论文检索

Ruiqi Wang, Xinggang Wang, Te Li, Rong Yang, Minhong Wan, Wenyu Liu

Category-level 6DoF object pose estimation intends to estimate the rotation, translation, and size of unseen objects. Many previous works use point clouds as a pre-learned shape prior to overcome intra-category variability. The shape prior is deformed to reconstruct instances' point clouds in canonical space and to build dense 3D-3D correspondences between the observed and reconstructed point clouds. However, the pre-learned shape prior is not jointly optimized with estimation networks, and they are trained with a surrogate objective. We propose a novel 6D pose estimation network, named Query6DoF, based on a series of category-specific sparse queries that represent the prior shape. Each query represents a shape component, and these queries are learnable embeddings that can be optimized together with the estimation network according to the point cloud reconstruction loss, the normalized object coordinate loss, and the 6d pose estimation loss. Query6DoF adopts a deformation-and-matching paradigm with attention, where the queries dynamically extract features from regions of interest using the attention mechanism and then directly regress results. Furthermore, Query6DoF reduces computation overhead through the sparseness of the queries and the incorporation of a lightweight global information injection block. With the aforementioned design, Query6DoF achieves state-of-the-art (SOTA) pose estimation performance on the NOCS datasets. The source code and models are available at https://github.com/hustvl/Query6DoF.

Qianqian Wang, Yen-Yu Chang, Ruojin Cai, Zhengqi Li, Bharath Hariharan, Aleksander Holynski, Noah Snavely

We present a new test-time optimization method for estimating dense and long-range motion from a video sequence. Prior optical flow or particle video tracking algorithms typically operate within limited temporal windows, struggling to track through occlusions and maintain global consistency of estimated motion trajectories. We propose a complete and globally consistent motion representation, dubbed OmniMotion, that allows for accurate, full-length motion estimation of every pixel in a video. OmniMotion represents a video using a quasi-3D canonical volume and performs pixel-wise tracking via bijections between local and canonical space. This representation allows us to ensure global consistency, track through occlusions, and model any combination of camera and object motion. Extensive evaluations on the TAP-Vid benchmark and real-world footage show that our approach outperforms prior state-of-the-art methods by a large margin both quantitatively and qualitatively.

Yan Luo, Min Shi, Yu Tian, Tobias Elze, Mengyu Wang

Glaucoma is the number one cause of irreversible blindness globally. A major challenge for accurate glaucoma detection and progression forecasting is the bottleneck of limited labeled patients with the state-of-the-art (SOTA) 3D retinal imaging data of optical coherence tomography (OCT). To address the data scarcity issue, this paper proposes two solutions. First, we develop a novel generalization-reinforced semi-supervised learning (SSL) model called pseudo supervisor to optimally utilize unlabeled data. Compared with SOTA models, the proposed pseudo supervisor optimizes the policy of predicting pseudo labels with unlabeled samples to improve empirical generalization. Our pseudo supervisor model is evaluated with two clinical tasks consisting of glaucoma detection and progression forecasting. The progression forecasting task is evaluated both unimodally and multimodally. Our pseudo supervisor model demonstrates superior performance than SOTA SSL comparison models. Moreover, our model also achieves the best results on the publicly available LAG fun- dus dataset. Second, we introduce the Harvard Glaucoma Detection and Progression (Harvard-GDP) Dataset, a multimodal multitask dataset that includes data from 1,000 patients with OCT imaging data, as well as labels for glaucoma detection and progression. This is the largest glaucoma detection dataset with 3D OCT imaging data and the first glaucoma progression forecasting dataset that is publicly available. Detailed sex and racial analysis are pro- vided, which can be used by interested researchers for fairness learning studies. Our released dataset is benchmarked with several SOTA supervised CNN and transformer deep learning models. The dataset and code are made publicly available via https://ophai.hms.harvard.edu/ datasets/harvard-gdp1000.

Nan Zhou, Jiaxin Chen, Di Huang

The visual models pretrained on large-scale benchmarks encode general knowledge and prove effective in building more powerful representations for downstream tasks. Most existing approaches follow the fine-tuning paradigm, either by initializing or regularizing the downstream model based on the pretrained one. The former fails to retain the knowledge in the successive fine-tuning phase, thereby prone to be over-fitting, and the latter imposes strong constraints to the weights or feature maps of the downstream model without considering semantic drift, often incurring insufficient optimization. To deal with these issues, we propose a novel fine-tuning framework, namely distribution regularization with semantic calibration (DR-Tune). It employs distribution regularization by enforcing the downstream task head to decrease its classification error on the pretrained feature distribution, which prevents it from over-fitting while enabling sufficient training of downstream encoders. Furthermore, to alleviate the interference by semantic drift, we develop the semantic calibration (SC) module to align the global shape and class centers of the pretrained and downstream feature distributions. Extensive experiments on widely used image classification datasets show that DR-Tune consistently improves the performance when combing with various backbones under different pretraining strategies. Code is available at: https://github.com/weeknan/DR-Tune.

Xiao Pan, Zongxin Yang, Jianxin Ma, Chang Zhou, Yi Yang

In this paper, we focus on the task of generalizable neural human rendering which trains conditional Neural Radiance Fields (NeRF) from multi-view videos of different characters. To handle the dynamic human motion, previous methods have primarily used a SparseConvNet (SPC)-based human representation to process the painted SMPL. However, such SPC-based representation i) optimizes under the volatile observation space which leads to the pose-misalignment between training and inference stages, and ii) lacks the global relationships among human parts that is critical for handling the incomplete painted SMPL. Tackling these issues, we present a brand-new framework named TransHuman, which learns the painted SMPL under the canonical space and captures the global relationships between human parts with transformers. Specifically, TransHuman is mainly composed of Transformer-based Human Encoding (TransHE), Deformable Partial Radiance Fields (DPaRF), and Fine-grained Detail Integration (FDI). TransHE first processes the painted SMPL under the canonical space via transformers for capturing the global relationships between human parts. Then, DPaRF binds each output token with a deformable radiance field for encoding the query point under the observation space. Finally, the FDI is employed to further integrate fine-grained information from reference images. Extensive experiments on ZJU-MoCap and H36M show that our TransHuman achieves a significantly new state-of-the-art performance with high efficiency. Project page: https://pansanity666.github.io/TransHuman/

Tianshi Cao, Karsten Kreis, Sanja Fidler, Nicholas Sharp, Kangxue Yin

We present TexFusion(Texture Diffusion), a new method to synthesize textures for given 3D geometries, using only large-scale text-guided image diffusion models. In contrast to recent works that leverage 2D text-to-image diffusion models to distill 3D objects using a slow and fragile optimization process, TexFusion introduces a new 3D-consistent generation technique specifically designed for texture synthesis that employs regular diffusion model sampling on different 2D rendered views. Specifically, we leverage latent diffusion models, apply the diffusion model's denoiser on a set of 2D renders of the 3D object, and aggregate the different denoising predictions on a shared latent texture map. Final RGB output textures are produced by optimizing an intermediate neural color field on the decodings of 2D renders of the latent texture. We thoroughly validate TexFusion and show that we can efficiently generate diverse, high quality and globally coherent textures. We achieve state-of-the-art text-guided texture synthesis performance using only image diffusion models, while avoiding the pitfalls of previous distillation-based methods. The text-conditioning offers detailed control and we also do not rely on any ground truth 3D textures for training. This makes our method very versatile and applicable to a broad range of geometries and texture types. We hope that TexFusion will advance AI-based texturing of 3D assets for applications in virtual reality, game design, simulation, and more.

Chen Yang, Meilu Zhu, Yifan Liu, Yixuan Yuan

Existing federated learning (FL) approaches are deployed under the unrealistic closed-set setting, with both training and testing classes belong to the same set, which makes the global model fail to identify the unseen classes as `unknown'. To this end, we aim to study a novel problem of federated open-set recognition (FedOSR), which learns an open-set recognition (OSR) model under federated paradigm such that it classifies seen classes while at the same time detects unknown classes. In this work, we propose a parameter disentanglement guided federated open-set recognition (FedPD) algorithm to address two core challenges of FedOSR: cross-client inter-set interference between learning closed-set and open-set knowledge and cross-client intra-set inconsistency by data heterogeneity. The proposed FedPD framework mainly leverages two modules, i.e., local parameter disentanglement (LPD) and global divide-and-conquer aggregation (GDCA), to first disentangle client OSR model into different subnetworks, then align the corresponding parts cross clients for matched model aggregation. Specifically, on the client side, LPD decouples an OSR model into a closed-set subnetwork and an open-set subnetwork by the task-related importance, thus preventing inter-set interference. On the server side, GDCA first partitions the two subnetworks into specific and shared parts, and subsequently aligns the corresponding parts through optimal transport to eliminate parameter misalignment. Extensive experiments on various datasets demonstrate the superior performance of our proposed method.

Jiahao Li, Zongxin Yang, Xiaohan Wang, Jianxin Ma, Chang Zhou, Yi Yang

In this study, we focus on the problem of 3D human mesh recovery from a single image under obscured conditions. Most state-of-the-art methods aim to improve 2D alignment technologies, such as spatial averaging and 2D joint sampling. However, they tend to neglect the crucial aspect of 3D alignment by improving 3D representations. Furthermore, recent methods struggle to separate target human from occlusion or background in crowded scenes as they optimize the 3D space of target human with 3D joint coordinates as local supervision. To address these issues, a desirable method would involve a framework for fusing 2D and 3D features and a strategy for optimizing the 3D space globally. Therefore, this paper presents 3D JOint contrastive learning with TRansformers (JOTR) framework for handling occluded 3D human mesh recovery. Our method includes an encoder-decoder transformer architecture to fuse 2D and 3D representations for achieving 2D&3D aligned results in a coarse-to-fine manner and a novel 3D joint contrastive learning approach for adding explicitly global supervision for the 3D feature space. The contrastive learning approach includes two contrastive losses: joint-to-joint contrast for enhancing the similarity of semantically similar voxels (i.e., human joints), and joint-to-non-joint contrast for ensuring discrimination from others (e.g., occlusions and background). Qualitative and quantitative analyses demonstrate that our method outperforms state-of-the-art competitors on both occlusion-specific and standard benchmarks, significantly improving the reconstruction of occluded humans.

Youmin Zhang, Fabio Tosi, Stefano Mattoccia, Matteo Poggi

Neural implicit representations have recently demonstrated compelling results on dense Simultaneous Localization And Mapping (SLAM) but suffer from the accumulation of errors in camera tracking and distortion in the reconstruction. Purposely, we present GO-SLAM, a deep-learning-based dense visual SLAM framework globally optimizing poses and 3D reconstruction in real-time. Robust pose estimation is at its core, supported by efficient loop closing and online full bundle adjustment, which optimize per frame by utilizing the learned global geometry of the complete history of input frames. Simultaneously, we update the implicit and continuous surface representation on-the-fly to ensure global consistency of 3D reconstruction. Results on various synthetic and real-world datasets demonstrate that GO-SLAM outperforms state-of-the-art approaches at tracking robustness and reconstruction accuracy. Furthermore, GO-SLAM is versatile and can run with monocular, stereo, and RGB-D input.

Fu-En Yang, Chien-Yi Wang, Yu-Chiang Frank Wang

Federated learning (FL) emerges as a decentralized learning framework which trains models from multiple distributed clients without sharing their data to preserve privacy. Recently, large-scale pre-trained models (e.g., Vision Transformer) have shown a strong capability of deriving robust representations. However, the data heterogeneity among clients, the limited computation resources, and the communication bandwidth restrict the deployment of large-scale models in FL frameworks. To leverage robust representations from large-scale models while enabling efficient model personalization for heterogeneous clients, we propose a novel personalized FL framework of client-specific Prompt Generation (pFedPG), which learns to deploy a personalized prompt generator at the server for producing client-specific visual prompts that efficiently adapts frozen backbones to local data distributions. Our proposed framework jointly optimizes the stages of personalized prompt adaptation locally and personalized prompt generation globally. The former aims to train visual prompts that adapt foundation models to each client, while the latter observes local optimization directions to generate personalized prompts for all clients. Through extensive experiments on benchmark datasets, we show that our pFedPG is favorable against state-of-the-art personalized FL methods under various types of data heterogeneity, allowing computation and communication efficient model personalization.

Yumeng Shi, Shihao Bai, Xiuying Wei, Ruihao Gong, Jianlei Yang

Deep neural networks have delivered remarkable performance and have been widely used in various visual tasks. However, their huge sizes cause significant inconvenience for transmission and storage. Many previous studies have explored model size compression. However, these studies often approach various lossy and lossless compression methods in isolation, leading to challenges in achieving high compression ratios efficiently. This work proposes a post-training model size compression method that combines lossy and lossless compression in a unified way. We first propose a unified parametric weight transformation, which ensures different lossy compression methods can be performed jointly in a post-training manner. Then, a dedicated differentiable counter is introduced to guide the optimization of lossy compression to arrive at a more suitable point for later lossless compression. Additionally, our method can easily control a desired global compression ratio and allocate adaptive ratios for different layers. Finally, our method can achieve a stable 10 times compression ratio without sacrificing accuracy and a 20 times compression ratio with minor accuracy loss in a short time. Our code is available at https://github.com/ModelTC/L2_Compression.

Lang Nie, Chunyu Lin, Kang Liao, Shuaicheng Liu, Yao Zhao

Traditional image stitching approaches tend to leverage increasingly complex geometric features (point, line, edge, etc.) for better performance. However, these hand-crafted features are only suitable for specific natural scenes with adequate geometric structures. In contrast, deep stitching schemes overcome adverse conditions by adaptively learning robust semantic features, but they cannot handle large-parallax cases. To solve these issues, we propose a parallax-tolerant unsupervised deep image stitching technique. First, we propose a robust and flexible warp to model the image registration from global homography to local thin-plate spline motion. It provides accurate alignment for overlapping regions and shape preservation for non-overlapping regions by joint optimization concerning alignment and distortion. Subsequently, to improve the generalization capability, we design a simple but effective iterative strategy to enhance the warp adaption in cross-dataset and cross-resolution applications. Finally, to further eliminate the parallax artifacts, we propose to composite the stitched image seamlessly by unsupervised learning for seam-driven composition masks. Compared with existing methods, our solution is parallax-tolerant and free from laborious designs of complicated geometric features for specific scenes. Extensive experiments show our superiority over the SoTA methods, both quantitatively and qualitatively. The code will be available soon.

Anagnostidis Sotiris, Aurelien Lucchi, Thomas Hofmann

Accurately predicting road networks from satellite images requires a global understanding of the network topology. We propose to capture such high-level information by introducing a graph-based framework that given a partially generated graph, sequentially adds new edges. To deal with misalignment between the model predictions and the intended purpose, and to optimize over complex, non-continuous metrics of interest, we adopt a reinforcement learning (RL) approach that nominates modifications that maximize a cumulative reward. As opposed to standard supervised techniques that tend to be more restricted to commonly used surrogate losses, our framework yields more power and flexibility to encode problem-dependent knowledge. Empirical results on several benchmark datasets demonstrate enhanced performance and increased high-level reasoning about the graph topology when using a tree-based search. We further demonstrate the superiority of our approach in handling examples with substantial occlusion and additionally provide evidence that our predictions better match the statistical properties of the ground dataset.

Etai Sella, Gal Fiebelman, Peter Hedman, Hadar Averbuch-Elor

Large scale text-guided diffusion models have garnered significant attention due to their ability to synthesize diverse images that convey complex visual concepts. This generative power has more recently been leveraged to perform text-to-3D synthesis. In this work, we present a technique that harnesses the power of latent diffusion models for editing existing 3D objects. Our method takes oriented 2D images of a 3D object as input and learns a grid-based volumetric representation of it. To guide the volumetric representation to conform to a target text prompt, we follow unconditional text-to-3D methods and optimize a Score Distillation Sampling (SDS) loss. However, we observe that combining this diffusion-guided loss with an image-based regularization loss that encourages the representation not to deviate too strongly from the input object is challenging, as it requires achieving two conflicting goals while viewing only structure-and-appearance coupled 2D projections. Thus, we introduce a novel volumetric regularization loss that operates directly in 3D space, utilizing the explicit nature of our 3D representation to enforce correlation between the global structure of the original and edited object. Furthermore, we present a technique that optimizes cross-attention volumetric grids to refine the spatial extent of the edits. Extensive experiments and comparisons demonstrate the effectiveness of our approach in creating a myriad of edits which cannot be achieved by prior works. Our code and data will be made publicly available.

Lujun Li, Peijie Dong, Zimian Wei, Ya Yang

In this paper, we present Auto-KD, the first automated search framework for optimal knowledge distillation design. Traditional distillation techniques typically require handcrafted designs by experts and extensive tuning costs for different teacher-student pairs. To address these issues, we empirically study different distillers, finding that they can be decomposed, combined, and simplified. Based on these observations, we build our uniform search space with advanced operations in transformations, distance functions, and hyperparameters components. For instance, the transformation parts are optional for global, intra-spatial, and inter-spatial operations, such as attention, mask, and multi-scale. Then, we introduce an effective search strategy based on the Monte Carlo tree search, modeling the search space as a Monte Carlo Tree (MCT) to capture the dependency among options. The MCT is updated using test loss and representation gap of student trained by candidate distillers as the reward for better exploration-exploitation balance. To accelerate the search process, we exploit offline processing without teacher inference, sparse training for student, and proxy settings based on distillation properties. In this way, our Auto-KD only needs small costs to search for optimal distillers before the distillation phase. Moreover, we expand Auto-KD for multi-layer and multi-teacher scenarios with training-free weighted factors. Our method is promising yet practical, and extensive experiments demonstrate that it generalizes well to different CNNs and Vision Transformer models and attains state-of-the-art performance across a range of vision tasks, including image classification, object detection, and semantic segmentation. Code is provided at https://github.com/lilujunai/Auto-KD.

Yixuan Pei, Zhiwu Qing, Shiwei Zhang, Xiang Wang, Yingya Zhang, Deli Zhao, Xueming Qian

Recently, prompt-based learning has made impressive progress on image class-incremental learning, but it still lacks sufficient exploration in the video domain. In this paper, we will fill this gap by learning multiple prompts based on a powerful image-language pre-trained model, i.e., CLIP, making it fit for video class-incremental learning (VCIL). For this purpose, we present a space-time prompting approach (ST-Prompt) which contains two kinds of prompts, i.e., task-specific prompts and task-agnostic prompts. The task-specific prompts are to address the catastrophic forgetting problem by learning multi-grained prompts, i.e., spatial prompts, temporal prompts and comprehensive prompts, for accurate task identification. The task-agnostic prompts maintain a globally-shared prompt pool, which can empower the pre-trained image models with temporal perception abilities by exchanging contexts between frames. By this means, ST-Prompt can transfer the plentiful knowledge in the image-language pre-trained models to the VCIL task with only a tiny set of prompts to be optimized. To evaluate ST-Prompt, we conduct extensive experiments on three standard benchmarks. The results show that ST-Prompt can significantly surpass the state-of-the-art VCIL methods, especially it gains 9.06% on HMDB51 dataset under the 1*25 stage setting.

Chaoqiang Zhao, Matteo Poggi, Fabio Tosi, Lei Zhou, Qiyu Sun, Yang Tang, Stefano Mattoccia

This paper tackles the challenges of self-supervised monocular depth estimation in indoor scenes caused by large rotation between frames and low texture. We ease the learning process by obtaining coarse camera poses from monocular sequences through multi-view geometry to deal with the former. However, we found that limited by the scale ambiguity across different scenes in the training dataset, a naive introduction of geometric coarse poses cannot play a positive role in performance improvement, which is counter-intuitive. To address this problem, we propose to refine those poses during training through rotation and translation/scale optimization. To soften the effect of the low texture, we combine the global reasoning of vision transformers with an overfitting-aware, iterative self-distillation mechanism, providing more accurate depth guidance coming from the network itself. Experiments on NYUv2, ScanNet, 7scenes, and KITTI datasets support the effectiveness of each component in our framework, which sets a new state-of-the-art for indoor self-supervised monocular depth estimation, as well as outstanding generalization ability. Code and models are available at https://github.com/zxcqlf/GasMono

Natalia Frumkin, Dibakar Gope, Diana Marculescu

Quantization scale and bit-width are the most important parameters when considering how to quantize a neural network. Prior work focuses on optimizing quantization scales in a global manner through gradient methods (gradient descent & Hessian analysis). Yet, when applying perturbations to quantization scales, we observe a very jagged, highly non-smooth test loss landscape. In fact, small perturbations in quantization scale can greatly affect accuracy, yielding a 0.5-0.8% accuracy boost in 4-bit quantized vision transformers (ViTs). In this regime, gradient methods break down, since they cannot reliably reach local minima. In our work, dubbed Evol-Q, we use evolutionary search to effectively traverse the non-smooth landscape. Additionally, we propose using an infoNCE loss, which not only helps combat overfitting on the small (1,000 images) calibration dataset but also makes traversing such a highly non-smooth surface easier. Evol-Q improves the top-1 accuracy of a fully quantized ViT-Base by 10.30%, 0.78%, and 0.15% for 3-bit, 4-bit, and 8-bit weight quantization levels. Extensive experiments on a variety of CNN and ViT architectures further demonstrate its robustness in extreme quantization scenarios.

Qi Zhu, Man Zhou, Naishan Zheng, Chongyi Li, Jie Huang, Feng Zhao

Video deblurring aims to restore the latent video frames from their blurred counterparts. Despite the remarkable progress, most promising video deblurring methods only investigate the temporal priors in the spatial domain and rarely explore their its potential in the frequency domain. In this paper, we revisit the blurred sequence in the Fourier space and figure out some intrinsic frequency-temporal priors that imply the temporal blur degradation can be accessibly decoupled in the potential frequency domain. Based on these priors, we propose a novel Fourier-based frequency-temporal video deblurring solution, where the core design accommodates the temporal spectrum to a popular video deblurring pipeline of feature extraction, alignment, aggregation, and optimization. Specifically, we design a Spectrum Prior-guided Alignment module by leveraging enlarged blur information in the potential spectrum to mitigate the blur effects on the alignment. Then, Temporal Energy prior-driven Aggregation is implemented to replenish the original local features by estimating the temporal spectrum energy as the global sharpness guidance. In addition, the customized frequency loss is devised to optimize the proposed method for decent spectral distribution. Extensive experiments demonstrate that our model performs favorably against other state-of-the-art methods, thus confirming the effectiveness of frequency-temporal prior modeling.

Minying Zhang, Tianpeng Bu, Lulu Hu

There are two main approaches to object detection: CNN-based and Transformer-based. The former views object detection as a dense local matching problem, while the latter sees it as a sparse global retrieval problem. Research in neuroscience has shown that the recognition decision in the brain is based on two processes, namely familiarity and recollection. Based on this biological support, we propose an efficient and effective dual-processing object detection framework. It integrates CNN- and Transformer-based detectors into a comprehensive object detection system consisting of a shared backbone, an efficient dual-stream encoder, and a dynamic dual-decoder. To better integrate local and global features, we design a search space for the CNN-Transformer dual-stream encoder to find the optimal fusion solution. To enable better coordination between the CNN- and Transformer-based decoders, we provide the dual-decoder with a selective mask. This mask dynamically chooses the more advantageous decoder for each position in the image based on high-level representation. As demonstrated by extensive experiments, our approach shows flexibility and effectiveness in prompting the mAP of the various source detectors by 3.0 3.7 without increasing FLOPs.