Cycle consistency has long been exploited as a powerful prior for jointly optimizing maps within a collection of shapes. In this paper, we investigate its utility in the approaches of Deep Functional Maps, which are considered state-of-the-art in non-rigid shape matching. We first justify that under certain conditions, the learned maps, when represented in the spectral domain, are already cycle consistent. Furthermore, we identify the discrepancy that spectrally consistent maps are not necessarily spatially, or point-wise, consistent. In light of this, we present a novel design of unsupervised Deep Functional Maps, which effectively enforces the harmony of learned maps under the spectral and the point-wise representation. By taking advantage of cycle consistency, our framework produces state-of-the-art results in mapping shapes even under significant distortions. Beyond that, by independently estimating maps in both spectral and spatial domains, our method naturally alleviates over-fitting in network training, yielding superior generalization performance and accuracy within an array of challenging tests for both near-isometric and non-isometric datasets.
论文检索
输入标题、作者或关键词，从 2,156 篇学术成果中精准定位
In this paper, we define and study a new Cloth2Body problem which has a goal of generating 3d human body meshes from a 2D clothing image. Unlike the existing human mesh recovery problem, Cloth2Body needs to address new and emerging challenges raised by the partial observation of the input and the high diversity of the output. Indeed, there are three specific challenges. First, how to locate and pose human bodies into the clothes. Second, how to effectively estimate body shapes out of various clothing types. Finally, how to generate diverse and plausible results from a 2D clothing image. To this end, we propose an end-to-end framework that can accurately estimate 3D body mesh parameterized by pose and shape from a 2D clothing image. Along this line, we first utilize Kinematics-aware Pose Estimation to estimate body pose parameters. 3D skeleton is employed as a proxy followed by an inverse kinematics module to boost the estimation accuracy. We additionally design an adaptive depth trick to align the re-projected 3D mesh better with 2D clothing image by disentangling the effects of object size and camera extrinsic. Next, we propose Physics-informed Shape Estimation to estimate body shape parameters. 3D shape parameters are predicted based on partial body measurements estimated from RGB image, which not only improves pixel-wise human-cloth alignment, but also enables flexible user editing. Finally, we design Evolution based pose generation method , a skeleton transplanting method inspired by genetic algorithms to generate diverse reasonable poses during inference. As shown by experimental results on both synthetic and real-world data, the proposed framework achieves state-of-the-art performance and can effectively recover natural and diverse 3D body meshes from 2D images that align well with clothing.
Learning a Room with the Occ-SDF Hybrid: Signed Distance Function Mingled with Occupancy Aids Scene Representation
PDF ↗Implicit neural rendering, using signed distance function (SDF) representation with geometric priors like depth or surface normal, has made impressive strides in the surface reconstruction of large-scale scenes. However, applying this method to reconstruct a room-level scene from images may miss structures in low-intensity areas and/or small, thin objects. We have conducted experiments on three datasets to identify limitations of the original color rendering loss and priors-embedded SDF scene representation.Our findings show that the color rendering loss creates an optimization bias against low-intensity areas, resulting in gradient vanishing and leaving these areas unoptimized. To address this issue, we propose a feature-based color rendering loss that utilizes non-zero feature values to bring back optimization signals. Additionally, the SDF representation can be influenced by objects along a ray path, disrupting the monotonic change of SDF values when a single object is present. Accordingly, we explore using the occupancy representation, which encodes each point separately and is unaffected by objects along a querying ray. Our experimental results demonstrate that the joint forces of the feature-based rendering loss and Occ-SDF hybrid representation scheme can provide high-quality reconstruction results, especially in challenging room-level scenarios. The code is available at https://github.com/shawLyu/Occ-SDF_Hybrid.
Domain adaptive detection aims to improve the generality of a detector, learned from the labeled source domain, on the unlabeled target domain. In this work, drawing inspiration from the concept of stability from the control theory that a robust system requires to remain consistent both externally and internally regardless of disturbances, we propose a novel framework that achieves unsupervised domain adaptive detection through stability analysis. In specific, we treat discrepancies between images and regions from different domains as disturbances, and introduce a novel simple but effective Network Stability Analysis (NSA) framework that considers various disturbances for domain adaptation. Particularly, we explore three types of perturbations including heavy and light image-level disturbances and instance-level disturbance. For each type, NSA performs external consistency analysis on the outputs from raw and perturbed images and/or internal consistency analysis on their features, using teacher-student models. By integrating NSA into Faster R-CNN, we immediately achieve state-of-the-art results. In particular, we set a new record of 52.7% mAP on Cityscapes-to-FoggyCityscapes, showing the potential of NSA for domain adaptive detection. It is worth noticing, our NSA is designed for general purpose, and thus applicable to one-stage detection model (e.g., FCOS) besides the adopted one, as shown by experiments. Code is released at https://github.com/tiankongzhang/NSA.
Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models
PDF ↗We propose a 3D generation pipeline that uses diffusion models to generate realistic human digital avatars. Due to the wide variety of human identities, poses, and stochastic details, the generation of 3D human meshes has been a challenging problem. To address this, we decompose the problem into 2D normal map generation and normal map-based 3D reconstruction. Specifically, we first simultaneously generate realistic normal maps for the front and backside of a clothed human, dubbed dual normal maps, using a pose-conditional diffusion model. For 3D reconstruction, we "carve" the prior SMPL-X mesh to a detailed 3D mesh according to the normal maps through mesh optimization. To further enhance the high-frequency details, we present a diffusion resampling scheme on both body and facial regions, thus encouraging the generation of realistic digital avatars. We also seamlessly incorporate a recent text-to-image diffusion model to support text-based human identity control. Our method, namely, Chupa, is capable of generating realistic 3D clothed humans with better perceptual quality and identity variety.
LEA2: A Lightweight Ensemble Adversarial Attack via Non-overlapping Vulnerable Frequency Regions
PDF ↗Recent work shows that well-designed adversarial examples can fool deep neural networks (DNNs). Due to their transferability, adversarial examples can also attack target models without extra information, called black-box attacks. However, most existing ensemble attacks depend on numerous substitute models to cover the vulnerable subspace of a target model. In this work, we find three types of models with non-overlapping vulnerable frequency regions, which can cover a large enough vulnerable subspace. Based on this finding, we propose a lightweight ensemble adversarial attack named LEA2, integrated by standard, weakly robust, and robust models. Moreover, we analyze Gaussian noise from the perspective of frequency and find that Gaussian noise is located in the vulnerable frequency regions of standard models. Therefore, we substitute standard models with Gaussian noise to ensure the use of high-frequency vulnerable regions while reducing attack time consumption. Experiments on several image datasets indicate that LEA^2 achieves better transferability under different defended models compared with extensive baselines and state-of-the-art attacks.
Large Pre-trained Transformers exhibit an intriguing capacity for in-context learning. Without gradient updates, these models can rapidly construct new predictors from demonstrations presented in the inputs. Recent works promote this ability in the vision-language domain by incorporating visual information into large language models that can already make in-context predictions. However, these methods could inherit issues in the language domain, such as template sensitivity and hallucination. Also, the scale of these language models raises a significant demand for computations, making learning and operating these models resource-intensive. To this end, we raise a question: "How can we enable in-context learning without relying on the intrinsic in-context ability of large language models?". To answer it, we propose a succinct and general framework, Self-supervised IN-Context learning (SINC), that introduces a meta-model to learn on self-supervised prompts consisting of tailored demonstrations. The learned models can be transferred to downstream tasks for making in-context predictions on-the-fly. Extensive experiments show that SINC outperforms gradient-based methods in various vision-language tasks under few-shot settings. Furthermore, the designs of SINC help us investigate the benefits of in-context learning across different tasks, and the analysis further reveals the essential components for the emergence of in-context learning in the vision-language domain.
Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation
PDF ↗Talking head video generation aims to animate a human face in a still image with dynamic poses and expressions using motion information derived from a target-driving video, while maintaining the person's identity in the source image. However, dramatic and complex motions in the driving video cause ambiguous generation, because the still source image cannot provide sufficient appearance information for occluded regions or delicate expression variations, which produces severe artifacts and significantly degrades the generation quality. To tackle this problem, we propose to learn a global facial representation space, and design a novel implicit identity representation conditioned memory compensation network, coined as MCNet, for high-fidelity talking head generation. Specifically, we devise a network module to learn a unified spatial facial meta-memory bank from all training samples, which can provide rich facial structure and appearance priors to compensate warped source facial features for the generation. Furthermore, we propose an effective query mechanism based on implicit identity representations learned from the discrete keypoints of the source image. It can greatly facilitate the retrieval of more correlated information from the memory bank for the compensation. Extensive experiments demonstrate that MCNet can learn representative and complementary facial memory, and can clearly outperform previous state-of-the-art talking head generation methods on VoxCeleb1 and CelebV datasets.
With the success of Vision Transformers (ViTs) in computer vision tasks, recent arts try to optimize the performance and complexity of ViTs to enable efficient deployment on mobile devices. Multiple approaches are proposed to accelerate attention mechanism, improve inefficient designs, or incorporate mobile-friendly lightweight convolutions to form hybrid architectures. However, ViT and its variants still have higher latency or considerably more parameters than lightweight CNNs, even true for the years-old MobileNet. In practice, latency and size are both crucial for efficient deployment on resource-constraint hardware. In this work, we investigate a central question, can transformer models run as fast as MobileNet and maintain a similar size? We revisit the design choices of ViTs and propose a novel supernet with low latency and high parameter efficiency. We further introduce a novel fine-grained joint search strategy for transformer models that can find efficient architectures by optimizing latency and number of parameters simultaneously. The proposed models, EfficientFormerV2, achieve 3.5% higher top-1 accuracy than MobileNetV2 on ImageNet-1K with similar latency and parameters. This work demonstrate that properly designed and optimized vision transformers can achieve high performance even with MobileNet-level size and speed.
Synthesizing expression is essential to create realistic talking faces. Previous works consider expressions and mouth shapes as a whole and predict them solely from audio inputs. However, the limited information contained in audio, such as phonemes and coarse emotion embedding, may not be suitable as the source of elaborate expressions. Besides, since expressions are tightly coupled to lip motions, generating expression from other sources is tricky and always neglects expression performed on mouth region, leading to inconsistency between them. To tackle the issues, this paper proposes Emotional Motion Memory Net (EMMN) that synthesizes expression overall on the talking face via emotion embedding and lip motion instead of the sole audio. Specifically, we extract emotion embedding from audio and design Motion Reconstruction module to decompose ground truth videos into mouth features and expression features before training, where the latter encode all facial factors about expression. During training, the emotion embedding and mouth features are used as keys, and the corresponding expression features are used as values to create key-value pairs stored in the proposed Motion Memory Net. Hence, once the audio-relevant mouth features and emotion embedding are individually predicted from audio at inference time, we treat them as a query to retrieve the best-matching expression features, performing expression overall on the face and thus avoiding inconsistent results. Extensive experiments demonstrate that our method can generate high-quality talking face videos with accurate lip movements and vivid expressions on unseen subjects.
LiDAR-Camera fusion-based 3D detection is a critical task for automatic driving. In recent years, many LiDAR-Camera fusion approaches sprung up and gained promising performances compared with single-modal detectors, but always lack carefully designed and effective supervision for the fusion process. In this paper, we propose a novel training strategy called SupFusion, which provides an auxiliary feature level supervision for effective LiDAR-Camera fusion and significantly boosts detection performance. Our strategy involves a data enhancement method named Polar Sampling, which densifies sparse objects and trains an assistant model to generate high-quality features as the supervision. These features are then used to train the LiDAR-Camera fusion model, where the fusion feature is optimized to simulate the generated high-quality features. Furthermore, we propose a simple yet effective deep fusion module, which contiguously gains superior performance compared with previous fusion methods with SupFusion strategy. In such a manner, our proposal shares the following advantages. Firstly, SupFusion introduces auxiliary feature-level supervision which could boost LiDAR-Camera detection performance without introducing extra inference costs. Secondly, the proposed deep fusion could continuously improve the detector's abilities. Our proposed SupFusion and deep fusion module is plug-and-play, we make extensive experiments to demonstrate its effectiveness. Specifically, we gain around 2% 3D mAP improvements on KITTI benchmark based on multiple LiDAR-Camera 3D detectors. Our code is available at https://github.com/IranQin/SupFusion.
Deep neural networks are valuable assets considering their commercial benefits and huge demands for costly annotation and computation resources. To protect the copyright of DNNs, backdoor-based ownership verification becomes popular recently, in which the model owner can watermark the model by embedding a specific backdoor behavior before releasing it. The defenders (usually the model owners) can identify whether a suspicious third-party model is "stolen" from them based on the presence of the behavior. Unfortunately, these watermarks are proven to be vulnerable to removal attacks even like fine-tuning. To further explore this vulnerability, we investigate the parametric space and find there exist many watermark-removed models in the vicinity of the watermarked one, which may be easily used by removal attacks. Inspired by this finding, we propose a minimax formulation to find these watermark-removed models and recover their watermark behavior. Extensive experiments demonstrate that our method improves the robustness of the model watermarking against parametric changes and numerous watermark-removal attacks. The codes for reproducing our main experiments are available at https://github.com/GuanhaoGan/robust-model-watermarking.
The ability to perceive and understand 3D scenes is crucial for many applications in computer vision and robotics. Inverse graphics is an appealing approach to 3D scene understanding that aims to infer the 3D scene structure from 2D images. In this paper, we introduce probabilistic modeling to the inverse graphics framework to quantify uncertainty and achieve robustness in 6D pose estimation tasks. Specifically, we propose 3D Neural Embedding Likelihood (3DNEL) as a unified probabilistic model over RGB-D images, and develop efficient inference procedures on 3D scene descriptions. 3DNEL effectively combines learned neural embeddings from RGB with depth information to improve robustness in sim-to-real 6D object pose estimation from RGB-D images. Performance on the YCB-Video dataset is on par with state-of-the-art yet is much more robust in challenging regimes. In contrast to discriminative approaches, 3DNEL's probabilistic generative formulation jointly models multiple objects in a scene, quantifies uncertainty in a principled way, and handles object pose tracking under heavy occlusion. Finally, 3DNEL provides a principled framework for incorporating prior knowledge about the scene and objects, which allows natural extension to additional tasks like camera pose tracking from video.
In this paper, we present TMR, a simple yet effective approach for text to 3D human motion retrieval. While previous work has only treated retrieval as a proxy evaluation metric, we tackle it as a standalone task. Our method extends the state-of-the-art text-to-motion synthesis model TEMOS, and incorporates a contrastive loss to better structure the cross-modal latent space. We show that maintaining the motion generation loss, along with the contrastive training, is crucial to obtain good performance. We introduce a benchmark for evaluation and provide an in-depth analysis by reporting results on several protocols. Our extensive experiments on the KIT-ML and HumanML3D datasets show that TMR outperforms the prior work by a significant margin, for example reducing the median rank from 54 to 19. Finally, we showcase the potential of our approach on moment retrieval. Our code and models are publicly available at https://mathis.petrovich.fr/tmr.
In many video restoration/translation tasks, image processing operations are naively extended to the video domain by processing each frame independently, disregarding the temporal connection of the video frames. This disregard for the temporal connection often leads to severe temporal inconsistencies. State-Of-The-Art (SOTA) techniques that address these inconsistencies rely on the availability of unprocessed videos to implicitly siphon and utilize consistent video dynamics to restore the temporal consistency of frame-wise processed videos which often jeopardizes the translation effect. We propose a general framework for this task that learns to infer and utilize consistent motion dynamics from inconsistent videos to mitigate the temporal flicker while preserving the perceptual quality for both the temporally neighboring and relatively distant frames without requiring the raw videos at test time. The proposed framework produces SOTA results on two benchmark datasets, DAVIS and videvo.net, processed by numerous image processing applications. The code and the trained models will be open-sourced upon acceptance.
Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration
PDF ↗We propose a novel end-to-end document understanding model called SeRum (SElective Region Understanding Model) for extracting meaningful information from document images, including document analysis, retrieval, and office automation. Unlike state-of-the-art approaches that rely on multi-stage technical schemes and are computationally expensive, SeRum converts document image understanding and recognition tasks into a local decoding process of the vision tokens of interest, using a content-aware token merge module. This mechanism enables the model to pay more attention to regions of interest generated by the query decoder, improving the model's effectiveness and speeding up the decoding speed of the generative scheme. We also designed several pre-training tasks to enhance the understanding and local awareness of the model. Experimental results demonstrate that SeRum achieves state-of-the-art performance on document understanding tasks and competitive results on text spotting tasks. SeRum represents a substantial advancement towards enabling efficient and effective end-to-end document understanding.
Recently, efficient fine-tuning of large-scale pre-trained models has attracted increasing research interests, where linear probing (LP) as a fundamental module is involved in exploiting the final representations for task-dependent classification. However, most of the existing methods focus on how to effectively introduce a few of learnable parameters, and little work pays attention to the commonly used LP module. In this paper, we propose a novel Moment Probing (MP) method to further explore the potential of LP. Distinguished from LP which builds a linear classification head based on the mean of final features (e.g., word tokens for ViT) or classification tokens, our MP performs a linear classifier on feature distribution, which provides a stronger representation ability by exploiting richer statistical information inherent in features. Specifically, we represent feature distribution by its characteristic function, which is efficiently approximated by using first- and second-order moments of features. Furthermore, we propose a multi-head convolutional cross-covariance to compute second-order moments in an efficient and effective manner. By considering that MP could affect feature learning, we introduce a partially shared module to learn two recalibrating parameters (PSRP) for backbones based on MP, namely MP+. Extensive experiments on ten benchmarks using various models show that our MP significantly outperforms LP and is competitive with counterparts at less training cost, while our MP+ achieves state-of-the-art performance.
Despite the fact that transformer-based models have yielded great success in computer vision tasks, they suffer from the challenge of high computational costs that limits their use on resource-constrained devices. One major reason is that vision transformers have redundant calculations since the self-attention operation generates patches with high similarity at a later stage in the network. Hierarchical architectures have been proposed for vision transformers to alleviate this challenge. However, by shrinking the spatial dimensions to half of the originals with downsampling layers, the challenge is actually overcompensated, as too much information is lost. In this paper, we propose FDViT to improve the hierarchical architecture of the vision transformer by using a flexible downsampling layer that is not limited to integer stride to smoothly reduce the sizes of the middle feature maps. Furthermore, a masked auto-encoder architecture is used to facilitate the training of the proposed flexible downsampling layer and produces informative outputs. Experimental results on benchmark datasets demonstrate that the proposed method can reduce computational costs while increasing classification performance and achieving state-of-the-art results. For example, the proposed FDViT-S model achieves a top-1 accuracy of 81.5%, which is 1.7 percent points higher than the ViT-S model and reduces 39% FLOPs.
Current feature matching methods focus on point-level matching, pursuing better representation learning of individual features, but lacking further understanding of the scene. This results in significant performance degradation when handling challenging scenes such as scenes with large viewpoint and illumination changes. To tackle this problem, we propose a novel model named SAM, which applies attentional grouping to guide Scene-Aware feature Matching. SAM handles multi-level features, i.e., image tokens and group tokens, with attention layers, and groups the image tokens with the proposed token grouping module. Our model can be trained by ground-truth matches only and produce reasonable grouping results. With the sense-aware grouping guidance, SAM is not only more accurate and robust but also more interpretable than conventional feature matching models. Sufficient experiments on various applications, including homography estimation, pose estimation, and image matching, demonstrate that our model achieves state-of-the-art performance.
The quad-Bayer patterned image sensor has made significant improvements in spatial resolution over recent years due to advancements in image sensor technology. This has enabled single-shot high-dynamic-range (HDR) imaging using spatially varying multiple exposures. Popular methods for multi-exposure array sensors involve varying the gain of each exposure, but this does not effectively change the photoelectronic energy in each exposure. Consequently, HDR images produced using gain-based exposure variation may suffer from noise and details being saturated. To address this problem, we intend to use time-varying exposures in quad-Bayer patterned sensors. This approach allows long-exposure pixels to receive more photon energy than short- or middle-exposure pixels, resulting in higher-quality HDR images. However, time-varying exposures are not ideal for dynamic scenes and require an additional deghosting method. To tackle this issue, we propose a single-shot HDR demosaicing method that takes time-varying multiple exposures as input and jointly solves both the demosaicing and deghosting problems. Our method uses a feature-extraction module to handle mosaiced multiple exposures and a multiscale transformer module to register spatial displacements of multiple exposures and colors. We also created a dataset of quad-Bayer sensor input with time-varying exposures and trained our network using this dataset. Results demonstrate that our method outperforms baseline HDR reconstruction methods with both synthetic and real datasets. With our method, we can achieve high-quality HDR images in challenging lighting conditions.