Large language models, trained on extensive corpora, successfully unify diverse linguistic tasks within a single generative framework. Inspired by this, recent works like Large Vision Model (LVM) extend this paradigm to vision by organizing tasks into sequential visual sentences, where visual prompts serve as the context to guide outputs. However, such modeling requires task-specific pre-training across modalities and sources, which is costly and limits scalability to unseen tasks. Given that pre-trained video generation models inherently capture temporal sequence dependencies, we explore a more unified and scalable alternative: can a pre-trained video generation model adapt to diverse image and video tasks? To answer this, we propose UniVid, a framework that fine-tunes a video diffusion transformer to handle various vision tasks without task-specific modifications. Tasks are represented as visual sentences, where the context sequence defines both the task and the expected output modality. We evaluate the generalization of UniVid from two perspectives: (1) cross-modal inference with contexts composed of both images and videos, extending beyond LVM’s uni-modal setting; (2) cross-source tasks from natural to annotated data, without multi-source pre-training. Despite being trained solely on natural video data, UniVid generalizes well in both settings. Notably, understanding and generation tasks can easily switch by simply reversing the visual sentence order in this paradigm. These findings highlight the potential of pre-trained video generation models to serve as a scalable and unified foundation for vision modeling. Our code is released at https://github.com/CUC-MIPG/UniVid.

Natural language often struggles to accurately associate positional and attribute information with multiple instances, which limits current text-based visual generation models to simpler compositions featuring only a few dominant instances. To address this limitation, this work enhances diffusion models by introducing regional instance control, where each instance is governed by a bounding box paired with a free-form caption. Previous methods in this area typically rely on implicit position encoding or explicit attention masks to separate regions of interest (ROIs), resulting in either inaccurate coordinate injection or large computational overhead. Inspired by ROI-Align in object detection, we introduce a complementary operation called ROI-Unpool. Together, ROI-Align and ROI- Unpool enable explicit, efficient, and accurate ROI manipulation on high-resolution feature maps for visual generation. Building on ROI-Unpool, we propose ROICtrl, an adapter for pretrained diffusion models that enables precise regional instance control. ROICtrl is compatible with community-finetuned diffusion models, as well as with existing spatial-based add-ons (e.g., ControlNet, T2I- Adapter) and embedding-based add-ons (e.g., IP-Adapter, ED-LoRA), extending their applications to multi-instance generation. Experiments show that ROICtrl achieves superior performance in regional instance control while significantly reducing computational costs.

We present a unified transformer, i.e., Show-o, that unifies multimodal understanding and generation. Unlike fully autoregressive models, Show-o unifies autoregressive and (discrete) diffusion modeling to adaptively handle inputs and outputs of various and mixed modalities. The unified model flexibly supports a wide range of vision-language tasks including visual question-answering, text-to-image generation, text-guided inpainting/extrapolation, and mixed-modality generation. Across various benchmarks, it demonstrates comparable or superior performance to existing individual models with an equivalent or larger number of parameters tailored for understanding or generation. This significantly highlights its potential as a next-generation foundation model.

Vector-Quantized (VQ-based) generative models usually consist of two basic components, i.e., VQ tokenizers and generative transformers. Prior research focuses on improving the reconstruction fidelity of VQ tokenizers but rarely examines how the improvement in reconstruction affects the generation ability of generative transformers. In this paper, we surprisingly find that improving the reconstruction fidelity of VQ tokenizers does not necessarily improve the generation. Instead, learning to compress semantic features within VQ tokenizers significantly improves generative transformers' ability to capture textures and structures. We thus highlight two competing objectives of VQ tokeniz-ers for image synthesis: semantic compression and details preservation. Different from previous work that pri-oritizes better details preservation, we propose Semantic-Quantized GAN (SeQ-GAN) with two learning phases to balance the two objectives. In the first phase, we propose a semantic-enhanced perceptual loss for better semantic compression. In the second phase, we fix the encoder and codebook, but enhance and finetune the decoder to achieve better details preservation. Our proposed SeQ-GAN significantly improves VQ-based generative models for both un-conditional and conditional image generation. Specifically, SeQ-GAN achieves a Fré chet Inception Distance (FID) of 6.25 and Inception Score (IS) of 140.9 on 256×256 Ima-geNet generation, which is a remarkable improvement over VIT-VQGAN (714M), which obtains 11.2 FID and 97.2 IS.

Current diffusion-based video editing primarily focuses on structure-preserved editing by utilizing various dense correspondences to ensure temporal consistency and motion alignment. However, these approaches are often in-effective when the target edit involves a shape change. To embark on video editing with shape change, we explore customized video subject swapping in this work, where we aim to replace the main subject in a source video with a target subject having a distinct identity and potentially different shape. In contrast to previous methods that rely on dense correspondences, we introduce the Video Swap framework that exploits semantic point correspondences, inspired by our observation that only a small number of semantic points are necessary to align the subject's motion trajectory and modify its shape. We also introduce various user-point interactions (e.g., removing points and dragging points) to address various semantic point correspondence. Extensive experiments demonstrate state-of-the-art video subject swapping results across a variety of real-world videos.

Despite recent progress in diffusion-based video editing, existing methods are limited to short-length videos due to the contradiction between long-range consistency and frame-wise editing. Prior attempts to address this challenge by introducing video-2D representations encounter significant difficulties with large motion- and view-change videos, especially in human-centric scenarios. To overcome this, we propose to introduce the dynamic Neural Radiance Fields (NeRF) as the innovative video representation, where the editing can be performed in the 3D spaces and propagated to the entire video via the deformation field. To provide consistent and controllable editing, we propose the image-based video-NeRF editing pipeline with a set of innovative designs, including multi-view multi-pose Score Distillation Sampling (SDS) from both the 2D personalized diffusion prior and 3D diffusion prior, reconstruction losses, text-guided local parts super-resolution, and style transfer. Extensive experiments demonstrate that our method dubbed as DynVideo-E, significantly outperforms SOTA approaches on two challenging datasets by a large margin of 50% ~ 95% for human preference. Code will be released at https://showlab.github.io/DynVideo-E/.

Recent advances in generative AI have significantly enhanced image and video editing, particularly in the context of text prompt control. State-of-the-art approaches predominantly rely on diffusion models to accomplish these tasks. However, the computational demands of diffusion-based methods are substantial, often necessitating large-scale paired datasets for training, and therefore challenging the deployment in real applications. To address these issues, this paper breaks down the text-based video editing task into two stages. First, we leverage an pre-trained text-to-image diffusion model to simultaneously edit few keyframes in an zero-shot way. Second, we introduce an efficient model called MaskINT, which is built on non-autoregressive masked generative transformers and specializes in frame interpolation between the edited keyframes, using the structural guidance from intermediate frames. Experimental results suggest that our MaskINT achieves comparable performance with diffusion-based methodologies, while significantly improve the inference time. This research offers a practical solution for text-based video editing and showcases the potential of non-autoregressive masked generative transformers in this domain.

Recent advancements in generation models have showcased remarkable capabilities in generating fantastic content. However, most of them are trained on proprietary high-quality data, and some models withhold their parameters and only provide accessible application programming interfaces (APIs), limiting their benefits for downstream tasks. To explore the feasibility of training a text-to-image generation model comparable to advanced models using publicly available resources, we introduce EvolveDirector. This framework interacts with advanced models through their public APIs to obtain text-image data pairs to train a base model. Our experiments with extensive data indicate that the model trained on generated data of the advanced model can approximate its generation capability. However, it requires large-scale samples of 10 million or more. This incurs significant expenses in time, computational resources, and especially the costs associated with calling fee-based APIs. To address this problem, we leverage pre-trained large vision-language models (VLMs) to guide the evolution of the base model. VLM continuously evaluates the base model during training and dynamically updates and refines the training dataset by the discrimination, expansion, deletion, and mutation operations. Experimental results show that this paradigm significantly reduces the required data volume. Furthermore, when approaching multiple advanced models, EvolveDirector can select the best samples generated by them to learn powerful and balanced abilities. The final trained model Edgen is demonstrated to outperform these advanced models. The code and model weights are available at https://github.com/showlab/EvolveDirector.

To replicate the success of text-to-image (T2I) generation, recent works employ large-scale video datasets to train a text-to-video (T2V) generator. Despite their promising results, such paradigm is computationally expensive. In this work, we propose a new T2V generation setting—One-Shot Video Tuning, where only one text-video pair is presented. Our model is built on state-of-the-art T2I diffusion models pre-trained on massive image data. We make two key observations: 1) T2I models can generate still images that represent verb terms; 2) extending T2I models to generate multiple images concurrently exhibits surprisingly good content consistency. To further learn continuous motion, we introduce Tune-A-Video, which involves a tailored spatio-temporal attention mechanism and an efficient one-shot tuning strategy. At inference, we employ DDIM inversion to provide structure guidance for sampling. Extensive qualitative and numerical experiments demonstrate the remarkable ability of our method across various applications.

Public large-scale text-to-image diffusion models, such as Stable Diffusion, have gained significant attention from the community. These models can be easily customized for new concepts using low-rank adaptations (LoRAs). However, the utilization of multiple-concept LoRAs to jointly support multiple customized concepts presents a challenge. We refer to this scenario as decentralized multi-concept customization, which involves single-client concept tuning and center-node concept fusion. In this paper, we propose a new framework called Mix-of-Show that addresses the challenges of decentralized multi-concept customization, including concept conflicts resulting from existing single-client LoRA tuning and identity loss during model fusion. Mix-of-Show adopts an embedding-decomposed LoRA (ED-LoRA) for single-client tuning and gradient fusion for the center node to preserve the in-domain essence of single concepts and support theoretically limitless concept fusion. Additionally, we introduce regionally controllable sampling, which extends spatially controllable sampling (e.g., ControlNet and T2I-Adapter) to address attribute binding and missing object problems in multi-concept sampling. Extensive experiments demonstrate that Mix-of-Show is capable of composing multiple customized concepts with high fidelity, including characters, objects, and scenes.

Current deep networks are very data-hungry and benefit from training on large-scale datasets, which are often time-consuming to collect and annotate. By contrast, synthetic data can be generated infinitely using generative models such as DALL-E and diffusion models, with minimal effort and cost. In this paper, we present DatasetDM, a generic dataset generation model that can produce diverse synthetic images and the corresponding high-quality perception annotations (e.g., segmentation masks, and depth). Our method builds upon the pre-trained diffusion model and extends text-guided image synthesis to perception data generation. We show that the rich latent code of the diffusion model can be effectively decoded as accurate perception annotations using a decoder module. Training the decoder only needs less than 1% (around 100 images) of manually labeled images, enabling the generation of an infinitely large annotated dataset. Then these synthetic data can be used for training various perception models on downstream tasks. To showcase the power of the proposed approach, we generate datasets with rich dense pixel-wise labels for a wide range of downstream tasks, including semantic15 segmentation, instance segmentation, and depth estimation. Notably, it achieves 1) state-of-the-art results on semantic segmentation and instance segmentation; 2) significantly more efficient and robust in domain generalization than the real data; 3) state-of-the-art results in zero-shot segmentation setting; and 4) flexibility for efficient application and novel task composition (e.g., image editing)

The high computational cost of neural networks has prevented recent successes in RGB-D salient object detection (SOD) from benefiting real-world applications. Hence, this article introduces a novel network, MobileSal, which focuses on efficient RGB-D SOD using mobile networks for deep feature extraction. However, mobile networks are less powerful in feature representation than cumbersome networks. To this end, we observe that the depth information of color images can strengthen the feature representation related to SOD if leveraged properly. Therefore, we propose an implicit depth restoration (IDR) technique to strengthen the mobile networks' feature representation capability for RGB-D SOD. IDR is only adopted in the training phase and is omitted during testing, so it is computationally free. Besides, we propose compact pyramid refinement (CPR) for efficient multi-level feature aggregation to derive salient objects with clear boundaries. With IDR and CPR incorporated, MobileSal performs favorably against state-of-the-art methods on six challenging RGB-D SOD datasets with much faster speed (450fps for the input size of 320×320) and fewer parameters (6.5M). The code is released at https://mmcheng.net/mobilesal.

Differentiable Architecture Search (DARTS) has attracted extensive attention due to its efficiency in searching for cell structures. DARTS mainly focuses on the operation search and derives the cell topology from the operation weights. However, the operation weights can not indicate the importance of cell topology and result in poor topology rating correctness. To tackle this, we propose to Decouple the Operation and Topology Search (DOTS), which decouples the topology representation from operation weights and makes an explicit topology search. DOTS is achieved by introducing a topology search space that contains combinations of candidate edges. The proposed search space directly reflects the search objective and can be easily extended to support a flexible number of edges in the searched cell. Existing gradient-based NAS methods can be incorporated into DOTS for further improvement by the topology search. Considering that some operations (e.g., Skip-Connection) can affect the topology, we propose a group operation search scheme to preserve topology-related operations for a better topology search. The experiments on CI-FAR10/100 and ImageNet demonstrate that DOTS is an effective solution for differentiable NAS. The code is released at https://github.com/guyuchao/DOTS.

Existing salient object detection (SOD) models usually focus on either backbone feature extractors or saliency heads, ignoring their relations. A powerful backbone could still achieve sub-optimal performance with a weak saliency head and vice versa. Moreover, the balance between model performance and inference latency poses a great challenge to model design, especially when considering different deployment scenarios. Considering all components in an integral neural architecture search (iNAS) space, we propose a flexible device-aware search scheme that only trains the SOD model once and quickly finds high-performance but low-latency models on multiple devices. An evolution search with latency-group sampling (LGS) is proposed to explore the entire latency area of our enlarged search space. Models searched by iNAS achieve similar performance with SOTA methods but reduce the 3.8×, 3.3×, 2.6×, 1.9× latency on Huawei Nova6 SE, Intel Core CPU, the Jetson Nano, and Nvidia Titan Xp. The code is released at https://mmcheng.net/inas/.

Recently, salient object detection (SOD) has witnessed vast progress with the rapid development of convolutional neural networks (CNNs). However, the improvement of SOD accuracy comes with the increase in network depth and width, resulting in large network size and heavy computational overhead. This prevents state-of-the-art SOD methods from being deployed into practical platforms, especially mobile devices. To promote the deployment of real-world SOD applications, we aim at developing a lightweight SOD model in this article. Our observation comes from that the primate visual system processes visual signals hierarchically with different receptive fields and eccentricities in different visual cortex areas. Inspired by this, we propose a hierarchical visual perception (HVP) module to imitate the primate visual cortex for hierarchical perception learning. With the HVP module incorporated, we design a lightweight SOD network, namely, HVPNet. Extensive experiments on popular benchmarks demonstrate that HVPNet achieves highly competitive accuracy compared with state-of-the-art SOD methods while running at 4.3 frames/s CPU speed and 333.2 frames/s GPU speed with only 1.23M parameters.

Spatiotemporal information is essential for video salient object detection (VSOD) due to the highly attractive object motion for human's attention. Previous VSOD methods usually use Long Short-Term Memory (LSTM) or 3D ConvNet (C3D), which can only encode motion information through step-by-step propagation in the temporal domain. Recently, the non-local mechanism is proposed to capture long-range dependencies directly. However, it is not straightforward to apply the non-local mechanism into VSOD, because i) it fails to capture motion cues and tends to learn motion-independent global contexts; ii) its computation and memory costs are prohibitive for video dense prediction tasks such as VSOD. To address the above problems, we design a Constrained Self-Attention (CSA) operation to capture motion cues, based on the prior that objects always move in a continuous trajectory. We group a set of CSA operations in Pyramid structures (PCSA) to capture objects at various scales and speeds. Extensive experimental results demonstrate that our method outperforms previous state-of-the-art methods in both accuracy and speed (110 FPS on a single Titan Xp) on five challenge datasets. Our code is available at https://github.com/guyuchao/PyramidCSA.