ECCV 2024 论文列表

"Story visualization aims to generate a series of realistic and coherent images based on a storyline. Current models adopt a frame-by-frame architecture by transforming the pre-trained text-to-image model into an auto-regressive manner. Although these models have shown notable progress, there are still three flaws. 1) The unidirectional generation of auto-regressive manner restricts the usability in many scenarios. 2) The additional introduced story history encoders bring an extremely high computational cost. 3) The story visualization and continuation models are trained and inferred independently, which is not user-friendly. To these ends, we propose a bidirectional, unified, and efficient framework, namely StoryImager. The StoryImager enhances the storyboard generative ability inherited from the pre-trained text-to-image model for a bidirectional generation. Specifically, we introduce a Target Frame Masking Strategy to extend and unify different story image generation tasks. Furthermore, we propose a Frame-Story Cross Attention Module that decomposes the cross attention for local fidelity and global coherence. Moreover, we design a Contextual Feature Extractor to extract contextual information from the whole storyline. The extensive experimental results demonstrate the excellent performance of our StoryImager. Code is available at https://github.com/tobran/StoryImager."

"Large pretrained plain vision Transformers (ViTs) have been the workhorse for many downstream tasks. However, existing works utilizing off-the-shelf ViTs are inefficient in terms of training and deployment, because adopting ViTs with individual sizes requires separate trainings and is restricted by fixed performance-efficiency trade-offs. In this paper, we are inspired by stitchable neural networks (SN-Net), which is a new framework that cheaply produces a single model that covers rich subnetworks by stitching pretrained model families, supporting diverse performance-efficiency trade-offs at runtime. Building upon this foundation, we introduce SN-Netv2, a systematically improved model stitching framework to facilitate downstream task adaptation. Specifically, we first propose a two-way stitching scheme to enlarge the stitching space. We then design a resource-constrained sampling strategy that takes into account the underlying FLOPs distributions in the space for better sampling. Finally, we observe that learning stitching layers as a low-rank update plays an essential role on downstream tasks to stabilize training and ensure a good Pareto frontier. With extensive experiments on ImageNet-1K, ADE20K, COCO-Stuff-10K and NYUv2, SN-Netv2 demonstrates superior performance over SN-Netv1 on downstream dense predictions and shows strong ability as a flexible vision backbone, achieving great advantages in both training efficiency and deployment flexibility."

"We propose StereoGlue, a method designed for joint feature matching and robust estimation that effectively reduces the combinatorial complexity of these tasks using single-point minimal solvers. StereoGlue is applicable to a range of problems, including but not limited to relative pose and homography estimation, determining absolute pose with 2D-3D correspondences, and estimating 3D rigid transformations between point clouds. StereoGlue starts with a set of one-to-many tentative correspondences, iteratively forms tentative matches, and estimates the minimal sample model. This model then facilitates guided matching, leading to consistent one-to-one matches, whose number serves as the model score. StereoGlue is superior to the state-of-the-art robust estimators on real-world datasets on multiple problems, improving upon a number of recent feature detectors and matchers. Additionally, it shows improvements in point cloud matching and absolute camera pose estimation. The code is at: https:// github.com/danini/stereoglue."

"Point-supervised temporal action localization pursues high-accuracy action detection under low-cost data annotation. Despite recent advances, a significant challenge remains: sparse labeling of individual frames leads to semantic ambiguity in determining action boundaries due to the lack of continuity in the highly sparse point-supervision scheme. We propose a Stepwise Multi-grained Boundary Detector (SMBD), which is comprised of a Background Anchor Generator (BAG) and a Dual Boundary Detector (DBD) to provide fine-grained supervision. Specifically, for each epoch in the training process, BAG computes the optimal background snippet between each pair of adjacent action labels, which we term Background Anchor. Subsequently, DBD leverages the background anchor and the action labels to locate the action boundaries from the perspectives of detecting action changes and scene changes. Then, the corresponding labels can be assigned to each side of the boundaries, with the boundaries continuously updated throughout the training process. Consequently, the proposed SMBD could ensure that more snippets contribute to the training process. Extensive experiments on the THUMOS’14, GTEA and BEOID datasets demonstrate that the proposed method outperforms existing state-of-the-art methods."

"Audio-Visual Segmentation (AVS) aims to achieve pixel-level localization of sound sources in videos, while Audio-Visual Semantic Segmentation (AVSS), as an extension of AVS, further pursues semantic understanding of audio-visual scenes. However, since the AVSS task requires the establishment of audio-visual correspondence and semantic understanding simultaneously, we observe that previous methods have struggled to handle this mashup of objectives in end-to-end training, resulting in insufficient learning and sub-optimization. Therefore, we propose a two-stage training strategy called Stepping Stones, which decomposes the AVSS task into two simple subtasks from localization to semantic understanding, which are fully optimized in each stage to achieve step-by-step global optimization. This training strategy has also proved its generalization and effectiveness on existing methods. To further improve the performance of AVS tasks, we propose a novel framework Adaptive Audio Visual Segmentation, in which we incorporate an adaptive audio query generator and integrate masked attention into the transformer decoder, facilitating the adaptive fusion of visual and audio features. Extensive experiments demonstrate that our methods achieve state-of-the-art results on all three AVS benchmarks. The project homepage can be accessed at https://gewu-lab.github.io/stepping stones."

This work presents a method that is able to predict the geolocation of a street-view photo taken in the wild within a state-sized search region by matching against a database of aerial reference imagery. We partition the search region into geographical cells and train a model to map cells and corresponding photos into a joint embedding space that is used to perform retrieval at test time. The model utilizes aerial images for each cell at multiple levels-of-detail to provide sufficient information about the surrounding scene. We propose a novel layout of the search region with consistent cell resolutions that allows scaling to large geographical regions. Experiments demonstrate that the method successfully localizes 60.6% of all non-panoramic street-view photos uploaded to the crowd-sourcing platform Mapillary in the state of Massachusetts to within 50m of their ground-truth location. Source code is available at https://github.com/fferflo/statewide-visu

"Point-based image editing has attracted remarkable attention since the emergence of DragGAN. Recently, DragDiffusion further pushes forward the generative quality via adapting this dragging technique to diffusion models. Despite these great success, this dragging scheme exhibits two major drawbacks, namely inaccurate point tracking and incomplete motion supervision, which may result in unsatisfactory dragging outcomes. To tackle these issues, we build a stable and precise drag-based editing framework, coined as StableDrag , by designing a discriminative point tracking method and a confidence-based latent enhancement strategy for motion supervision. The former allows us to precisely locate the updated handle points, thereby boosting the stability of long-range manipulation, while the latter is responsible for guaranteeing the optimized latent as high-quality as possible across all the manipulation steps. Thanks to these unique designs, we instantiate two types of image editing models including StableDrag-GAN and StableDrag-Diff, which attains more stable dragging performance, through extensive qualitative experiments and quantitative assessment on DragBench."

"Rapid advances in the field of generative AI and text-to-image methods in particular have transformed the way we interact with and perceive computer-generated imagery today. In parallel, much progress has been made in 3D face reconstruction, using 3D Morphable Models (3DMM). In this paper, we present , a novel hybrid 2D/3D generation method that outputs photorealistic videos of talking faces leveraging a large pre-trained text-to-image prior (2D), controlled via a 3DMM (3D). Specifically, we introduce a person-specific fine-tuning of a general 2D stable diffusion model which we lift to a video model by providing temporal 3DMM sequences as conditioning and by introducing a temporal denoising procedure. As an output, this model generates temporally smooth imagery of a person with 3DMM-based controls, i.e., a person-specific avatar. The facial appearance of this person-specific avatar can be edited and morphed to text-defined celebrities, without any fine-tuning at test time. The method is analyzed quantitatively and qualitatively, and we show that our method outperforms state-of-the-art monocular head avatar methods. https://svp.is.tue.mpg.de/"

"In recent years, deep generative models have developed rapidly and can generate high-quality images based on input texts. Assessing the quality of synthetic images in a way consistent with human preferences is critical for both generative model evaluation and preferred image selection. Previous works aligned models with human preferences by training scoring models on image pairs with preference annotations. These carefully annotated image pairs well describe human preferences for choosing images. However, current training paradigm of these preference models is to directly maximize the preferred image score while minimizing the non-preferred image score in each image pair through cross-entropy loss. This simple and naive training paradigm mainly has two problems: 1) For image pairs of similar quality, it is unreasonable to blindly minimize the score of non-preferred images and can easily lead to overfitting. 2) The human robustness to small visual perturbations is not taken into account, resulting in the final model being unable to make stable choices. Therefore, we propose Stable Preference to redefine the training paradigm of human preference model and a anti-interference loss to improve the robustness to visual disturbances. Our method achieves state-of-the-art performance on two popular text-to-image human preference datasets. Extensive ablation studies and visualizations demonstrate the rationality and effectiveness of our method."

"We introduce Spline-based Transformers, a novel class of Transformer models that eliminate the need for positional encoding. Inspired by workflows using splines in computer animation, our Spline-based Transformers embed an input sequence of elements as a smooth trajectory in latent space. Overcoming drawbacks of positional encoding such as sequence length extrapolation, Spline-based Transformers also provide a novel way for users to interact with transformer latent spaces by directly manipulating the latent control points to create new latent trajectories and sequences. We demonstrate the superior performance of our approach in comparison to conventional positional encoding on a variety of datasets, ranging from synthetic 2D to large-scale real-world datasets of images, 3D shapes, and animations."

"Digitizing 3D static scenes and 4D dynamic events from multi-view images has long been a challenge in computer vision and graphics. Recently, 3D Gaussian Splatting (3DGS) has emerged as a practical and scalable reconstruction method, gaining popularity due to its impressive reconstruction quality, real-time rendering capabilities, and compatibility with widely used visualization tools. However, the method requires a substantial number of input views to achieve high-quality scene reconstruction, introducing a significant practical bottleneck. This challenge is especially severe in capturing dynamic scenes, where deploying an extensive camera array can be prohibitively costly. In this work, we identify the lack of spatial autocorrelation of splat features as one of the factors contributing to the suboptimal performance of the 3DGS technique in sparse reconstruction settings. To address the issue, we propose an optimization strategy that effectively regularizes splat features by modeling them as the outputs of a corresponding implicit neural field. This results in a consistent enhancement of reconstruction quality across various scenarios. Our approach effectively handles static and dynamic cases, as demonstrated by extensive testing across different setups and scene complexities."

"Spiking neural networks (SNNs) offer an energy-efficient alternative to conventional deep learning by emulating the event-driven processing manner of the brain. Incorporating Transformers with SNNs has shown promise for accuracy. However, they struggle to learn high-frequency patterns, such as moving edges and pixel-level brightness changes, because they rely on the global self-attention mechanism. Learning these high-frequency representations is challenging but essential for SNN-based event-driven vision. To address this issue, we propose the Spiking Wavelet Transformer (SWformer), an attention-free architecture that effectively learns comprehensive spatial-frequency features in a spike-driven manner by leveraging the sparse wavelet transform. The critical component is a Frequency-Aware Token Mixer (FATM) with three branches: 1) spiking wavelet learner for spatial-frequency domain learning, 2) convolution-based learner for spatial feature extraction, and 3) spiking pointwise convolution for cross-channel information aggregation - with negative spike dynamics incorporated in 1) to enhance frequency representation. The FATM enables the SWformer to outperform vanilla Spiking Transformers in capturing high-frequency visual components, as evidenced by our empirical results. Experiments on both static and neuromorphic datasets demonstrate SWformer’s effectiveness in capturing spatial-frequency patterns in a multiplication-free and event-driven fashion, outperforming state-of-the-art SNNs. SWformer achieves a 22.03% reduction in parameter count, and a 2.52% performance improvement on the ImageNet dataset compared to vanilla Spiking Transformers. The code is available at: https://github.com/bic-L/Spiking-Wavelet-Transformer."

"Event-to-Video (E2V) reconstruction aims to recover grayscale video from neuromorphic event streams, with Spiking Neural Networks (SNNs) being promising energy-efficient models for this task. Event voxels effectively compress event streams for E2V reconstruction, yet their temporal latent representation is rarely considered in SNN-based approaches. In this paper, we propose a spike-temporal latent representation (STLR) model for SNN-based E2V reconstruction. The STLR solves the temporal latent coding of event voxels for video frame reconstruction. It is composed of two cascaded SNNs: a) Spike-based Voxel Temporal Encoder (SVT) and b) U-shape SNN Decoder. The SVT is a spike-driven spatial unfolding network with a specially designed coding dynamic. It encodes the event voxel into the layer-wise spiking features for latent coding, approximating the fixed point of the Iterative Shrinkage-Thresholding Algorithm. Then, the U-shape SNN decoder reconstructs the video based on the encoded spikes. Experimental results demonstrate that the STLR achieves performance comparable to popular SNNs on IJRR, HQF, and MVSEC datasets while significantly enhancing energy efficiency."

"Egocentric videos provide comprehensive contexts for user and scene understanding, spanning multisensory perception to behavioral interaction. We propose Spherical World-Locking (SWL) as a general framework for egocentric scene representation, which implicitly transforms multisensory streams with respect to measurements of head orientation. Compared to conventional head-locked egocentric representations with a 2D planar field-of-view, SWL effectively offsets challenges posed by self-motion, allowing for improved spatial synchronization between input modalities. Using a set of multisensory embeddings on a world-locked sphere, we design a unified encoder-decoder transformer architecture that preserves the spherical structure of the scene representation, without requiring expensive projections between image and world coordinate systems. We evaluate the effectiveness of the proposed framework on multiple benchmark tasks for egocentric video understanding, including audio-visual active speaker localization, auditory spherical source localization, and behavior anticipation in everyday activities."

"Composed Image Retrieval (CIR) is a complex task that retrieves images using a query, which is configured with an image and a caption that describes desired modifications to that image. Supervised CIR approaches have shown strong performance, but their reliance on expensive manually-annotated datasets restricts their scalability and broader applicability. To address these issues, previous studies have proposed pseudo-word token-based Zero-Shot CIR (ZS-CIR) methods, which utilize a projection module to map images to word tokens. However, we conjecture that this approach has a downside: the projection module distorts the original image representation and confines the resulting composed embeddings to the text-side. In order to resolve this, we introduce a novel ZS-CIR method that uses Spherical Linear Interpolation (Slerp) to directly merge image and text representations by identifying an intermediate embedding of both. Furthermore, we introduce Text-Anchored-Tuning (TAT), a method that fine-tunes the image encoder while keeping the text encoder fixed. TAT closes the modality gap between images and text, making the Slerp process much more effective. Notably, the TAT method is not only efficient in terms of the scale of the training dataset and training time, but it also serves as an excellent initial checkpoint for training supervised CIR models, thereby highlighting its wider potential. The integration of the Slerp-based ZS-CIR with a TAT-tuned model enables our approach to deliver state-of-the-art retrieval performance across CIR benchmarks. Code is available at https://github.com/youngkyunJang/SLERP-TAT"

"While recent advances in 3D-aware Generative Adversarial Networks (GANs) have aided the development of near-frontal view human face synthesis, the challenge of comprehensively synthesizing a full 3D head viewable from all angles still persists. Although PanoHead [?] proves the possibilities of using a large-scale dataset with images of both frontal and back views for full-head synthesis, it often causes artifacts for back views. Based on our in-depth analysis, we found the reasons are mainly twofold. First, from network architecture perspective, we found each plane in the utilized tri-plane/tri-grid representation space tends to confuse the features from both sides, causing “mirroring” artifacts (e.g., the glasses appear in the back). Second, from data supervision aspect, we found that existing discriminator training in 3D-aware GANs mainly focuses on the quality of the rendered image itself, and does not care much about its plausibility with the perspective from which it was rendered. This makes it possible to generate “face” in non-frontal views, due to its easiness to fool the discriminator. In response, we propose SphereHead, a novel tri-plane representation in the spherical coordinate system that fits the human head’s geometric characteristics and efficiently mitigates many of the generated artifacts. We further introduce a view-image consistency loss for the discriminator to emphasize the correspondence of the camera parameters and the images. The combination of these efforts results in visually superior outcomes with significantly fewer artifacts. Our code and dataset is publicly available at https://lhyfst.github.io/spherehead/."

"Text-to-image diffusion models (SD) exhibit significant advancements while requiring extensive computational resources. Existing acceleration methods usually require extensive training and are not universally applicable. LCM-LoRA, trainable once for diverse models, offers universality but rarely considers ensuring the consistency of generated content before and after acceleration. This paper proposes SpeedUpNet (SUN), an innovative acceleration module, to address the challenges of universality and consistency. Exploiting the role of cross-attention layers in U-Net for SD models, we introduce an adapter specifically designed for these layers, quantifying the offset in image generation caused by negative prompts relative to positive prompts. This learned offset demonstrates stability across a range of models, enhancing SUN’s universality. To improve output consistency, we propose a Multi-Step Consistency (MSC) loss, which stabilizes the offset and ensures fidelity in accelerated content. Experiments on SD v1.5 show that SUN leads to an overall speedup of more than 10 times compared to the baseline 25-step DPM-solver++, and offers two extra advantages: (1) training-free integration into various fine-tuned Stable-Diffusion models and (2) state-of-the-art FIDs of the generated data set before and after acceleration guided by random combinations of positive and negative prompts. Code is available1 . 1 Project: https://williechai.github.io/speedup-plugin-for-stable-diffusions.github.io"

"This study advances material classification using Spectral Sub-Surface Scattering (4) measurements. While spectrum and subsurface scattering measurements have individually been used in material classification, we argue that the strong spectral dependence of subsurface scattering lends itself to highly discriminative features. However, obtaining 4 measurements requires a time-consuming hyperspectral scan. We avoid this by showing that a carefully chosen 2D projection of the 4 point spread function is sufficient for material estimation. We also design and implement a novel imaging setup, consisting of a point illumination and a spectrally-dispersing camera, to make the desired 2D projections. Finally, through comprehensive experiments, we demonstrate the superiority of 4 imaging over spectral and sub-surface scattering measurements for the task of material classification."

"Vision Transformers (ViTs) are increasingly used in computer vision due to their high performance, but their vulnerability to adversarial attacks is a concern. Existing methods lack a solid theoretical basis, focusing mainly on empirical training adjustments. This study introduces , tailored to fortify ViTs against adversarial attacks, with theoretical underpinnings. We establish local Lipschitz bounds for the self-attention layer and propose the Maximum Singular Value Penalization (MSVP) to precisely manage these bounds By incorporating MSVP into ViTs’ attention layers, we enhance the model’s robustness without compromising training efficiency. SpecFormer, the resulting model, outperforms other state-of-the-art models in defending against adversarial attacks, as proven by experiments on CIFAR and ImageNet datasets. Code is released at https://github.com/microsoft/robustlearn."