Abstract:Text-to-video (T2V) generation has recently garnered significant attention thanks to the large multi-modality model Sora. However, T2V generation still faces two important challenges: 1) Lacking a precise open sourced high-quality dataset. The previous popular video datasets, e.g. WebVid-10M and Panda-70M, are either with low quality or too large for most research institutions. Therefore, it is challenging but crucial to collect a precise high-quality text-video pairs for T2V generation. 2) Ignoring to fully utilize textual information. Recent T2V methods have focused on vision transformers, using a simple cross attention module for video generation, which falls short of thoroughly extracting semantic information from text prompt. To address these issues, we introduce OpenVid-1M, a precise high-quality dataset with expressive captions. This open-scenario dataset contains over 1 million text-video pairs, facilitating research on T2V generation. Furthermore, we curate 433K 1080p videos from OpenVid-1M to create OpenVidHD-0.4M, advancing high-definition video generation. Additionally, we propose a novel Multi-modal Video Diffusion Transformer (MVDiT) capable of mining both structure information from visual tokens and semantic information from text tokens. Extensive experiments and ablation studies verify the superiority of OpenVid-1M over previous datasets and the effectiveness of our MVDiT.
Abstract:Person-generic audio-driven face generation is a challenging task in computer vision. Previous methods have achieved remarkable progress in audio-visual synchronization, but there is still a significant gap between current results and practical applications. The challenges are two-fold: 1) Preserving unique individual traits for achieving high-precision lip synchronization. 2) Generating high-quality facial renderings in real-time performance. In this paper, we propose a novel generalized audio-driven framework RealTalk, which consists of an audio-to-expression transformer and a high-fidelity expression-to-face renderer. In the first component, we consider both identity and intra-personal variation features related to speaking lip movements. By incorporating cross-modal attention on the enriched facial priors, we can effectively align lip movements with audio, thus attaining greater precision in expression prediction. In the second component, we design a lightweight facial identity alignment (FIA) module which includes a lip-shape control structure and a face texture reference structure. This novel design allows us to generate fine details in real-time, without depending on sophisticated and inefficient feature alignment modules. Our experimental results, both quantitative and qualitative, on public datasets demonstrate the clear advantages of our method in terms of lip-speech synchronization and generation quality. Furthermore, our method is efficient and requires fewer computational resources, making it well-suited to meet the needs of practical applications.
Abstract:Recent advances in low light image enhancement have been dominated by Retinex-based learning framework, leveraging convolutional neural networks (CNNs) and Transformers. However, the vanilla Retinex theory primarily addresses global illumination degradation and neglects local issues such as noise and blur in dark conditions. Moreover, CNNs and Transformers struggle to capture global degradation due to their limited receptive fields. While state space models (SSMs) have shown promise in the long-sequence modeling, they face challenges in combining local invariants and global context in visual data. In this paper, we introduce MambaLLIE, an implicit Retinex-aware low light enhancer featuring a global-then-local state space design. We first propose a Local-Enhanced State Space Module (LESSM) that incorporates an augmented local bias within a 2D selective scan mechanism, enhancing the original SSMs by preserving local 2D dependency. Additionally, an Implicit Retinex-aware Selective Kernel module (IRSK) dynamically selects features using spatially-varying operations, adapting to varying inputs through an adaptive kernel selection process. Our Global-then-Local State Space Block (GLSSB) integrates LESSM and IRSK with LayerNorm as its core. This design enables MambaLLIE to achieve comprehensive global long-range modeling and flexible local feature aggregation. Extensive experiments demonstrate that MambaLLIE significantly outperforms state-of-the-art CNN and Transformer-based methods. Project Page: https://mamballie.github.io/anon/
Abstract:Camouflaged object detection (COD) aims to segment objects visually embedded in their surroundings, which is a very challenging task due to the high similarity between the objects and the background. To address it, most methods often incorporate additional information (e.g., boundary, texture, and frequency clues) to guide feature learning for better detecting camouflaged objects from the background. Although progress has been made, these methods are basically individually tailored to specific auxiliary cues, thus lacking adaptability and not consistently achieving high segmentation performance. To this end, this paper proposes an adaptive guidance learning network, dubbed \textit{AGLNet}, which is a unified end-to-end learnable model for exploring and adapting different additional cues in CNN models to guide accurate camouflaged feature learning. Specifically, we first design a straightforward additional information generation (AIG) module to learn additional camouflaged object cues, which can be adapted for the exploration of effective camouflaged features. Then we present a hierarchical feature combination (HFC) module to deeply integrate additional cues and image features to guide camouflaged feature learning in a multi-level fusion manner.Followed by a recalibration decoder (RD), different features are further aggregated and refined for accurate object prediction. Extensive experiments on three widely used COD benchmark datasets demonstrate that the proposed method achieves significant performance improvements under different additional cues, and outperforms the recent 20 state-of-the-art methods by a large margin. Our code will be made publicly available at: \textcolor{blue}{{https://github.com/ZNan-Chen/AGLNet}}.
Abstract:Recent advancements in image inpainting, particularly through diffusion modeling, have yielded promising outcomes. However, when tested in scenarios involving the completion of images based on the foreground objects, current methods that aim to inpaint an image in an end-to-end manner encounter challenges such as "over-imagination", inconsistency between foreground and background, and limited diversity. In response, we introduce Anywhere, a pioneering multi-agent framework designed to address these issues. Anywhere utilizes a sophisticated pipeline framework comprising various agents such as Visual Language Model (VLM), Large Language Model (LLM), and image generation models. This framework consists of three principal components: the prompt generation module, the image generation module, and the outcome analyzer. The prompt generation module conducts a semantic analysis of the input foreground image, leveraging VLM to predict relevant language descriptions and LLM to recommend optimal language prompts. In the image generation module, we employ a text-guided canny-to-image generation model to create a template image based on the edge map of the foreground image and language prompts, and an image refiner to produce the outcome by blending the input foreground and the template image. The outcome analyzer employs VLM to evaluate image content rationality, aesthetic score, and foreground-background relevance, triggering prompt and image regeneration as needed. Extensive experiments demonstrate that our Anywhere framework excels in foreground-conditioned image inpainting, mitigating "over-imagination", resolving foreground-background discrepancies, and enhancing diversity. It successfully elevates foreground-conditioned image inpainting to produce more reliable and diverse results.
Abstract:Blind super-resolution methods based on stable diffusion showcase formidable generative capabilities in reconstructing clear high-resolution images with intricate details from low-resolution inputs. However, their practical applicability is often hampered by poor efficiency, stemming from the requirement of thousands or hundreds of sampling steps. Inspired by the efficient text-to-image approach adversarial diffusion distillation (ADD), we design AddSR to address this issue by incorporating the ideas of both distillation and ControlNet. Specifically, we first propose a prediction-based self-refinement strategy to provide high-frequency information in the student model output with marginal additional time cost. Furthermore, we refine the training process by employing HR images, rather than LR images, to regulate the teacher model, providing a more robust constraint for distillation. Second, we introduce a timestep-adapting loss to address the perception-distortion imbalance problem introduced by ADD. Extensive experiments demonstrate our AddSR generates better restoration results, while achieving faster speed than previous SD-based state-of-the-art models (e.g., 7x faster than SeeSR).
Abstract:Facial Appearance Editing (FAE) aims to modify physical attributes, such as pose, expression and lighting, of human facial images while preserving attributes like identity and background, showing great importance in photograph. In spite of the great progress in this area, current researches generally meet three challenges: low generation fidelity, poor attribute preservation, and inefficient inference. To overcome above challenges, this paper presents DiffFAE, a one-stage and highly-efficient diffusion-based framework tailored for high-fidelity FAE. For high-fidelity query attributes transfer, we adopt Space-sensitive Physical Customization (SPC), which ensures the fidelity and generalization ability by utilizing rendering texture derived from 3D Morphable Model (3DMM). In order to preserve source attributes, we introduce the Region-responsive Semantic Composition (RSC). This module is guided to learn decoupled source-regarding features, thereby better preserving the identity and alleviating artifacts from non-facial attributes such as hair, clothes, and background. We further introduce a consistency regularization for our pipeline to enhance editing controllability by leveraging prior knowledge in the attention matrices of diffusion model. Extensive experiments demonstrate the superiority of DiffFAE over existing methods, achieving state-of-the-art performance in facial appearance editing.
Abstract:Pixel2Mesh (P2M) is a classical approach for reconstructing 3D shapes from a single color image through coarse-to-fine mesh deformation. Although P2M is capable of generating plausible global shapes, its Graph Convolution Network (GCN) often produces overly smooth results, causing the loss of fine-grained geometry details. Moreover, P2M generates non-credible features for occluded regions and struggles with the domain gap from synthetic data to real-world images, which is a common challenge for single-view 3D reconstruction methods. To address these challenges, we propose a novel Transformer-boosted architecture, named T-Pixel2Mesh, inspired by the coarse-to-fine approach of P2M. Specifically, we use a global Transformer to control the holistic shape and a local Transformer to progressively refine the local geometry details with graph-based point upsampling. To enhance real-world reconstruction, we present the simple yet effective Linear Scale Search (LSS), which serves as prompt tuning during the input preprocessing. Our experiments on ShapeNet demonstrate state-of-the-art performance, while results on real-world data show the generalization capability.
Abstract:In this paper, we abstract the process of people hearing speech, extracting meaningful cues, and creating various dynamically audio-consistent talking faces, termed Listening and Imagining, into the task of high-fidelity diverse talking faces generation from a single audio. Specifically, it involves two critical challenges: one is to effectively decouple identity, content, and emotion from entangled audio, and the other is to maintain intra-video diversity and inter-video consistency. To tackle the issues, we first dig out the intricate relationships among facial factors and simplify the decoupling process, tailoring a Progressive Audio Disentanglement for accurate facial geometry and semantics learning, where each stage incorporates a customized training module responsible for a specific factor. Secondly, to achieve visually diverse and audio-synchronized animation solely from input audio within a single model, we introduce the Controllable Coherent Frame generation, which involves the flexible integration of three trainable adapters with frozen Latent Diffusion Models (LDMs) to focus on maintaining facial geometry and semantics, as well as texture and temporal coherence between frames. In this way, we inherit high-quality diverse generation from LDMs while significantly improving their controllability at a low training cost. Extensive experiments demonstrate the flexibility and effectiveness of our method in handling this paradigm. The codes will be released at https://github.com/modelscope/facechain.
Abstract:Multi-modal fusion is vital to the success of super-resolution of depth maps. However, commonly used fusion strategies, such as addition and concatenation, fall short of effectively bridging the modal gap. As a result, guided image filtering methods have been introduced to mitigate this issue. Nevertheless, it is observed that their filter kernels usually encounter significant texture interference and edge inaccuracy. To tackle these two challenges, we introduce a Scene Prior Filtering network, SPFNet, which utilizes the priors surface normal and semantic map from large-scale models. Specifically, we design an All-in-one Prior Propagation that computes the similarity between multi-modal scene priors, i.e., RGB, normal, semantic, and depth, to reduce the texture interference. In addition, we present a One-to-one Prior Embedding that continuously embeds each single-modal prior into depth using Mutual Guided Filtering, further alleviating the texture interference while enhancing edges. Our SPFNet has been extensively evaluated on both real and synthetic datasets, achieving state-of-the-art performance.