StereoCrafter: Diffusion-based Generation of Long and High-fidelity Stereoscopic 3D from Monocular Videos

This paper presents a novel framework for converting 2D videos to immersive stereoscopic 3D, addressing the growing demand for 3D content in immersive experience. Leveraging foundation models as priors, our approach overcomes the limitations of traditional methods and boosts the performance to ensure the high-fidelity generation required by the display devices. The proposed system consists of two main steps: depth-based video splatting for warping and extracting occlusion mask, and stereo video inpainting. We utilize pre-trained stable video diffusion as the backbone and introduce a fine-tuning protocol for the stereo video inpainting task. To handle input video with varying lengths and resolutions, we explore auto-regressive strategies and tiled processing. Finally, a sophisticated data processing pipeline has been developed to reconstruct a large-scale and high-quality dataset to support our training. Our framework demonstrates significant improvements in 2D-to-3D video conversion, offering a practical solution for creating immersive content for 3D devices like Apple Vision Pro and 3D displays. In summary, this work contributes to the field by presenting an effective method for generating high-quality stereoscopic videos from monocular input, potentially transforming how we experience digital media.

OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion Models

Personalization is an important topic in text-to-image generation, especially the challenging multi-concept personalization. Current multi-concept methods are struggling with identity preservation, occlusion, and the harmony between foreground and background. In this work, we propose OMG, an occlusion-friendly personalized generation framework designed to seamlessly integrate multiple concepts within a single image. We propose a novel two-stage sampling solution. The first stage takes charge of layout generation and visual comprehension information collection for handling occlusions. The second one utilizes the acquired visual comprehension information and the designed noise blending to integrate multiple concepts while considering occlusions. We also observe that the initiation denoising timestep for noise blending is the key to identity preservation and layout. Moreover, our method can be combined with various single-concept models, such as LoRA and InstantID without additional tuning. Especially, LoRA models on civitai.com can be exploited directly. Extensive experiments demonstrate that OMG exhibits superior performance in multi-concept personalization.

Dual Teacher Knowledge Distillation with Domain Alignment for Face Anti-spoofing

Face recognition systems have raised concerns due to their vulnerability to different presentation attacks, and system security has become an increasingly critical concern. Although many face anti-spoofing (FAS) methods perform well in intra-dataset scenarios, their generalization remains a challenge. To address this issue, some methods adopt domain adversarial training (DAT) to extract domain-invariant features. However, the competition between the encoder and the domain discriminator can cause the network to be difficult to train and converge. In this paper, we propose a domain adversarial attack (DAA) method to mitigate the training instability problem by adding perturbations to the input images, which makes them indistinguishable across domains and enables domain alignment. Moreover, since models trained on limited data and types of attacks cannot generalize well to unknown attacks, we propose a dual perceptual and generative knowledge distillation framework for face anti-spoofing that utilizes pre-trained face-related models containing rich face priors. Specifically, we adopt two different face-related models as teachers to transfer knowledge to the target student model. The pre-trained teacher models are not from the task of face anti-spoofing but from perceptual and generative tasks, respectively, which implicitly augment the data. By combining both DAA and dual-teacher knowledge distillation, we develop a dual teacher knowledge distillation with domain alignment framework (DTDA) for face anti-spoofing. The advantage of our proposed method has been verified through extensive ablation studies and comparison with state-of-the-art methods on public datasets across multiple protocols.

Fingerprint Presentation Attack Detection by Channel-wise Feature Denoising

Due to the diversity of attack materials, fingerprint recognition systems (AFRSs) are vulnerable to malicious attacks. It is of great importance to propose effective Fingerprint Presentation Attack Detection (PAD) methods for the safety and reliability of AFRSs. However, current PAD methods often have poor robustness under new attack materials or sensor settings. This paper thus proposes a novel Channel-wise Feature Denoising fingerprint PAD (CFD-PAD) method by considering handling the redundant "noise" information which ignored in previous works. The proposed method learned important features of fingerprint images by weighting the importance of each channel and finding those discriminative channels and "noise" channels. Then, the propagation of "noise" channels is suppressed in the feature map to reduce interference. Specifically, a PA-Adaption loss is designed to constrain the feature distribution so as to make the feature distribution of live fingerprints more aggregate and spoof fingerprints more disperse. Our experimental results evaluated on LivDet 2017 showed that our proposed CFD-PAD can achieve 2.53% ACE and 93.83% True Detection Rate when the False Detection Rate equals to 1.0% (TDR@FDR=1%) and it outperforms the best single model based methods in terms of ACE (2.53% vs. 4.56%) and TDR@FDR=1%(93.83% vs. 73.32\%) significantly, which proves the effectiveness of the proposed method. Although we have achieved a comparable result compared with the state-of-the-art multiple model based method, there still achieves an increase of TDR@FDR=1% from 91.19% to 93.83% by our method. Besides, our model is simpler, lighter and, more efficient and has achieved a 74.76% reduction in time-consuming compared with the state-of-the-art multiple model based method. Code will be publicly available.

Taming Self-Supervised Learning for Presentation Attack Detection: In-Image De-Folding and Out-of-Image De-Mixing

Biometric systems are vulnerable to the Presentation Attacks (PA) performed using various Presentation Attack Instruments (PAIs). Even though there are numerous Presentation Attack Detection (PAD) techniques based on both deep learning and hand-crafted features, the generalization of PAD for unknown PAI is still a challenging problem. The common problem with existing deep learning-based PAD techniques is that they may struggle with local optima, resulting in weak generalization against different PAs. In this work, we propose to use self-supervised learning to find a reasonable initialization against local trap, so as to improve the generalization ability in detecting PAs on the biometric system.The proposed method, denoted as IF-OM, is based on a global-local view coupled with De-Folding and De-Mixing to derive the task-specific representation for PAD.During De-Folding, the proposed technique will learn region-specific features to represent samples in a local pattern by explicitly maximizing cycle consistency. While, De-Mixing drives detectors to obtain the instance-specific features with global information for more comprehensive representation by maximizing topological consistency. Extensive experimental results show that the proposed method can achieve significant improvements in terms of both face and fingerprint PAD in more complicated and hybrid datasets, when compared with the state-of-the-art methods. Specifically, when training in CASIA-FASD and Idiap Replay-Attack, the proposed method can achieve 18.60% Equal Error Rate (EER) in OULU-NPU and MSU-MFSD, exceeding baseline performance by 9.54%. Code will be made publicly available.