CVPR 2024 Papers

Weakly supervised video anomaly detection (WSVAD) is a challenging task. Generating fine-grained pseudo-labels based on weak-label and then self-training a classifier is currently a promising solution. However since the existing methods use only RGB visual modality and the utilization of category text information is neglected thus limiting the generation of more accurate pseudo-labels and affecting the performance of self-training. Inspired by the manual labeling process based on the event description in this paper we propose a novel pseudo-label generation and self-training framework based on Text Prompt with Normality Guidance (TPWNG) for WSVAD. Our idea is to transfer the rich language-visual knowledge of the contrastive language-image pre-training (CLIP) model for aligning the video event description text and corresponding video frames to generate pseudo-labels. Specifically We first fine-tune the CLIP for domain adaptation by designing two ranking losses and a distributional inconsistency loss. Further we propose a learnable text prompt mechanism with the assist of a normality visual prompt to further improve the matching accuracy of video event description text and video frames. Then we design a pseudo-label generation module based on the normality guidance to infer reliable frame-level pseudo-labels. Finally we introduce a temporal context self-adaptive learning module to learn the temporal dependencies of different video events more flexibly and accurately. Extensive experiments show that our method achieves state-of-the-art performance on two benchmark datasets UCF-Crime and XD-Violence demonstrating the effectiveness of our proposed method.

The increasing prevalence of video clips has sparked growing interest in text-video retrieval. Recent advances focus on establishing a joint embedding space for text and video relying on consistent embedding representations to compute similarity. However the text content in existing datasets is generally short and concise making it hard to fully describe the redundant semantics of a video. Correspondingly a single text embedding may be less expressive to capture the video embedding and empower the retrieval. In this study we propose a new stochastic text modeling method T-MASS i.e. text is modeled as a stochastic embedding to enrich text embedding with a flexible and resilient semantic range yielding a text mass. To be specific we introduce a similarity-aware radius module to adapt the scale of the text mass upon the given text-video pairs. Plus we design and develop a support text regularization to further control the text mass during the training. The inference pipeline is also tailored to fully exploit the text mass for accurate retrieval. Empirical evidence suggests that T-MASS not only effectively attracts relevant text-video pairs while distancing irrelevant ones but also enables the determination of precise text embeddings for relevant pairs. Our experimental results show a substantial improvement of T-MASS over baseline (3% 6.3% by R@1). Also T-MASS achieves state-of-the-art performance on five benchmark datasets including MSRVTT LSMDC DiDeMo VATEX and Charades.

Significant progress has been made in scene text detection models since the rise of deep learning but scene text layout analysis which aims to group detected text instances as paragraphs has not kept pace. Previous works either treated text detection and grouping using separate models or train a model from scratch while using a unified one. All of them have not yet made full use of the already well-trained text detectors and easily obtainable detection datasets. In this paper we present Text Grouping Adapter (TGA) a module that can enable the utilization of various pre-trained text detectors to learn layout analysis allowing us to adopt a well-trained text detector right off the shelf or just fine-tune it efficiently. Designed to be compatible with various text detector architectures TGA takes detected text regions and image features as universal inputs to assemble text instance features. To capture broader contextual information for layout analysis we propose to predict text group masks from text instance features by one-to-many assignment. Our comprehensive experiments demonstrate that even with frozen pre-trained models incorporating our TGA into various pre-trained text detectors and text spotters can achieve superior layout analysis performance simultaneously inheriting generalized text detection ability from pre-training. In the case of full parameter fine-tuning we can further improve layout analysis performance.

To adequately utilize the available image evidence in multi-view video-based avatar modeling we propose TexVocab a novel avatar representation that constructs a texture vocabulary and associates body poses with texture maps for animation. Given multi-view RGB videos our method initially back-projects all the available images in the training videos to the posed SMPL surface producing texture maps in the SMPL UV domain. Then we construct pairs of human poses and texture maps to establish a texture vocabulary for encoding dynamic human appearances under various poses. Unlike the commonly used joint-wise manner we further design a body-part-wise encoding strategy to learn the structural effects of the kinematic chain. Given a driving pose we query the pose feature hierarchically by decomposing the pose vector into several body parts and interpolating the texture features for synthesizing fine-grained human dynamics. Overall our method is able to create animatable human avatars with detailed and dynamic appearances from RGB videos and the experiments show that our method outperforms state-of-the-art approaches.

We introduce TexTile a novel differentiable metric to quantify the degree upon which a texture image can be concatenated with itself without introducing repeating artifacts (i.e. the tileability). Existing methods for tileable texture synthesis focus on general texture quality but lack explicit analysis of the intrinsic repeatability properties of a texture. In contrast our TexTile metric effectively evaluates the tileable properties of a texture opening the door to more informed synthesis and analysis of tileable textures. Under the hood TexTile is formulated as a binary classifier carefully built from a large dataset of textures of different styles semantics regularities and human annotations.Key to our method is a set of architectural modifications to baseline pre-train image classifiers to overcome their shortcomings at measuring tileability along with a custom data augmentation and training regime aimed at increasing robustness and accuracy. We demonstrate that TexTile can be plugged into different state-of-the-art texture synthesis methods including diffusion-based strategies and generate tileable textures while keeping or even improving the overall texture quality. Furthermore we show that TexTile can objectively evaluate any tileable texture synthesis method whereas the current mix of existing metrics produces uncorrelated scores which heavily hinders progress in the field.

This paper focuses on synthesizing high-quality and complete textures directly on the surface of 3D models within 3D space. 2D diffusion-based methods face challenges in generating 2D texture maps due to the infinite possibilities of UV mapping for a given 3D mesh. Utilizing point clouds helps circumvent variations arising from diverse mesh topologies and UV mappings. Nevertheless achieving dense point clouds to accurately represent texture details poses a challenge due to limited computational resources. To address these challenges we propose an efficient octree-based diffusion pipeline called TexOct. Our method starts by sampling a point cloud from the surface of a given 3D model with each point containing texture noise values. We utilize an octree structure to efficiently represent this point cloud. Additionally we introduce an innovative octree-based diffusion model that leverages the denoising capabilities of the Denoising Diffusion Probabilistic Model (DDPM). This model gradually reduces the texture noise on the octree nodes resulting in the restoration of fine texture. Experimental results on ShapeNet demonstrate that TexOct effectively generates high-quality 3D textures in both unconditional and text / image-conditional scenarios.

In many practical applications 3D point cloud analysis requires rotation invariance. In this paper we present a learnable descriptor invariant under 3D rotations and reflections i.e. the O(3) actions utilizing the recently introduced steerable 3D spherical neurons and vector neurons. Specifically we propose an embedding of the 3D spherical neurons into 4D vector neurons which leverages end-to-end training of the model. In our approach we perform TetraTransform---an equivariant embedding of the 3D input into 4D constructed from the steerable neurons---and extract deeper O(3)-equivariant features using vector neurons. This integration of the TetraTransform into the VN-DGCNN framework termed TetraSphere negligibly increases the number of parameters by less than 0.0002%. TetraSphere sets a new state-of-the-art performance classifying randomly rotated real-world object scans of the challenging subsets of ScanObjectNN. Additionally TetraSphere outperforms all equivariant methods on randomly rotated synthetic data: classifying objects from ModelNet40 and segmenting parts of the ShapeNet shapes. Thus our results reveal the practical value of steerable 3D spherical neurons for learning in 3D Euclidean space. The code is available at https://github.com/pavlo-melnyk/tetrasphere.

Zero-Shot Temporal Action Localization (ZS-TAL) seeks to identify and locate actions in untrimmed videos unseen during training. Existing ZS-TAL methods involve fine-tuning a model on a large amount of annotated training data. While effective training-based ZS-TAL approaches assume the availability of labeled data for supervised learning which can be impractical in some applications. Furthermore the training process naturally induces a domain bias into the learned model which may adversely affect the model's generalization ability to arbitrary videos. These considerations prompt us to approach the ZS-TAL problem from a radically novel perspective relaxing the requirement for training data. To this aim we introduce a novel method that performs Test-Time adaptation for Temporal Action Localization (T3AL). In a nutshell T3AL adapts a pre-trained Vision and Language Model (VLM). T3AL operates in three steps. First a video-level pseudo-label of the action category is computed by aggregating information from the entire video. Then action localization is performed adopting a novel procedure inspired by self-supervised learning. Finally frame-level textual descriptions extracted with a state-of-the-art captioning model are employed for refining the action region proposals. We validate the effectiveness of T 3AL by conducting experiments on the THUMOS14 and the ActivityNet-v1.3 datasets. Our results demonstrate that T3AL significantly outperforms zero-shot baselines based on state-of-the-art VLMs confirming the benefit of a test-time adaptation approach.

Out-of-Distribution (OOD) detection aims to address the excessive confidence prediction by neural networks by triggering an alert when the input sample deviates significantly from the training distribution (in-distribution) indicating that the output may not be reliable. Current OOD detection approaches explore all kinds of cues to identify OOD data such as finding irregular patterns in the feature space logit space gradient space or the raw image space. Surprisingly we observe a linear trend between the OOD score produced by current OOD detection algorithms and the network features on several datasets. We conduct a thorough investigation theoretically and empirically to analyze and understand the meaning of such a linear trend in OOD detection. This paper proposes a Robust Test-time Linear method (RTL) to utilize such linear trends like a `free lunch' when we have a batch of data to perform OOD detection. By using a simple linear regression as a test time adaptation we can make a more precise OOD prediction. We further propose an online variant of the proposed method which achieves promising performance and is more practical for real applications. Theoretical analysis is given to prove the effectiveness of our methods. Extensive experiments on several OOD datasets show the efficacy of RTL for OOD detection tasks significantly improving the results of base OOD detectors. Project will be available at https://github.com/kfan21/RTL.

Face Anti-Spoofing (FAS) is pivotal in safeguarding facial recognition systems against presentation attacks. While domain generalization (DG) methods have been developed to enhance FAS performance they predominantly focus on learning domain-invariant features during training which may not guarantee generalizability to unseen data that differs largely from the source distributions. Our insight is that testing data can serve as a valuable resource to enhance the generalizability beyond mere evaluation for DG FAS. In this paper we introduce a novel Test-Time Domain Generalization (TTDG) framework for FAS which leverages the testing data to boost the model's generalizability. Our method consisting of Test-Time Style Projection (TTSP) and Diverse Style Shifts Simulation (DSSS) effectively projects the unseen data to the seen domain space. In particular we first introduce the innovative TTSP to project the styles of the arbitrarily unseen samples of the testing distribution to the known source space of the training distributions. We then design the efficient DSSS to synthesize diverse style shifts via learnable style bases with two specifically designed losses in a hyperspherical feature space. Our method eliminates the need for model updates at the test time and can be seamlessly integrated into not only the CNN but also ViT backbones. Comprehensive experiments on widely used cross-domain FAS benchmarks demonstrate our method's state-of-the-art performance and effectiveness.

It is common to observe performance degradation when transferring models trained on some (source) datasets to target testing data due to a domain gap between them. Existing methods for bridging this gap such as domain adaptation (DA) may require the source data on which the model was trained (often not available) while others i.e. source-free DA require many passes through the testing data. We propose an online test-time adaptation method for depth completion the task of inferring a dense depth map from a single image and associated sparse depth map that closes the performance gap in a single pass. We first present a study on how the domain shift in each data modality affects model performance. Based on our observations that the sparse depth modality exhibits a much smaller covariate shift than the image we design an embedding module trained in the source domain that preserves a mapping from features encoding only sparse depth to those encoding image and sparse depth. During test time sparse depth features are projected using this map as a proxy for source domain features and are used as guidance to train a set of auxiliary parameters (i.e. adaptation layer) to align image and sparse depth features from the target test domain to that of the source domain. We evaluate our method on indoor and outdoor scenarios and show that it improves over baselines by an average of 21.1%. Code available at https://github.com/seobbro/TTA-depth-completion.

We propose a novel approach to the action segmentation task for long untrimmed videos based on solving an optimal transport problem. By encoding a temporal consistency prior into a Gromov-Wasserstein problem we are able to decode a temporally consistent segmentation from a noisy affinity/matching cost matrix between video frames and action classes. Unlike previous approaches our method does not require knowing the action order for a video to attain temporal consistency. Furthermore our resulting (fused) Gromov-Wasserstein problem can be efficiently solved on GPUs using a few iterations of projected mirror descent. We demonstrate the effectiveness of our method in an unsupervised learning setting where our method is used to generate pseudo-labels for self-training. We evaluate our segmentation approach and unsupervised learning pipeline on the Breakfast 50-Salads YouTube Instructions and Desktop Assembly datasets yielding state-of-the-art results for the unsupervised video action segmentation task.

Reconstructing human-object interaction in 3D from a single RGB image is a challenging task and existing data driven methods do not generalize beyond the objects present in the carefully curated 3D interaction datasets. Capturing large-scale real data to learn strong interaction and 3D shape priors is very expensive due to the combinatorial nature of human-object interactions. In this paper we propose ProciGen (Procedural interaction Generation) a method to procedurally generate datasets with both plausible interaction and diverse object variation. We generate 1M+ human-object interaction pairs in 3D and leverage this large-scale data to train our HDM (Hierarchical Diffusion Model) a novel method to reconstruct interacting human and unseen object instances without any templates. Our HDM is an image-conditioned diffusion model that learns both realistic interaction and highly accurate human and object shapes. Experiments show that our HDM trained with ProciGen significantly outperforms prior methods that require template meshes and our dataset allows training methods with strong generalization ability to unseen object instances. Our code and data are released.

While pre-trained large-scale vision models have shown significant promise for semantic correspondence their features often struggle to grasp the geometry and orientation of instances. This paper identifies the importance of being geometry-aware for semantic correspondence and reveals a limitation of the features of current foundation models under simple post-processing. We show that incorporating this information can markedly enhance semantic correspondence performance with simple but effective solutions in both zero-shot and supervised settings. We also construct a new challenging benchmark for semantic correspondence built from an existing animal pose estimation dataset for both pre-training validating models. Our method achieves a PCK@0.10 score of 65.4 (zero-shot) and 85.6 (supervised) on the challenging SPair-71k dataset outperforming the state of the art by 5.5p and 11.0p absolute gains respectively. Our code and datasets are publicly available at: https://telling-left-from-right.github.io.

Teeth localization segmentation and labeling in 2D images have great potential in modern dentistry to enhance dental diagnostics treatment planning and population-based studies on oral health. However general instance segmentation frameworks are incompetent due to 1) the subtle differences between some teeth' shapes (e.g. maxillary first premolar and second premolar) 2) the teeth's position and shape variation across subjects and 3) the presence of abnormalities in the dentition (e.g. caries and edentulism). To address these problems we propose a ViT-based framework named TeethSEG which consists of stacked Multi-Scale Aggregation (MSA) blocks and an Anthropic Prior Knowledge (APK) layer. Specifically to compose the two modules we design 1) a unique permutation-based upscaler to ensure high efficiency while establishing clear segmentation boundaries with 2) multi-head self/cross-gating layers to emphasize particular semantics meanwhile maintaining the divergence between token embeddings. Besides we collect 3) the first open-sourced intraoral image dataset IO150K which comprises over 150k intraoral photos and all photos are annotated by orthodontists using a human-machine hybrid algorithm. Experiments on IO150K demonstrate that our TeethSEG outperforms the state-of-the-art segmentation models on dental image segmentation.

Neural Radiance Fields (NeRF) revolutionize the realm of visual media by providing photorealistic Free-Viewpoint Video (FVV) experiences offering viewers unparalleled immersion and interactivity. However the technology's significant storage requirements and the computational complexity involved in generation and rendering currently limit its broader application. To close this gap this paper presents Temporal Tri-Plane Radiance Fields (TeTriRF) a novel technology that significantly reduces the storage size for Free-Viewpoint Video (FVV) while maintaining low-cost generation and rendering. TeTriRF introduces a hybrid representation with tri-planes and voxel grids to support scaling up to long-duration sequences and scenes with complex motions or rapid changes. We propose a group training scheme tailored to achieving high training efficiency and yielding temporally consistent low-entropy scene representations on feature domain. Leveraging these properties of the representations we introduce a compression pipeline with off-the-shelf video codecs achieving an order of magnitude less storage size compared to the state-of-the-art. Our experiments demonstrate that TeTriRF can achieve competitive quality with a higher compression rate.

Recent progress in the text-driven 3D stylization of a single object has been considerably promoted by CLIP-based methods. However the stylization of multi-object 3D scenes is still impeded in that the image-text pairs used for pre-training CLIP mostly consist of an object. Meanwhile the local details of multiple objects may be susceptible to omission due to the existing supervision manner primarily relying on coarse-grained contrast of image-text pairs. To overcome these challenges we present a novel framework dubbed TeMO to parse multi-object 3D scenes and edit their styles under the contrast supervision at multiple levels. We first propose a Decoupled Graph Attention (DGA) module to distinguishably reinforce the features of 3D surface points. Particularly a cross-modal graph is constructed to align the object points accurately and noun phrases decoupled from the 3D mesh and textual description. Then we develop a Cross-Grained Contrast (CGC) supervision system where a fine-grained loss between the words in the textual description and the randomly rendered images are constructed to complement the coarse-grained loss. Extensive experiments show that our method can synthesize high-quality stylized content and outperform the existing methods over a wide range of multi-object 3D meshes.

Modeling and visualizing relationships between tasks or datasets is an important step towards solving various meta-tasks such as dataset discovery multi-tasking and transfer learning. However many relationships such as containment and transferability are naturally asymmetric and current approaches for representation and visualization (e.g. t-SNE) do not readily support this. We propose Task2Box an approach to represent tasks using box embeddings---axis-aligned hyperrectangles in low dimensional spaces---that can capture asymmetric relationships between them through volumetric overlaps. We show that Task2Box accurately predicts unseen hierarchical relationships between nodes in ImageNet and iNaturalist datasets as well as transferability between tasks in the Taskonomy benchmark. We also show that box embeddings estimated from task representations (e.g. CLIP Task2Vec or attribute based) can be used to predict relationships between unseen tasks more accurately than classifiers trained on the same representations as well as handcrafted asymmetric distances (e.g. KL divergence). This suggests that low-dimensional box embeddings can effectively capture these task relationships and have the added advantage of being interpretable. We use the approach to visualize relationships among publicly available image classification datasets on popular dataset hosting platform called Hugging Face.

Part-aware panoptic segmentation (PPS) requires (a) that each foreground object and background region in an image is segmented and classified and (b) that all parts within foreground objects are segmented classified and linked to their parent object. Existing methods approach PPS by separately conducting object-level and part-level segmentation. However their part-level predictions are not linked to individual parent objects. Therefore their learning objective is not aligned with the PPS task objective which harms the PPS performance. To solve this and make more accurate PPS predictions we propose Task-Aligned Part-aware Panoptic Segmentation (TAPPS). This method uses a set of shared queries to jointly predict (a) object-level segments and (b) the part-level segments within those same objects. As a result TAPPS learns to predict part-level segments that are linked to individual parent objects aligning the learning objective with the task objective and allowing TAPPS to leverage joint object-part representations. With experiments we show that TAPPS considerably outperforms methods that predict objects and parts separately and achieves new state-of-the-art PPS results.