CVPR 2025 Papers

Masked autoencoders (MAE) have shown tremendous potential for self-supervised learning (SSL) in vision and beyond. However, point clouds from LiDARs used in automated driving are particularly challenging for MAEs since large areas of the 3D volume are empty. Consequently, existing work suffers from leaking occupancy information into the decoder and has significant computational complexity, thereby limiting the SSL pre-training to only 2D bird's eye view encoders in practice. In this work, we propose the novel neighborhood occupancy MAE (NOMAE) that overcomes the aforementioned challenges by employing masked occupancy reconstruction only in the neighborhood of non-masked voxels. We incorporate voxel masking and occupancy reconstruction at multiple scales with our proposed hierarchical mask generation technique to capture features of objects of different sizes in the point cloud. NOMAEs are extremely flexible and can be directly employed for SSL in existing 3D architectures. We perform extensive evaluations on the nuScenes and Waymo Open datasets for the downstream perception tasks of semantic segmentation and 3D object detection, comparing with both discriminative and generative SSL methods. The results demonstrate that NOMAE sets the new state-of-the-art on multiple benchmarks for multiple point cloud perception tasks.

Existing Weakly Supervised Semantic Segmentation (WSSS) relies on the CNN-based Class Activation Map (CAM) and Transformer-based self-attention map to generate class-specific masks for semantic segmentation. However, CAM and self-attention maps usually cause incomplete segmentation due to classification bias issue. To address this issue, we propose a Multi-Label Prototype Visual Spatial Search (MuP-VSS) method with a spatial query mechanism, which learns a set of learnable class token vectors as queries to search the similarity visual tokens from image patch tokens. Specifically, MuP-VSS consists of two key components: multi-label prototype representation and multi-label prototype optimization. The former designs a global embedding to learn the global tokens from the images, and then proposes a Prototype Embedding Module (PEM) to interact with patch tokens to understand the local semantic information. The latter utilizes the exclusivity and consistency principles of the multi-label prototypes to design three prototype losses to optimize them, which contain cross-class prototype (CCP) contrastive loss, cross-image prototype (CIP) contrastive loss, and patch-to-prototype (P2P) consistency loss. CCP loss models exclusivity of multi-label prototypes learned from a single image to enhance the discriminative properties of each class better. CCP loss learns the consistency of the same class-specific prototypes extracted from multiple images to enhance the semantic consistency. P2P loss is proposed to control the semantic response of the prototype to the image patches. Experimental results on Pascal VOC 2012 and MS COCO show that MuP-VSS significantly outperforms recent methods and achieves state-of-the-art performance.

Federated Semi-Supervised Learning (FSSL) aims to leverage unlabeled data across clients with limited labeled data to train a global model with strong generalization ability. Most FSSL methods rely on consistency regularization with pseudo-labels, converting predictions from local or global models into hard pseudo-labels as supervisory signals. However, we discover that the quality of pseudo-label is largely deteriorated by data heterogeneity, an intrinsic facet of federated learning. In this paper, we study the problem of FSSL in-depth and show that (1) heterogeneity exacerbates pseudo-label mismatches, further degrading model performance and convergence, and (2) local and global models' predictive tendencies diverge as heterogeneity increases. Motivated by these findings, we propose a simple and effective method called Semi-supervised Aggregation for Globally-Enhanced Ensemble (SAGE), that can flexibly correct pseudo-labels based on confidence discrepancies. This strategy effectively mitigates performance degradation caused by incorrect pseudo-labels and enhances consensus between local and global models. Experimental results demonstrate that SAGE outperforms existing FSSL methods in both performance and convergence. Our code is available at \href https://github.com/Jay-Codeman/SAGE https://github.com/Jay-Codeman/SAGE .

Pre-training with random masked inputs has emerged as a novel trend in self-supervised training. However, supervised learning still faces a challenge in adopting masking augmentations, primarily due to unstable training. In this paper, we propose a novel way to involve masking augmentations dubbed Masked Sub-branch (MaskSub). MaskSub consists of the main-branch and sub-branch, the latter being a part of the former. The main-branch undergoes conventional training recipes, while the sub-branch merits intensive masking augmentations, during training. MaskSub tackles the challenge by mitigating adverse effects through a relaxed loss function similar to a self-distillation loss. Our analysis shows that MaskSub improves performance, with the training loss converging faster than in standard training, which suggests our method stabilizes the training process. We further validate MaskSub across diverse training scenarios and models, including DeiT-III training, MAE finetuning, CLIP finetuning, BERT training, and hierarchical architectures (ResNet and Swin Transformer). Our results show that MaskSub consistently achieves impressive performance gains across all the cases. MaskSub provides a practical and effective solution for introducing additional regularization under various training recipes. Code available at https://github.com/naver-ai/augsub

Self-supervised learning has transformed 2D computer vision by enabling models trained on large, unannotated datasets to provide versatile off-the-shelf features that perform similarly to models trained with labels. However, in 3D scene understanding, self-supervised methods are typically only used as a weight initialization step for task-specific fine-tuning, limiting their utility for general-purpose feature extraction. This paper aims to address this shortcoming by proposing a robust evaluation protocol specifically designed to assess the quality of self-supervised features for 3D scene understanding. Our protocol uses multi-resolution feature sampling of hierarchical models to create rich point-level representations that capture the semantic capabilities of the model and, hence, are suitable for evaluation with linear probing and nearest-neighbor methods. Furthermore, we introduce the first self-supervised model that performs similarly to supervised models when only off-the-shelf features are used in a linear probing setup. In particular, our model is trained natively in 3D with a novel self-supervised approach based on a Masked Scene Modeling objective, which reconstructs deep features of masked patches in a bottom-up manner and is specifically tailored to hierarchical 3D models. Our experiments not only demonstrate that our method achieves competitive performance to supervised models, but also surpasses existing self-supervised approaches by a large margin.

One of the main challenges in reliable camera-based 3D pose estimation for walking subjects is to deal with self-occlusions, especially in the case of using low-resolution cameras or at longer distance scenarios. In recent years, millimeter-wave (mmWave) radar has emerged as a promising alternative, offering inherent resilience to the effect of occlusions and distance variations. However, mmWave-based human walking pose estimation (HWPE) is still in the nascent development stages, primarily due to its unique set of practical challenges including the quality of the observed radar signal dependent on the subject's motion direction. This paper introduces the first comprehensive study comparing mmWave radar to camera systems for HWPE, highlighting its utility for distance-agnostic and occlusion-resilient pose estimation. Building upon mmWave's unique advantages, we address its intrinsic directionality issue through a new approach--the synergetic integration of multi-modal, multi-view mmWave signals, achieving robust HWPE against variations both in distance and walking direction. Extensive experiments on a newly curated dataset not only demonstrate the superior potential of mmWave technology over traditional camera-based HWPE systems, but also validate the effectiveness of our approach in overcoming the core limitations of mmWave HWPE.

Text images are unique in their dual nature, encompassing both visual and linguistic information. The visual component encompasses structural and appearance-based features, while the linguistic dimension incorporates contextual and semantic elements. In scenarios with degraded visual quality, linguistic patterns serve as crucial supplements for comprehension, highlighting the necessity of integrating both aspects for robust scene text recognition (STR). Contemporary STR approaches often use language models or semantic reasoning modules to capture linguistic features, typically requiring large-scale annotated datasets. Self-supervised learning, which lacks annotations, presents challenges in disentangling linguistic features related to the global context. Typically, sequence contrastive learning emphasizes the alignment of local features, while masked image modeling (MIM) tends to exploit local structures to reconstruct visual patterns, resulting in limited linguistic knowledge. In this paper, we propose a Linguistics-aware Masked Image Modeling (LMIM) approach, which channels the linguistic information into the decoding process of MIM through a separate branch. Specifically, we design a linguistics alignment module to extract vision-independent features as linguistic guidance using inputs with different visual appearances. As features extend beyond mere visual structures, LMIM must consider the global context to achieve reconstruction. Extensive experiments on various benchmarks quantitatively demonstrate our state-of-the-art performance, and attention visualizations qualitatively show the simultaneous capture of both visual and linguistic information. The code is available at https://github.com/zhangyifei01/LMIM.

Multi-view person association is a fundamental step towards multi-view analysis of human activities. Although the person re-identification features have been proven effective, they become unreliable in challenging scenes where persons share similar appearances. Therefore, cross-view geometric constraints are required for a more robust association. However, most existing approaches are either fully-supervised using ground-truth identity labels or require calibrated camera parameters that are hard to obtain. In this work, we investigate the potential of learning from synchronization, and propose a self-supervised uncalibrated multi-view person association approach, Self-MVA, without using any annotations. Specifically, we propose a self-supervised learning framework, consisting of an encoder-decoder model and a self-supervised pretext task, cross-view image synchronization, which aims to distinguish whether two images from different views are captured at the same time. The model encodes each person's unified geometric and appearance features, and we train it by utilizing synchronization labels for supervision after applying Hungarian matching to bridge the gap between instance-wise and image-wise distances. To further reduce the solution space, we propose two types of self-supervised linear constraints: multi-view re-projection and pairwise edge association. Extensive experiments on three challenging public benchmark datasets (WILDTRACK, MVOR, and SOLDIERS) show that our approach achieves state-of-the-art results, surpassing existing unsupervised and fully-supervised approaches. Code is available at https://github.com/CAMMA-public/Self-MVA.

Traditional semi-supervised learning achieves significant success in closed-world scenarios. To better align with the openness of the real world, researchers propose open-world semi-supervised learning (OWSSL), which enables models to effectively recognize known and unknown classes even without labels for unknown classes. Recently, researchers have attempted to enhance the model performance in recognizing visually similar classes by integrating textual information. However, these attempts do not effectively align images with text, resulting in limited improvements in model performance. In response to this challenge, we propose a novel OWSSL method. By adopting a global-and-local textual prompt learning strategy to enhance image-text alignment effectiveness, and implementing a forward-and-backward strategy to reduce noise in image-text matching for unlabeled samples, we ultimately enhance the model's ability to extract and recognize discriminative features across different classes. Experimental results on multiple fine-grained datasets demonstrate that our method achieves significant performance improvements compared to state-of-the-art methods.

Training a generic 3D face reconstruction model in a self-supervised manner using large-scale, in-the-wild 2D face image datasets enhances robustness to varying lighting conditions and occlusions while allowing the model to capture animatable wrinkle details across diverse facial expressions. However, a generic model often fails to adequately represent the unique characteristics of specific individuals. In this paper, we propose a method to train a generic base model and then transfer it to yield person-specific models by integrating lightweight adapters within the large-parameter ViT-MAE base model. These person-specific models excel at capturing individual facial shapes and detailed features while preserving the robustness and prior knowledge of detail variations from the base model. During training, we introduce a silhouette vertex re-projection loss to address boundary "landmark marching" issues on the 3D face caused by pose variations. Additionally, we employ an innovative teacher-student loss to leverage the inherent strengths of UNet in feature boundary localization for training our detail MAE. Quantitative and qualitative experiments demonstrate that our approach achieves state-of-the-art performance in face alignment, detail accuracy, and richness. The source code is available at https://github.com/danielmao2000/person-specific-animatable-face.

In this paper, we present a new dynamic collaborative network for semi-supervised 3D vessel segmentation, termed DiCo. Conventional mean teacher (MT) methods typically employ a static approach, where the roles of the teacher and student models are fixed. However, due to the complexity of 3D vessel data, the teacher model may not always outperform the student model, leading to cognitive biases that can limit performance. To address this issue, we propose a dynamic collaborative network that allows the two models to dynamically switch their teacher-student roles. Additionally, we introduce a multi-view integration module to capture various perspectives of the inputs, mirroring the way doctors conduct medical analysis. We also incorporate adversarial supervision to constrain the shape of the segmented vessels in unlabeled data. In this process, the 3D volume is projected into 2D views to mitigate the impact of label inconsistencies. Experiments demonstrate that our DiCo method sets new state-of-the-art performance on three 3D vessel segmentation benchmarks. The code repository address is https://github.com/xujiaommcome/DiCo.

The current state-of-the-art methods in domain adaptive object detection (DAOD) use Mean Teacher self-labelling, where a teacher model, directly derived as an exponential moving average of the student model, is used to generate labels on the target domain which are then used to improve both models in a positive loop. This couples learning and generating labels on the target domain, and other recent works also leverage the generated labels to add additional domain alignment losses. We believe this coupling is brittle and excessively constrained: there is no guarantee that a student trained only on source data can generate accurate target domain labels and initiate the positive feedback loop, and much better target domain labels can likely be generated by using a large pretrained network that has been exposed to much more data. Vision foundational models are exactly such models, and they have shown impressive task generalization capabilities even when frozen. We want to leverage these models for DAOD and introduce DINO Teacher, which consists of two components. First, we train a new labeller on source data only using a large frozen DINOv2 backbone and show it generates more accurate labels than Mean Teacher. Next, we align the student's source and target image patch features with those from a DINO encoder, driving source and target representations closer to the generalizable DINO representation. We obtain state-of-the-art performance on multiple DAOD datasets.

Self-supervised learning (SSL) models are vulnerable to backdoor attacks. Existing backdoor attacks that are effective in SSL often involve noticeable triggers, like colored patches or visible noise, which are vulnerable to human inspection. This paper proposes an imperceptible and effective backdoor attack against self-supervised models. We first find that existing imperceptible triggers designed for supervised learning are less effective in compromising self-supervised models. We then identify this ineffectiveness is attributed to the overlap in distributions between the backdoor and augmented samples used in SSL. Building on this insight, we design an attack using optimized triggers disentangled with the augmented transformation in the SSL, while remaining imperceptible to human vision. Experiments on five datasets and six SSL algorithms demonstrate our attack is highly effective and stealthy. It also has strong resistance to existing backdoor defenses. Our code can be found at https://github.com/Zhang-Henry/INACTIVE.

Monocular depth estimation (MDE) with self-supervised training approaches struggles in low-texture areas, where photometric losses may lead to ambiguous depth predictions. To address this, we propose a novel technique that enhances spatial information by applying a distance transform over pre-semantic contours, augmenting discriminative power in low texture regions. Our approach jointly estimates pre-semantic contours, depth and ego-motion. The pre-semantic contours are leveraged to produce new input images, with variance augmented by the distance transform in uniform areas. This approach results in more effective loss functions, enhancing the training process for depth and ego-motion. We demonstrate theoretically that the distance transform is the optimal variance-augmenting technique in this context. Through extensive experiments on KITTI and Cityscapes, our model demonstrates robust performance, surpassing conventional self-supervised methods in MDE.

Self-supervised monocular depth estimation has long been treated as a point-wise prediction problem, where the depth of each pixel is usually estimated independently. However, artifacts are often observed in the estimated depth map, e.g., depth values for points located in the same region may jump dramatically. To address this issue, we propose a novel self-supervised monocular depth estimation framework called GeoDepth, where we explore the intrinsic geometric representation in 3D scenes for producing accurate and continuous depth maps. In particular, we model the complex 3D scene as a collection of planes with varying sizes, where each plane is characterized by a unique set of parameters, namely planar normal (indicating plane orientation) and planar offset (defining the perpendicular distance from the camera center to the plane). Under this modeling, points in the same plane are enforced to share a unique representation and their depth variations related only to pixel coordinates, thus this geometric relationship can be exploited to regularize the depth variations of these points. To this end, we design a structured plane generation module that introduces spatio-temporal geometric cues and the plane uniqueness principle to recover the correct scene plane representation. In addition, we develop a depth discontinuity module to identify depth discontinuity regions and subsequently optimize them. Our experiments on the KITTI and NYUv2 datasets demonstrate that GeoDepth achieves state-of-the-art performance, with additional tests on Make3D and ScanNet validating its generalization capabilities.

We address the problem of generating videos from unposed internet photos. A handful of input images serve as keyframes, and our model interpolates between them to simulate a path moving between the cameras. Given random images, a model's ability to capture underlying geometry, recognize scene identity, and relate frames in terms of camera position and orientation reflects a fundamental understanding of 3D structure and scene layout. However, existing video models such as Luma Dream Machine fail at this task. We design a self-supervised method that takes advantage of the consistency of videos and variability of multiview internet photos to train a scalable, 3D-aware video model without any 3D annotations such as camera parameters. We validate that our method outperforms commercial models in terms of geometric and appearance consistency. We also show our model benefits applications that enable camera control, such as 3D Gaussian Splatting. Our results suggest that we can scale up scene-level 3D learning using only 2D data such as videos and multiview internet photos.

Recorrupted-to-Recorrupted (R2R) has emerged as a methodology for training deep networks for image restoration in a self-supervised manner from noisy measurement data alone, demonstrating equivalence in expectation to the supervised squared loss in the case of Gaussian noise. However, its effectiveness with non-Gaussian noise remains unexplored. In this paper, we propose Generalized R2R (GR2R), extending the R2R framework to handle a broader class of noise distribution as additive noise like log-Rayleigh and address the natural exponential family including Poisson, Gamma and Binomial noise distributions, which play a key role in many applications including low-photon imaging and synthetic aperture radar. We show that the GR2R loss is an unbiased estimator of the supervised loss and that the popular Stein's unbiased risk estimator can be seen as a special case. A series of experiments with Gaussian, Poisson, and Gamma noise validate GR2R's performance, showing its effectiveness compared to other self-supervised methods.

3D Semantic Occupancy Prediction is fundamental for spatial understanding, yet existing approaches face challenges in scalability and generalization due to their reliance on extensive labeled data and computationally intensive voxel-wise representations. In this paper, we introduce GaussTR, a novel Gaussian-based Transformer framework that unifies sparse 3D modeling with foundation model alignment through Gaussian representations to advance 3D spatial understanding. GaussTR predicts sparse sets of Gaussians in a feed-forward manner to represent 3D scenes. By splatting the Gaussians into 2D views and aligning the rendered features with foundation models, GaussTR facilitates self-supervised 3D representation learning and enables open-vocabulary semantic occupancy prediction without requiring explicit annotations. Empirical experiments on the Occ3D-nuScenes dataset demonstrate GaussTR's state-of-the-art zero-shot performance of 12.27 mIoU, along with a 40% reduction in training time. These results highlight the efficacy of GaussTR for scalable and holistic 3D spatial understanding, with promising implications in autonomous driving and embodied agents. The code is available at https://github.com/hustvl/GaussTR.