Mechanism Design

When we look around and perform complex tasks how we see and selectively process what we see is crucial. However the lack of this visual search mechanism in current multimodal LLMs (MLLMs) hinders their ability to focus on important visual details especially when handling high-resolution and visually crowded images. To address this we introduce V* an LLM-guided visual search mechanism that employs the world knowledge in LLMs for efficient visual querying. When combined with an MLLM this mechanism enhances collaborative reasoning contextual understanding and precise visual grounding. This integration results in a new MLLM meta-architecture named Show sEArch and TelL (SEAL). We further create V*Bench a benchmark specifically designed to evaluate MLLMs in their ability to process high-resolution images and focus on visual details. Our study highlights the necessity of incorporating visual search capabilities into multimodal systems. The code is available at https://github.com/penghao-wu/vstar

Foundation segmentation models while powerful pose a significant risk: they enable users to effortlessly extract any objects from any digital content with a single click potentially leading to copyright infringement or malicious misuse. To mitigate this risk we introduce a new task "Anything Unsegmentable" to grant any image "the right to be unsegmented". The ambitious pursuit of the task is to achieve highly transferable adversarial attack against all prompt-based segmentation models regardless of model parameterizations and prompts. We highlight the non-transferable and heterogeneous nature of prompt-specific adversarial noises. Our approach focuses on disrupting image encoder features to achieve prompt-agnostic attacks. Intriguingly targeted feature attacks exhibit better transferability compared to untargeted ones suggesting the optimal update direction aligns with the image manifold. Based on the observations we design a novel attack named Unsegment Anything by Simulating Deformation (UAD). Our attack optimizes a differentiable deformation function to create a target deformed image which alters structural information while preserving achievable feature distance by adversarial example. Extensive experiments verify the effectiveness of our approach compromising a variety of promptable segmentation models with different architectures and prompt interfaces.

We introduce a co-designed approach for human portrait relighting that combines a physics-guided architecture with a pre-training framework. Drawing on the Cook-Torrance reflectance model we have meticulously configured the architecture design to precisely simulate light-surface interactions. Furthermore to overcome the limitation of scarce high-quality lightstage data we have developed a self-supervised pre-training strategy. This novel combination of accurate physical modeling and expanded training dataset establishes a new benchmark in relighting realism.

Point cloud filtering is a fundamental 3D vision task which aims to remove noise while recovering the underlying clean surfaces. State-of-the-art methods remove noise by moving noisy points along stochastic trajectories to the clean surfaces. These methods often require regularization within the training objective and/or during post-processing to ensure fidelity. In this paper we introduce StraightPCF a new deep learning based method for point cloud filtering. It works by moving noisy points along straight paths thus reducing discretization errors while ensuring faster convergence to the clean surfaces. We model noisy patches as intermediate states between high noise patch variants and their clean counterparts and design the VelocityModule to infer a constant flow velocity from the former to the latter. This constant flow leads to straight filtering trajectories. In addition we introduce a DistanceModule that scales the straight trajectory using an estimated distance scalar to attain convergence near the clean surface. Our network is lightweight and only has 530K parameters being 17% of IterativePFN (a most recent point cloud filtering network). Extensive experiments on both synthetic and real-world data show our method achieves state-of-the-art results. Our method also demonstrates nice distributions of filtered points without the need for regularization. The implementation code can be found at: https://github.com/ddsediri/StraightPCF.

Recently efficient Vision Transformers have shown great performance with low latency on resource-constrained devices. Conventionally they use 4x4 patch embeddings and a 4-stage structure at the macro level while utilizing sophisticated attention with multi-head configuration at the micro level. This paper aims to address computational redundancy at all design levels in a memory-efficient manner. We discover that using larger-stride patchify stem not only reduces memory access costs but also achieves competitive performance by leveraging token representations with reduced spatial redundancy from the early stages. Furthermore our preliminary analyses suggest that attention layers in the early stages can be substituted with convolutions and several attention heads in the latter stages are computationally redundant. To handle this we introduce a single-head attention module that inherently prevents head redundancy and simultaneously boosts accuracy by parallelly combining global and local information. Building upon our solutions we introduce SHViT a Single-Head Vision Transformer that obtains the state-of-the-art speed-accuracy tradeoff. For example on ImageNet-1k our SHViT-S4 is 3.3x 8.1x and 2.4x faster than MobileViTv2x1.0 on GPU CPU and iPhone12 mobile device respectively while being 1.3% more accurate. For object detection and instance segmentation on MS COCO using Mask-RCNN head our model achieves performance comparable to FastViT-SA12 while exhibiting 3.8x and 2.0x lower backbone latency on GPU and mobile device respectively.

We introduce SAOR a novel approach for estimating the 3D shape texture and viewpoint of an articulated object from a single image captured in the wild. Unlike prior approaches that rely on pre-defined category-specific 3D templates or tailored 3D skeletons SAOR learns to articulate shapes from single-view image collections with a skeleton-free part-based model without requiring any 3D object shape priors. To prevent ill-posed solutions we propose a cross-instance consistency loss that exploits disentangled object shape deformation and articulation. This is helped by a new silhouette-based sampling mechanism to enhance viewpoint diversity during training. Our method only requires estimated object silhouettes and relative depth maps from off-the-shelf pre-trained networks during training. At inference time given a single-view image it efficiently outputs an explicit mesh representation. We obtain improved qualitative and quantitative results on challenging quadruped animals compared to relevant existing work.

Advancements in 3D instance segmentation have traditionally been tethered to the availability of annotated datasets limiting their application to a narrow spectrum of object categories. Recent efforts have sought to harness vision-language models like CLIP for open-set semantic reasoning yet these methods struggle to distinguish between objects of the same categories and rely on specific prompts that are not universally applicable. In this paper we introduce SAI3D a novel zero-shot 3D instance segmentation approach that synergistically leverages geometric priors and semantic cues derived from Segment Anything Model (SAM). Our method partitions a 3D scene into geometric primitives which are then progressively merged into 3D instance segmentations that are consistent with the multi-view SAM masks. Moreover we design a hierarchical region-growing algorithm with a dynamic thresholding mechanism which largely improves the robustness of fine-grained 3D scene parsing. Empirical evaluations on ScanNet Matterport3D and the more challenging ScanNet++ datasets demonstrate the superiority of our approach. Notably SAI3D outperforms existing open-vocabulary baselines and even surpasses fully-supervised methods in class-agnostic segmentation on ScanNet++. Our project page is at https://yd-yin.github.io/SAI3D/.

Recent studies have drawn attention to the untapped potential of the "star operation" (element-wise multiplication) in network design. While intuitive explanations abound the foundational rationale behind its application remains largely unexplored. Our study attempts to reveal the star operation's ability of mapping inputs into high-dimensional non-linear feature spaces--akin to kernel tricks--without widening the network. We further introduce StarNet a simple yet powerful prototype demonstrating impressive performance and low latency under compact network structure and efficient budget. Like stars in the sky the star operation appears unremarkable but holds a vast universe of potential. Our work encourages further exploration across tasks with codes available at https://github.com/ma-xu/Rewrite-the-Stars.

Generalizable face anti-spoofing (FAS) approaches have drawn growing attention due to their robustness for diverse presentation attacks in unseen scenarios. Most previous methods always utilize domain generalization (DG) frameworks via directly aligning diverse source samples into a common feature space. However these methods neglect the hierarchical relations in FAS samples which may hinder the generalization ability by direct alignment. To address these issues we propose a novel Hierarchical Prototype-guided Distribution Refinement (HPDR) framework to learn embedding in hyperbolic space which facilitates the hierarchical relation construction. We also collaborate with prototype learning for hierarchical distribution refinement in hyperbolic space. In detail we propose the Hierarchical Prototype Learning to simultaneously guide domain alignment and improve the discriminative ability via constraining the multi-level relations between prototypes and instances in hyperbolic space. Moreover we design a Prototype-oriented Classifier which further considers relations between the sample and prototypes to improve the robustness of the final decision. Extensive experiments and visualizations demonstrate the effectiveness of our method against previous competitors.

In this work we introduce ProMotion a unified prototypical transformer-based framework engineered to model fundamental motion tasks. ProMotion offers a range of compelling attributes that set it apart from current task-specific paradigms. 1. We adopt a prototypical perspective establishing a unified paradigm that harmonizes disparate motion learning approaches. This novel paradigm streamlines the architectural design enabling the simultaneous assimilation of diverse motion information. 2. We capitalize on a dual mechanism involving the feature denoiser and the prototypical learner to decipher the intricacies of motion. This approach effectively circumvents the pitfalls of ambiguity in pixel-wise feature matching significantly bolstering the robustness of motion representation. We demonstrate a profound degree of transferability across distinct motion patterns. This inherent versatility reverberates robustly across a comprehensive spectrum of both 2D and 3D downstream tasks. Empirical results demonstrate that outperforms various well-known specialized architectures achieving 0.54 and 0.054 Abs Rel error on the Sintel and KITTI depth datasets 1.04 and 2.01 average endpoint error on the clean and final pass of Sintel flow benchmark and 4.30 F1-all error on the KITTI flow benchmark. For its efficacy we hope our work can catalyze a paradigm shift in universal models in computer vision.

This paper is not motivated to seek innovation within the attention mechanism. Instead it focuses on overcoming the existing trade-offs between accuracy and efficiency within the context of point cloud processing leveraging the power of scale. Drawing inspiration from recent advances in 3D large-scale representation learning we recognize that model performance is more influenced by scale than by intricate design. Therefore we present Point Transformer V3 (PTv3) which prioritizes simplicity and efficiency over the accuracy of certain mechanisms that are minor to the overall performance after scaling such as replacing the precise neighbor search by KNN with an efficient serialized neighbor mapping of point clouds organized with specific patterns. This principle enables significant scaling expanding the receptive field from 16 to 1024 points while remaining efficient (a 3x increase in processing speed and a 10x improvement in memory efficiency compared with its predecessor PTv2). PTv3 attains state-of-the-art results on over 20 downstream tasks that span both indoor and outdoor scenarios. Further enhanced with multi-dataset joint training PTv3 pushes these results to a higher level.

In this paper we present an end-to-end 3D-building-wireframe reconstruction method to regress edges directly from aerial light-detection-and-ranging (LiDAR) point clouds. Our method named parametric-building-wireframe reconstruction (PBWR) takes aerial LiDAR point clouds and initial edge entities as input and fully uses the self-attention mechanism of transformers to regress edge parameters without any intermediate steps such as corner prediction. We propose an edge non-maximum suppression (E-NMS) module based on edge similarity to remove redundant edges. Additionally a dedicated edge loss function is utilized to guide the PBWR in regressing edges parameters when the simple use of the edge distance loss is not suitable. In our experiments our proposed method demonstrated state-of-the-art results on the Building3D dataset achieving an improvement of approximately 36% in Entry-level dataset edge accuracy and around a 42% improvement in the Tallinn dataset.

State-of-the-art neural implicit surface representations have achieved impressive results in indoor scene reconstruction by incorporating monocular geometric priors as additional supervision. However we have observed that multi-view inconsistency between such priors poses a challenge for high-quality reconstructions. In response we present NC-SDF a neural signed distance field (SDF) 3D reconstruction framework with view-dependent normal compensation (NC). Specifically we integrate view-dependent biases in monocular normal priors into the neural implicit representation of the scene. By adaptively learning and correcting the biases our NC-SDF effectively mitigates the adverse impact of inconsistent supervision enhancing both the global consistency and local details in the reconstructions. To further refine the details we introduce an informative pixel sampling strategy to pay more attention to intricate geometry with higher information content. Additionally we design a hybrid geometry modeling approach to improve the neural implicit representation. Experiments on synthetic and real-world datasets demonstrate that NC-SDF outperforms existing approaches in terms of reconstruction quality.

Recently the emergence of naturalistic adversarial patch (NAP) which possesses a deceptive appearance and various representations underscores the necessity of developing robust detection strategies. However existing approaches fail to differentiate the deep-seated natures in adversarial patches i.e. aggressiveness and naturalness leading to unsatisfactory precision and generalization against NAPs. To tackle this issue we propose NAPGuard to provide strong detection capability against NAPs via the elaborated critical feature modulation framework. For improving precision we propose the aggressive feature aligned learning to enhance the model's capability in capturing accurate aggressive patterns. Considering the challenge of inaccurate model learning caused by deceptive appearance we align the aggressive features by the proposed pattern alignment loss during training. Since the model could learn more accurate aggressive patterns it is able to detect deceptive patches more precisely. To enhance generalization we design the natural feature suppressed inference to universally mitigate the disturbance from different NAPs. Since various representations arise in diverse disturbing forms to hinder generalization we suppress the natural features in a unified approach via the feature shield module. Therefore the models could recognize NAPs within less disturbance and activate the generalized detection ability. Extensive experiments show that our method surpasses state-of-the-art methods by large margins in detecting NAPs (improve 60.24% AP@0.5 on average).

Recent 3D face reconstruction methods have made remarkable advancements yet there remain huge challenges in monocular high-quality facial reflectance reconstruction. Existing methods rely on a large amount of light-stage captured data to learn facial reflectance models. However the lack of subject diversity poses challenges in achieving good generalization and widespread applicability. In this paper we learn the reflectance prior in image space rather than UV space and present a framework named ID2Reflectance. Our framework can directly estimate the reflectance maps of a single image while using limited reflectance data for training. Our key insight is that reflectance data shares facial structures with RGB faces which enables obtaining expressive facial prior from inexpensive RGB data thus reducing the dependency on reflectance data. We first learn a high-quality prior for facial reflectance. Specifically we pretrain multi-domain facial feature codebooks and design a codebook fusion method to align the reflectance and RGB domains. Then we propose an identity-conditioned swapping module that injects facial identity from the target image into the pre-trained auto-encoder to modify the identity of the source reflectance image. Finally we stitch multi-view swapped reflectance images to obtain renderable assets. Extensive experiments demonstrate that our method exhibits excellent generalization capability and achieves state-of-the-art facial reflectance reconstruction results for in-the-wild faces.

Recent learning methods for object pose estimation require resource-intensive training for each individual object instance or category hampering their scalability in real applications when confronted with previously unseen objects. In this paper we propose MatchU a Fuse-Describe-Match strategy for 6D pose estimation from RGB-D images. MatchU is a generic approach that fuses 2D texture and 3D geometric cues for 6D pose prediction of unseen objects. We rely on learning geometric 3D descriptors that are rotation-invariant by design. By encoding pose-agnostic geometry the learned descriptors naturally generalize to unseen objects and capture symmetries. To tackle ambiguous associations using 3D geometry only we fuse additional RGB information into our descriptor. This is achieved through a novel attention-based mechanism that fuses cross-modal information together with a matching loss that leverages the latent space learned from RGB data to guide the descriptor learning process. Extensive experiments reveal the generalizability of both the RGB-D fusion strategy as well as the descriptor efficacy. Benefiting from the novel designs MatchU surpasses all existing methods by a significant margin in terms of both accuracy and speed even without the requirement of expensive re-training or rendering.

Self-attention mechanism is the key of the Transformer but often criticized for its computation demands. Previous token pruning works motivate their methods from the view of computation redundancy but still need to load the full network and require same memory costs. This paper introduces a novel strategy that simplifies vision transformers and reduces computational load through the selective removal of non-essential attention layers guided by entropy considerations. We identify that regarding the attention layer in bottom blocks their subsequent MLP layers i.e. two feed-forward layers can elicit the same entropy quantity. Meanwhile the accompanied MLPs are under-exploited since they exhibit smaller feature entropy compared to those MLPs in the top blocks. Therefore we propose to integrate the uninformative attention layers into their subsequent counterparts by degenerating them into identical mapping yielding only MLP in certain transformer blocks. Experimental results on ImageNet-1k show that the proposed method can remove 40% attention layer of DeiT-B improving throughput and memory bound without performance compromise.

Parameter-efficient fine-tuning for pre-trained Vision Transformers aims to adeptly tailor a model to downstream tasks by learning a minimal set of new adaptation parameters while preserving the frozen majority of pre-trained parameters. Striking a balance between retaining the generalizable representation capacity of the pre-trained model and acquiring task-specific features poses a key challenge. Currently there is a lack of focus on guiding this delicate trade-off. In this study we approach the problem from the perspective of Singular Value Decomposition (SVD) of pre-trained parameter matrices providing insights into the tuning dynamics of existing methods. Building upon this understanding we propose a Residual-based Low-Rank Rescaling (RLRR) fine-tuning strategy. This strategy not only enhances flexibility in parameter tuning but also ensures that new parameters do not deviate excessively from the pre-trained model through a residual design. Extensive experiments demonstrate that our method achieves competitive performance across various downstream image classification tasks all while maintaining comparable new parameters. We believe this work takes a step forward in offering a unified perspective for interpreting existing methods and serves as motivation for the development of new approaches that move closer to effectively considering the crucial trade-off mentioned above. Our code is available at https://github.com/zstarN70/RLRR.git.

This paper studies the problem of language-guided reflection separation which aims at addressing the ill-posed reflection separation problem by introducing language descriptions to provide layer content. We propose a unified framework to solve this problem which leverages the cross-attention mechanism with contrastive learning strategies to construct the correspondence between language descriptions and image layers. A gated network design and a randomized training strategy are employed to tackle the recognizable layer ambiguity. The effectiveness of the proposed method is validated by the significant performance advantage over existing reflection separation methods on both quantitative and qualitative comparisons.

Human pose and shape (HPS) estimation with lensless imaging is not only beneficial to privacy protection but also can be used in covert surveillance scenarios due to the small size and simple structure of this device. However this task presents significant challenges due to the inherent ambiguity of the captured measurements and lacks effective methods for directly estimating human pose and shape from lensless data. In this paper we propose the first end-to-end framework to recover 3D human poses and shapes from lensless measurements to our knowledge. We specifically design a multi-scale lensless feature decoder to decode the lensless measurements through the optically encoded mask for efficient feature extraction. We also propose a double-head auxiliary supervision mechanism to improve the estimation accuracy of human limb ends. Besides we establish a lensless imaging system and verify the effectiveness of our method on various datasets acquired by our lensless imaging system. The code and dataset are available at https://cic.tju.edu.cn/faculty/likun/projects/LPSNet.