Self-supervised pre-training of image encoders is omnipresent in the literature, particularly following the introduction of Masked autoencoders (MAE). Current efforts attempt to learn object-centric representations from motion in videos. In particular, SiamMAE recently introduced a Siamese network, training a shared-weight encoder from two frames of a video with a high asymmetric masking ratio (95%). In this work, we propose CropMAE, an alternative approach to the Siamese pre-training introduced by SiamMAE. Our method specifically differs by exclusively considering pairs of cropped images sourced from the same image but cropped differently, deviating from the conventional pairs of frames extracted from a video. CropMAE therefore alleviates the need for video datasets, while maintaining competitive performances and drastically reducing pre-training time. Furthermore, we demonstrate that CropMAE learns similar object-centric representations without explicit motion, showing that current self-supervised learning methods do not learn objects from motion, but rather thanks to the Siamese architecture. Finally, CropMAE achieves the highest masking ratio to date (98.5%), enabling the reconstruction of images using only two visible patches.
论文检索
输入标题、作者或关键词，从 3,199 篇学术成果中精准定位
We present a new approach for generating 3D house wireframes with semantic enrichment using an autoregressive model. Unlike conventional generative models that independently process vertices, edges, and faces, our approach employs a unified wire-based representation for improved coherence in learning 3D wireframe structures. By re-ordering wire sequences based on semantic meanings, we facilitate seamless semantic integration during sequence generation. Our two-phase technique merges a graph-based autoencoder with a transformer-based decoder to learn latent geometric tokens and generate semantic-aware wireframes. Through iterative prediction and decoding during inference, our model produces detailed wireframes that can be easily segmented into distinct components, such as walls, roofs, and rooms, reflecting the semantic essence of the shape. Empirical results on a comprehensive house dataset validate the superior accuracy, novelty, and semantic fidelity of our model compared to existing generative models.
Masked AutoEncoders (MAE) have emerged as a robust self-supervised framework, offering remarkable performance across a wide range of downstream tasks. To increase the difficulty of the pretext task and learn richer visual representations, existing works have focused on replacing standard random masking with more sophisticated strategies, such as adversarial-guided and teacher-guided masking. However, these strategies depend on the input data, commonly requiring additional computations, networks, or losses to generate the mask pattern. This raises the question: Can we enhance MAE performance beyond random masking without relying on input data or incurring additional computational costs? In this work, we introduce a simple yet effective data-independent method, termed ColorMAE, which generates masks by altering white noise with different filters on its spectrum. Drawing inspiration from color noise in image processing, we explore four types of filters to yield mask patterns with different spatial and semantic priors. ColorMAE requires no additional learnable parameters or computational overhead in the network, yet it significantly enhances the learned representations. We provide a comprehensive empirical evaluation, demonstrating our strategy's superiority in various downstream tasks compared to random masking. Notably, we report an improvement of 2.72 in mIoU in semantic segmentation tasks relative to baseline MAE implementations.
With generative models producing high quality images that are indistinguishable from real ones, there is growing concern regarding the malicious usage of AI-generated images. Imperceptible image watermarking is one viable solution towards such concerns. Prior watermarking methods map the image to a latent space for adding the watermark. Moreover, Latent Diffusion Models (LDM) generate the image in the latent space of a pre-trained autoencoder. We argue that this latent space can be used to integrate watermarking into the generation process. To this end, we preset LaWa, an in-generation image watermarking method designed for LDMs. By using coarse-to-fine multi-scale watermark embedding modules, LaWa modifies the latent space of pre-trained autoencoders and achieves high robustness against a wide range of image transformations while preserving perceptual quality of the image. We show that LaWa can also be used as a general image watermarking method. Through extensive experiments, we demonstrate that LaWa outperforms previous works in perceptual quality, robustness against attacks, and computational complexity, while having very low false positive rate. Code is available as supplementary materials.
The generation of large-scale urban layouts has garnered substantial interest across various disciplines. Prior methods have utilized procedural generation requiring manual rule coding or deep learning needing abundant data. However, prior approaches have not considered the context-sensitive nature of urban layout generation. Our approach addresses this gap by leveraging a canonical graph representation for the entire city, which facilitates scalability and captures the multi-layer semantics inherent in urban layouts. We introduce a novel graph-based masked autoencoder (GMAE) for city-scale urban layout generation. The method encodes attributed buildings, city blocks, communities and cities into a unified graph structure, enabling self-supervised masked training for graph autoencoder. Additionally, we employ scheduled iterative sampling for 2.5D layout generation, prioritizing the generation of important city blocks and buildings. Our approach achieves good realism, semantic consistency, and correctness across the heterogeneous urban styles in 330 US cities. Codes and datasets are released at: https://github.com/Arking1995/COHO.
Semantic Bird's Eye View (BEV) maps offer a rich representation with strong occlusion reasoning for various decision making tasks in autonomous driving. However, most BEV mapping approaches employ a fully supervised learning paradigm that relies on large amounts of human-annotated BEV ground truth data. In this work, we address this limitation by proposing the first unsupervised representation learning approach to generate semantic BEV maps from a monocular frontal view (FV) image in a label-efficient manner. Our approach pretrains the network to independently reason about scene geometry and scene semantics using two disjoint neural pathways in an unsupervised manner, and then finetunes it for the task of semantic BEV mapping using only a small fraction of labels in the BEV. We achieve label-free pretraining by exploiting spatial and temporal consistency of FV images to learn scene geometry while relying on a novel temporal masked autoencoder formulation to encode the scene representation. Extensive evaluations on the KITTI-360 and nuScenes datasets demonstrate that our approach performs on par with the existing state-of-the-art approaches while using only 1% of BEV labels and no additional labeled data.
3D generation has witnessed significant advancements, yet efficiently producing high-quality 3D assets from a single image remains challenging. In this paper, we present a triplane autoencoder, which encodes 3D models into a compact triplane latent space to effectively compress both the 3D geometry and texture information. Within the autoencoder framework, we introduce a 3D-aware cross-attention mechanism, which utilizes low-resolution latent representations to query features from a high-resolution 3D feature volume, thereby enhancing the representation capacity of the latent space. Subsequently, we train a diffusion model on this refined latent space. In contrast to solely relying on image embedding for 3D generation, our proposed method advocates for the simultaneous utilization of both image embedding and shape embedding as conditions. Specifically, the shape embedding is estimated via a diffusion prior model conditioned on the image embedding. Through comprehensive experiments, we demonstrate that our method outperforms state-of-the-art algorithms, achieving superior performance while requiring less training data and time. Our approach enables the generation of high-quality 3D assets in merely 7 seconds on a single A100 GPU. More results and visualization can be found on our project page: https://compress3d.github.io/
The scarcity of annotated data in LiDAR point cloud understanding hinders effective representation learning. Consequently, scholars have been actively investigating efficacious self-supervised pre-training paradigms. Nevertheless, temporal information, which is inherent in the LiDAR point cloud sequence, is consistently disregarded. To better utilize this property, we propose an effective pre-training strategy, namely Temporal Masked Auto-Encoders (T-MAE), which takes as input temporally adjacent frames and learns temporal dependency. A SiamWCA backbone, containing a Siamese encoder and a windowed cross-attention (WCA) module, is established for the two-frame input. Considering that the movement of an ego-vehicle alters the view of the same instance, temporal modeling also serves as a robust and natural data augmentation, enhancing the comprehension of target objects. SiamWCA is a powerful architecture but heavily relies on annotated data. Our T-MAE pre-training strategy alleviates its demand on annotated data. Comprehensive experiments demonstrate that T-MAE achieves the best performance on both Waymo and ONCE datasets among competitive self-supervised approaches.
SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders
PDF ↗Existing zero-shot skeleton-based action recognition methods utilize projection networks to learn a shared latent space of skeleton features and semantic embeddings. The inherent imbalance in action recognition datasets, characterized by variable skeleton sequences yet constant class labels, presents significant challenges for alignment. To address the imbalance, we propose SA-DVAE---Semantic Alignment via Disentangled Variational Autoencoders, a method that first adopts feature disentanglement to separate skeleton features into two independent parts---one is semantic-related and another is irrelevant---to better align skeleton and semantic features. We implement this idea via a pair of modality-specific variational autoencoders coupled with a total correction penalty. We conduct experiments on three benchmark datasets: NTU RGB+D, NTU RGB+D 120 and PKU-MMD, and our experimental results show that SA-DAVE produces improved performance over existing methods.
ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders
PDF ↗We propose ViC-MAE, a model that combines both Masked AutoEncoders (MAE) and contrastive learning. ViC-MAE is trained using a global feature obtained by pooling the local representations learned under an MAE reconstruction loss and leveraging this representation under a contrastive objective across images and video frames. We show that visual representations learned under ViC-MAE generalize well to video and image classification tasks. Particularly, ViC-MAE obtains state-of-the-art transfer learning performance from video to images on Imagenet-1k compared to the recently proposed OmniMAE by achieving a top-1 accuracy of 86% (+1.3% absolute improvement) when trained on the same data and 87.1% (+2.4% absolute improvement) when training on extra data. At the same time, ViC-MAE outperforms most other methods on video benchmarks by obtaining 75.9% top-1 accuracy on the challenging Something something-v2 video benchmark. When training on videos and images from diverse datasets, our method maintains a balanced transfer-learning performance between video and image classification benchmarks, coming only as a close second to the best-supervised method. Source code and model checkpoints will be released with this paper.
Self-supervised learning is increasingly applied to Earth observation problems that leverage satellite and other remotely sensed data. Within satellite imagery, metadata such as time and location often hold significant semantic information that improves scene understanding. In this paper, we introduce Satellite Metadata-Image Pretraining (SatMIP), a new approach for harnessing metadata in the pretraining phase through a flexible and unified multimodal learning objective. SatMIP represents metadata as textual captions and aligns images with metadata in a shared embedding space by solving a metadata-image contrastive task. Our model learns a non-trivial image representation that can effectively handle recognition tasks. We further enhance this model by combining image self-supervision and metadata supervision, introducing SatMIPS. As a result, SatMIPS improves over its image-image pretraining baseline, SimCLR, and accelerates convergence. Comparison against four recent contrastive and masked autoencoding-based methods for remote sensing also highlight the efficacy of our approach. Furthermore, we find that metadata supervision yields better scalability to larger backbones, and more robust hierarchical pretraining.
Panoptic and instance segmentation networks are often trained with specialized object detection modules, complex loss functions, and ad-hoc post-processing steps to handle the permutation-invariance of the instance masks. This work builds upon Stable Diffusion and proposes a latent diffusion approach for panoptic segmentation, resulting in a simple architecture which omits these complexities. Our training process consists of two steps: (1) training a shallow autoencoder to project the segmentation masks to latent space; (2) training a diffusion model to allow image-conditioned sampling in latent space. The use of a generative model unlocks the exploration of mask completion or inpainting, which has applications in interactive segmentation. The experimental validation on COCO and ADE20k yields strong results for segmentation tasks. Finally, we demonstrate the approach's adaptability to a multi-task setting by introducing learnable task embeddings.
The unsupervised task of Joint Alignment (JA) of images is complicated by several hurdles such as high complexity, geometric distortions, and convergence to poor local optima or (due to undesired trivial solutions) even poor global optima. While it was recently shown that Vision Transformers (ViT) features are useful for, among other things, JA, it is important to understand that, by themselves, these features do not completely eliminate the aforementioned issues. Thus, even with ViT features, researchers opt to tackle JA using both 1) expensive models and 2) numerous regularization terms. Unfortunately, that approach leads to long training times and hard-to-tune (and dataset-specific) regularization hyperparameters. Our approach is different. We introduce the Spatial Joint Alignment Model (SpaceJAM), a lightweight method that simplifies JA considerably. Specifically, the method consists of a novel loss function, a Lie-algebraic parametrization, an efficient handling of flips, a small autoencoder, and a (recurrent) small Spatial Transformer Net. The entire model has only $\sim$16K trainable parameters. Of note, the regularization-free SpaceJAM obviates the need for explicitly maintaining an atlas during training. Optionally, and after solving the JA, SpaceJAM can generate an atlas in a single forward pass. Evaluated on the SPair-71K and CUB datasets, and compared to existing methods, SpaceJAM achieves better alignment capabilities and does so with orders of magnitude fewer trainable parameters and at least a 10x speedup in training time. Our code will be released upon acceptance.
3D point clouds play a pivotal role in outdoor scene perception, especially in the context of autonomous driving. Recent advancements in 3D LiDAR segmentation often focus intensely on the spatial positioning and distribution of points for accurate segmentation. However, these methods, while robust in variable conditions, encounter challenges due to sole reliance on coordinates and point intensity, leading to poor isometric invariance and suboptimal segmentation. To tackle this challenge, our work introduces Range-Aware Pointwise Distance Distribution (RAPiD) features and the associated RAPiD-Seg architecture. Our RAPiD features exhibit rigid transformation invariance and effectively adapt to variations in point density, with a design focus on capturing the localized geometry of neighboring structures. They utilize inherent LiDAR isotropic radiation and semantic categorization for enhanced local representation and computational efficiency, while incorporating a 4D distance metric that integrates geometric and surface material reflectivity for improved semantic segmentation. To effectively embed high-dimensional RAPiD features, we propose a double-nested autoencoder structure with a novel class-aware embedding objective to encode high-dimensional features into manageable voxel-wise embeddings. Additionally, we propose RAPiD-Seg which incorporates a channel-wise attention fusion and a two-stage training strategy, further optimizing the embedding for enhanced performance and generalization. Our method outperforms contemporary LiDAR segmentation work in terms of mIoU on SemanticKITTI (76.1) and nuScenes (83.6) datasets (leaderboard rankings: 1st on both datasets).
Recent video masked autoencoder (MAE) works have designed improved masking algorithms focused on saliency. These works leverage visual cues such as motion to mask the most salient regions. However, the robustness of visual cues depends on how often input videos match underlying statistical assumptions. On the other hand, natural language description is an information dense representation of video that implicitly captures saliency without requiring modality-specific assumptions, and has not been explored yet for video MAE. To this end, we introduce a novel text-guided masking strategy (TGM) that masks the video regions with highest correspondence to paired captions. Without leveraging any explicit visual cues for saliency, our text-guided masking is competitive with state-of-the-art masking algorithms such as motion-guided masking. To further benefit from the semantics of natural language for masked reconstruction, we next introduce a unified framework for joint MAE and masked video-text contrastive learning. We show that across existing masking algorithms, unifying MAE and masked video-text contrastive learning improves downstream performance compared to pure MAE on a variety of video recognition tasks, especially for linear probe. When our TGM is combined within this unified framework, we achieve the best relative performance on five action recognition and one egocentric datasets, highlighting the complementary nature of natural language captions for masked video modeling.
The field of neural rendering has witnessed significant progress with advancements in generative models and differentiable rendering techniques. Though 2D diffusion has achieved success, a unified 3D diffusion pipeline remains unsettled. This paper introduces a novel framework called LN3Diff to address this gap and enable fast, high-quality, and generic conditional 3D generation. Our approach harnesses a 3D-aware architecture and variational autoencoder (VAE) to encode the input image into a structured, compact, and perceptually equivalent latent space. The latent is decoded by a transformer-based decoder into a high-capacity 3D neural field. Through training a diffusion model on this 3D-aware latent space, our method achieves state-of-the-art performance on ShapeNet for 3D generation and demonstrates superior performance in monocular 3D reconstruction and conditional 3D generation across various datasets. Moreover, it surpasses existing 3D diffusion methods in terms of inference speed, requiring no per-instance optimization. Our proposed LN3Diff presents a significant advancement in 3D generative modeling and holds promise for various applications in 3D vision and graphics tasks.
Domain Generalization (DG), designed to enhance out-of-distribution (OOD) generalization, is all about learning invariance against domain shifts utilizing sufficient supervision signals. Yet, the scarcity of such labeled data has led to the rise of unsupervised domain generalization (UDG) — a more important yet challenging task in that models are trained across diverse domains in an unsupervised manner and eventually tested on unseen domains. UDG is fast gaining attention but is still far from well-studied. To close the research gap, we propose a novel learning framework designed for UDG, termed the Disentangled Masked AutoEncoder (DisMAE), aiming to discover the disentangled representations that faithfully reveal the intrinsic features and superficial variations without access to the class label. At its core is the distillation of domain-invariant semantic features, which cannot be distinguished by domain classifier, while filtering out the domain-specific variations (for example, color schemes and texture patterns) that are unstable and redundant. Notably, DisMAE co-trains the asymmetric dual-branch architecture with semantic and lightweight variation encoders, offering dynamic data manipulation and representation level augmentation capabilities. Extensive experiments on four benchmark datasets (i.e., DomainNet, PACS, VLCS, and Colored MNIST) with both DG and UDG tasks demonstrate that DisMAE can achieve competitive OOD performance compared with the state-of-the-art DG and UDG baselines, which shed light on potential research lines for improving generalization ability with large-scale unlabeled data.
Sounding Video Generation (SVG) is an audio-video joint generation task challenged by high-dimensional signal spaces, distinct data formats, and different patterns of content information. To address these issues, we introduce a novel multi-modal latent diffusion model (MM-LDM) for the SVG task. We first unify the representation of audio and video data by converting them into a single or a couple of images. Then, we introduce a hierarchical multi-modal autoencoder that constructs a low-level perceptual latent space for each modality and a shared high-level semantic feature space. The former space is perceptually equivalent to the raw signal space of each modality but drastically reduces signal dimensions. The latter space serves to bridge the information gap between modalities and provides more insightful cross-modal guidance. Our proposed method achieves new state-of-the-art results with significant quality and efficiency gains. Specifically, our method achieves a comprehensive improvement on all evaluation metrics and a faster training and sampling speed on Landscape and AIST++ datasets. Moreover, we explore its performance on open-domain sounding video generation, long sounding video generation, audio continuation, video continuation, and conditional single-modal generation tasks for a comprehensive evaluation, where our MM-LDM demonstrates exciting adaptability and generalization ability.
Video harmonization aims to address the discrepancy in color and lighting between foreground and background elements within video compositions, thereby enhancing the innate coherence of composite video content. Nevertheless, existing methods struggle to effectively handle video composite tasks with excessively large-scale foregrounds. In this paper, we propose Video Harmonization Masked Autoencoders (VHMAE), a simple yet powerful end-to-end video harmonization method designed to tackle this challenge once and for all. Unlike other typically MAE-based methods employing random or tube masking strategies, we innovative treat all foregrounds in each frame required for harmonization as prediction regions, which are designated as masked tokens and fed into our network to produce the final refinement video. To this end, the network is optimized to prioritize the harmonization task, proficiently reconstructing the masked region despite the limited background information. Specifically, we introduce the Pattern Alignment Module (PAM) to extract content information from the extensive masked foreground region, aligning the latent semantic features of the masked foreground content with the background context while disregarding the impact of various colors or illumination. Moreover, We propose the Patch Balancing Loss, which effectively mitigates the undesirable grid-like artifacts commonly observed in MAE-based approaches for image generation, thereby ensuring consistency between the predicted foreground and the visible background. Additionally, we introduce a real-composited video harmonization dataset named RCVH, which serves as a valuable benchmark for assessing the efficacy of techniques aimed at video harmonization across different real video sources. Comprehensive experiments demonstrate that our VHMAE outperforms state-of-the-art techniques on both RCVH and HYouTube datasets.
In this work, we focus on exploring explicit fine-grained control of generative facial image editing, all while generating faithful facial appearances and consistent semantic details, which however, is quite challenging and has not been extensively explored, especially under an one-shot scenario. We identify the key challenge as the exploration of disentangled conditional control between high-level semantics and explicit parameters ( e.g., 3DMM) in the generation process, and accordingly propose a novel diffusion-based editing framework, named DisControlFace. Specifically, we leverage a Diffusion Autoencoder (Diff-AE) as the semantic reconstruction backbone. To enable explicit face editing, we construct an Exp-FaceNet that is compatible with Diff-AE to generate spatial-wise explicit control conditions based on estimated 3DMM parameters. Different from current diffusion-based editing methods that train the whole conditional generative model from scratch, we freeze the pre-trained weights of the Diff-AE to maintain its semantically deterministic conditioning capability and accordingly propose a random semantic masking (RSM) strategy to effectively achieve an independent training of Exp-FaceNet. This setting endows the model with disentangled face control meanwhile reducing semantic information shift in editing. Our model can be trained using 2D in-the-wild portrait images without requiring 3D or video data and perform robust editing on any new facial image through a simple one-shot fine-tuning. Comprehensive experiments demonstrate that DisControlFace can generate realistic facial images with better editing accuracy and identity preservation over SOTA methods.