning to extract and extend the reference appearance, and finally produces faithful multi-view guidance images and the personalized 3DGS outputs through a view-consistent generation process guided by geometric cues. Extensive experiments on real-world scenes show that our CP-GS effectively mitigates the viewpoint bias, achieving high-quality image-conditioned 3DGS personalization that significantly outperforms existing methods.

3D Gaussian Splatting (3DGS) has demonstrated impressive Novel View Synthesis (NVS) results in a real-time rendering manner. During training, it relies heavily on the average magnitude of view-space positional gradients to grow Gaussians to reduce rendering loss. However, this average operation smooths the positional gradients from different viewpoints and rendering errors from different pixels, hindering the growth and optimization of many defective Gaussians. This leads to strong spurious artifacts in some areas. To address this problem, we propose Hard Gaussian Splatting, dubbed HGS, which considers multi-view significant positional gradients and rendering errors to grow hard Gaussians that fill the gaps of classical Gaussian Splatting on 3D scenes, thus achieving superior NVS results. In detail, we present positional gradient driven HGS, which leverages multi-view significant positional gradients to uncover hard Gaussians. Moreover, we propose rendering error guided HGS, which identifies noticeable pixel rendering errors and potentially over-large Gaussians to jointly mine hard Gaussians. By growing and optimizing these hard Gaussians, our method helps to resolve blurring and needle-like artifacts. Experiments on various datasets demonstrate that our method achieves state-of-the-art rendering quality while maintaining real-time efficiency, yielding LPIPS improvements of 5.1%, 19.7% and 6.3% on Mip-NeRF360, Tanks&Temples and Deep Blending, respectively.

In this paper, we aim to create physical digital twins of deformable objects under interaction. Existing methods focus more on the physical learning of current state modeling, but generalize worse to future prediction. This is because existing methods ignore the intrinsic physical properties of deformable objects, resulting in the limited physical learning in the current state modeling. To address this, we present NeuSpring, a neural spring field for the reconstruction and simulation of deformable objects from videos. Built upon spring-mass models for realistic physical simulation, our method consists of two major innovations: 1) a piecewise topology solution that efficiently models multi-region spring connection topologies using zero-order optimization, which considers the material heterogeneity of real-world objects. 2) a neural spring field that represents spring physical properties across different frames using a canonical coordinate-based neural network, which effectively leverages the spatial associativity of springs for physical learning. Experiments on real-world datasets demonstrate that our NeuSping achieves superior reconstruction and simulation performance for current state modeling and future prediction, with Chamfer distance improved by 20% and 25%, respectively.

Drag-Based Image Editing (DBIE), which allows users to manipulate images by directly dragging objects within them, has recently attracted much attention from the community. However, it faces two key challenges: (i) point-based drag is often highly ambiguous and difficult to align with user intentions; (ii) current DBIE methods primarily rely on alternating between motion supervision and point tracking, which is not only cumbersome but also fails to produce high-quality results. These limitations motivate us to explore DBIE from a new perspective---unifying it as a Latent Region Optimization (LRO) problem that aims to use region-level geometric transformations to optimize latent code to realize drag manipulation. Thus, by specifying the areas and types of geometric transformations, we can effectively address the ambiguity issue. We also propose a simple yet effective editing framework, dubbed DragNeXt. It solves LRO through Progressive Backward Self-Intervention (PBSI), simplifying the overall procedure of the alternating workflow while further enhancing quality by fully leveraging region-level structure information and progressive guidance from intermediate drag states. We validate DragNeXt on our NextBench, and extensive experiments demonstrate that our proposed method can significantly outperform existing approaches.

Few-Shot Class-Incremental Learning (FSCIL) requires models to be updated incrementally with limited labeled samples given in each session, differing from the traditional training paradigm and easily resulting in severe spurious relations between categories. Thus, in this paper, we propose to address FSCIL from a new perspective: enhancing FSCIL via disentangling spurious relations between categories. Accordingly, we propose a simple yet effective approach, dubbed ConTrollable Relation-disentangLed Few-Shot Class-Incremental Learning (CTRL-FSCIL). Specifically, during a base session, we propose to anchor base class embeddings in feature space and build disentangled proxies to bridge gaps between the learning processes of categories encountered in different sessions, making category relations controllable. Furthermore, during incremental learning, the parameters of the backbone network are frozen in order to relieve the negative impact of data scarcity. Meanwhile, a relation disentanglement loss is employed to guide a relation control module to disentangle spurious relations between learned categories. In this way, spurious relation issues in FSCIL can be alleviated. Extensive experiments on CIFAR-100, mini-ImageNet, and CUB-200 demonstrate the effectiveness of CTRL-FSCIL. Our code has been publicly released on github.

Recently, large efforts have been made to design efficient linear-complexity visual Transformers. However, current linear attention models are generally unsuitable to be deployed in resource-constrained mobile devices, due to suffering from either few efficiency gains or significant accuracy drops. In this paper, we propose a new deCoupled duAl-interactive lineaR attEntion (CARE) mechanism, revealing that features’ decoupling and interaction can fully unleash the power of linear attention. We first propose an asymmetrical feature decoupling strategy that asymmetrically decouples the learning process for local inductive bias and long-range dependencies, thereby preserving sufficient local and global information while effectively enhancing the efficiency of models. Then, a dynamic memory unit is employed to maintain critical information along the network pipeline. Moreover, we design a dual interaction module to effectively facilitate interaction between local inductive bias and long-range information as well as among features at different layers. By adopting a decoupled learning way and fully exploiting complementarity across features, our method can achieve both high efficiency and accuracy. Extensive experiments on ImageNet-1K, COCO, and ADE20K datasets demonstrate the effectiveness of our approach, e.g., achieving 78.4/82.1% top-1 accuracy on ImagegNet-1K at the cost of only 0.7/1.9 GMACs. Codes will be released on github.

The Multimodal Large Language Model (MLLM) is currently experiencing rapid growth, driven by the advanced capabilities of language-based LLMs. Unlike their specialist predecessors, existing MLLMs are evolving towards a Multimodal Generalist paradigm. Initially limited to understanding multiple modalities, these models have advanced to not only comprehend but also generate across modalities. Their capabilities have expanded from coarse-grained to fine-grained multimodal understanding and from supporting singular modalities to accommodating a wide array of or even arbitrary modalities. To assess the capabilities of various MLLMs, a diverse array of benchmark test sets has been proposed. This leads to a critical question: Can we simply assume that higher performance across tasks indicates a stronger MLLM capability, bringing us closer to human-level AI? We argue that the answer is not as straightforward as it seems. In this project, we introduce an evaluation framework to delineate the capabilities and behaviors of current multimodal generalists. This framework, named General-Level, establishes 5-scale levels of MLLM performance and generality, offering a methodology to compare MLLMs and gauge the progress of existing systems towards more robust multimodal generalists and, ultimately, towards AGI (Artificial General Intelligence). Central to our framework is the use of Synergy as the evaluative criterion, categorizing capabilities based on whether MLLMs preserve synergy across comprehension and generation, as well as across multimodal interactions. To evaluate the comprehensive abilities of various generalists, we present a massive multimodal benchmark, General-Bench, which encompasses a broader spectrum of skills, modalities, formats, and capabilities, including over 700 tasks and 325,800 instances. The evaluation results that involve over 100 existing state-of-the-art MLLMs uncover the capability rankings of generalists, highlighting the challenges in reaching genuine AI. We expect this project to pave the way for future research on next-generation multimodal foundation models, providing a robust infrastructure to accelerate the realization of AGI. Project Page: https://generalist.top/, Leaderboard: https://generalist.top/leaderboard/, Benchmark: https://huggingface.co/General-Level/.

Nowadays, vision-based computing tasks play an important role in various real-world applications. However, many vision computing tasks, e.g., semantic segmentation, are usually computationally expensive, posing a challenge to the computing systems that are resource-constrained but require fast response speed. Therefore, it is valuable to develop accurate and real-time vision processing models that only require limited computational resources. To this end, we propose the spatial-detail guided context propagation network (SGCPNet) for achieving real-time semantic segmentation. In SGCPNet, we propose the strategy of spatial-detail guided context propagation. It uses the spatial details of shallow layers to guide the propagation of the low-resolution global contexts, in which the lost spatial information can be effectively reconstructed. In this way, the need for maintaining high-resolution features along the network is freed, therefore largely improving the model efficiency. On the other hand, due to the effective reconstruction of spatial details, the segmentation accuracy can be still preserved. In the experiments, we validate the effectiveness and efficiency of the proposed SGCPNet model. On the Cityscapes dataset, for example, our SGCPNet achieves 69.5% mIoU segmentation accuracy, while its speed reaches 178.5 FPS on 768 1536 images on a GeForce GTX 1080 Ti GPU card. In addition, SGCPNet is very lightweight and only contains 0.61 M parameters. The code will be released at https://github.com/zhouyuan888888/SGCPNet.

It is often the case that data are with multiple views in real-world applications. Fully exploring the information of each view is significant for making data more representative. However, due to various limitations and failures in data collection and pre-processing, it is inevitable for real data to suffer from view missing and data scarcity. The coexistence of these two issues makes it more challenging to achieve the pattern classification task. Currently, to our best knowledge, few appropriate methods can well-handle these two issues simultaneously. Aiming to draw more attention from the community to this challenge, we propose a new task in this paper, called few-shot partial multi-view learning, which focuses on overcoming the negative impact of the view-missing issue in the low-data regime. The challenges of this task are twofold: (i) it is difficult to overcome the impact of data scarcity under the interference of missing views; (ii) the limited number of data exacerbates information scarcity, thus making it harder to address the view-missing issue in turn. To address these challenges, we propose a new unified Gaussian dense-anchoring method. The unified dense anchors are learned for the limited partial multi-view data, thereby anchoring them into a unified dense representation space where the influence of data scarcity and view missing can be alleviated. We conduct extensive experiments to evaluate our method. The results on Cub-googlenet-doc2vec, Handwritten, Caltech102, Scene15, Animal, ORL, tieredImagenet, and Birds-200-2011 datasets validate its effectiveness. The codes will be released at https://github.com/zhouyuan888888/UGDA.

Metric-based few-shot learning categorizes unseen query instances by measuring their distance to the categories appearing in the given support set. To facilitate distance measurement, prototypes are used to approximate the representations of categories. However, we find prototypical representations are generally not discriminative enough to represent the discrepancy of inter-categorical distribution of queries, thereby limiting the classification accuracy. To overcome this issue, we propose a new Progressive Hierarchical-Refinement (PHR) method, which effectively refines the discrimination of prototypes by conducting the Progressive Discrimination Maximization strategy based on the hierarchical feature representations. Specifically, we first encode supports and queries into the representation space of spatial level, global level, and semantic level. Then, the refining coefficients are constructed by exploring the metric information contained in these hierarchical embedding spaces simultaneously. Under the guidance of the refining coefficients, the meta-refining loss progressively maximizes the discrimination degree of inter-categorical prototypical representations. In addition, the refining vectors are adopted to further enhance the representations of prototypes. In this way, the metric-based classification can be more accurate. Our PHR method shows the competitive performance on the miniImagenet, CIFAR-FS, FC100, and CUB datasets. Moreover, PHR presents good compatibility. It can be incorporated with other few-shot learning models, making them more accurate.