ECCV 2024 Papers

"Class incremental semantic segmentation aims to preserve old knowledge while learning new tasks, however, it is impeded by catastrophic forgetting and background shift issues. Prior works indicate the pivotal importance of initializing new classifiers and mainly focus on transferring knowledge from the background classifier or preparing classifiers for future classes, neglecting the flexibility and variance of new classifiers. In this paper, we propose a new classifier pre-tuning (NeST) method applied before the formal training process, learning a transformation from old classifiers to generate new classifiers for initialization rather than directly tuning the parameters of new classifiers. Our method can make new classifiers align with the backbone and adapt to the new data, preventing drastic changes in the feature extractor when learning new classes. Besides, we design a strategy considering the cross-task class similarity to initialize matrices used in the transformation, helping achieve the stability-plasticity trade-off. Experiments on Pascal VOC 2012 and ADE20K datasets show that the proposed strategy can significantly improve the performance of previous methods. The code is available at https://github.com/zhengyuan-xie/ ECCV24_NeST."

"Prior works have addressed the problem of driver intention prediction (DIP) by identifying maneuvers after their onset. On the other hand, early anticipation is equally important in scenarios that demand a preemptive response before a maneuver begins. However, there is no prior work aimed at addressing the problem of driver action anticipation before the onset of the maneuver, limiting the ability of the advanced driver assistance system (ADAS) for early maneuver anticipation. In this work, we introduce Anticipating Driving Maneuvers (ADM), a new task that enables driver action anticipation before the onset of the maneuver. To initiate research in ADM task, we curate Driving Action Anticipation Dataset, DAAD, that is multi-view : in- and out-cabin views in dense and heterogeneous scenarios, and multimodal : egocentric view and gaze information. The dataset captures sequences both before the initiation and during the execution of a maneuver. During dataset collection, we also ensure to capture wide diversity in traffic scenarios, weather and illumination, and driveway conditions. Next, we propose a strong baseline based on a transformer architecture to effectively model multiple views and modalities over longer video lengths. We benchmark the existing DIP methods on DAAD and related datasets. Finally, we perform an ablation study showing the effectiveness of multiple views and modalities in maneuver anticipation. Project Page: https://cvit.iiit.ac. in/research/projects/cvit-projects/daad."

"In this work, we tackle the challenge of enhancing the realism and expressiveness in talking head video generation by focusing on the dynamic and nuanced relationship between audio cues and facial movements. We identify the limitations of traditional techniques that often fail to capture the full spectrum of human expressions and the uniqueness of individual facial styles. To address these issues, we propose EMO, a novel framework that utilizes a direct audio-to-video synthesis approach, bypassing the need for intermediate 3D models or facial landmarks. Our method ensures seamless frame transitions and consistent identity preservation throughout the video, resulting in highly expressive and lifelike animations. Experimental results demonstrate that EMO is able to produce not only convincing speaking videos but also singing videos in various styles, significantly outperforming existing state-of-the-art methodologies in terms of expressiveness and realism."

"Road surface reconstruction plays a vital role in autonomous driving systems, enabling road lane perception and high-precision mapping. Recently, neural implicit encoding has achieved remarkable results in scene representation, particularly in the realistic rendering of scene textures. However, it faces challenges in directly representing geometric information for large-scale scenes. To address this, we propose EMIE-MAP, a novel method for large-scale road surface reconstruction based on explicit mesh and implicit encoding. The road geometry is represented using explicit mesh, where each vertex stores implicit encoding representing the color and semantic information. To overcome the difficulty in optimizing road elevation, we introduce a trajectory-based elevation initialization and an elevation residual learning method. Additionally, by employing shared implicit encoding and multi-camera color decoding, we achieve separate modeling of scene physical properties and camera characteristics, allowing surround-view reconstruction compatible with different camera models. Our method achieves remarkable road surface reconstruction performance in open source datasets and a variety of real-world challenging scenarios."

"Brain-inspired computer architecture facilitates low-power, low-latency deep neural network inference for embedded AI applications. The hardware performance crucially hinges on the quantity of non-zero activations (i.e., events) during inference. Thus, we propose a novel event suppression method, dubbed ELSE, which enhances inference Efficiency via Line-based Sparsity Exploration. Specifically, it exploits spatial correlation between adjacent lines in activation maps to reduce network events. ELSE reduces event-triggered computations by 3.14∼6.49× for object detection and by 2.43∼5.75× for pose estimation across various network architectures compared to conventional processing. Additionally, we show that combining ELSE with other event suppression methods can either significantly enhance computation savings for spatial suppression or reduce state memory footprint by > 2× for temporal suppression. The latter alleviates the challenge of temporal execution exceeding the resource constraints of real-world embedded platforms. These results highlight ELSE’s significant event suppression ability and its capacity to deliver complementary performance enhancements for SOTA methods."

"Scanned point clouds are often sparse and incomplete due to the limited field of view of sensing devices, significantly impeding the performance of downstream applications. Therefore, the task of point cloud completion is introduced to obtain a dense and complete point cloud from the incomplete input. The fundamental challenges in tackling this task involve accurately inferring the missing shapes and upsampling them to higher densities. In this paper, we propose a novel approach to address this task, which formulates the completion task as a dual problem: a feature-wise extrapolation problem where the shape features of the partial point cloud are extrapolated to outlier regions for the recovery of missing portions, and a feature-wise interpolation problem to achieve point cloud upsampling. Based on these, we propose the EINet, a new point cloud completion paradigm with a novel Extrapolation module that can predict the missing shapes for the partial point cloud and a newly designed Interpolation module to upsample the point cloud. Extensive evaluation results demonstrate that EINet achieves compelling performance compared to previous state-of-the-art methods. The code is open-sourced at https://github.com/corecai163/EINet."

"[height=4.8cm]figures/teaserc lic2020.pdf Figure 1: Distortion-perception comparison (top left is best) We introduce EGIC, an enhanced generative image compression method that allows traversing the distortion-perception curve efficiently from a single model. EGIC is based on two novel building blocks: i) OASIS-C, a conditional pre-trained semantic segmentation-guided discriminator, which provides both spatially and semantically-aware gradient feedback to the generator, conditioned on the latent image distribution, and ii) Output Residual Prediction (ORP), a retrofit solution for multi-realism image compression that allows control over the synthesis process by adjusting the impact of the residual between an MSE-optimized and GAN-optimized decoder output on the GAN-based reconstruction. Together, EGIC forms a powerful codec, outperforming state-of-the-art diffusion and GAN-based methods (, HiFiC, MS-ILLM, and DIRAC-100), while performing almost on par with VTM-20.0 on the distortion end. EGIC is simple to implement, very lightweight, and provides excellent interpolation characteristics, which makes it a promising candidate for practical applications targeting the low bit range."

"Currently, there is relatively limited research on the background activity noise of event cameras in different brightness conditions, and the relevant real-world datasets are extremely scarce. This limitation contributes to the lack of robustness in existing event denoising algorithms when applied in practical scenarios. This paper addresses this gap by collecting and analyzing background activity noise from the DAVIS346 event camera under different illumination conditions. We introduce the first real-world event denoising dataset, ED24, encompassing 21 noise levels and noise annotations. Furthermore, we propose EDformer, an innovative event-by-event denoising model based on transformer. This model excels in event denoising by learning the spatiotemporal correlations among events across varied noise levels. In comparison to existing denoising algorithms, the proposed EDformer achieves state-of-the-art performance in denoising accuracy, including open-source datasets and datasets captured in practical scenarios with low-light intensity requirements such as zebrafish blood vessels imaging."

"Achieving disentangled control over multiple facial motions and accommodating diverse input modalities greatly enhances the application and entertainment of the talking head generation. This necessitates a deep exploration of the decoupling space for facial features, ensuring that they a) operate independently without mutual interference and b) can be preserved to share with different modal inputs—both aspects often neglected in existing methods. To address this gap, this paper proposes a novel Efficient Disentanglement framework for Talking head generation (EDTalk). Our framework enables individual manipulation of mouth shape, head pose, and emotional expression, conditioned on video or audio inputs. Specifically, we employ three lightweight modules to decompose the facial dynamics into three distinct latent spaces representing mouth, pose, and expression, respectively. Each space is characterized by a set of learnable bases whose linear combinations define specific motions. To ensure independence and accelerate training, we enforce orthogonality among bases and devise an efficient training strategy to allocate motion responsibilities to each space without relying on external knowledge. The learned bases are then stored in corresponding banks, enabling shared visual priors with audio input. Furthermore, considering the properties of each space, we propose an Audio-to-Motion module for audio-driven talking head synthesis. Experiments are conducted to demonstrate the effectiveness of EDTalk. The code and pretrained models are released at: https://tanshuai0219.github.io/EDTalk/"

"Exemplar-guided image translation, synthesizing photo-realistic images that conform to both structural control and style exemplars, is attracting attention due to its ability to enhance user control over style manipulation. Previous methodologies have predominantly depended on establishing dense correspondences across cross-domain inputs. Despite these efforts, they incur quadratic memory and computational costs for establishing dense correspondence, resulting in limited versatility and performance degradation. In this paper, we propose a novel approach termed Exemplar-guided Image Translation with Brownian-Bridge Diffusion Models (EBDM). Our method formulates the task as a stochastic Brownian bridge process, a diffusion process with a fixed initial point as structure control and translates into the corresponding photo-realistic image while being conditioned solely on the given exemplar image. To efficiently guide the diffusion process toward the style of exemplar, we delineate three pivotal components: the Global Encoder, the Exemplar Network, and the Exemplar Attention Module to incorporate global and detailed texture information from exemplar images. Leveraging Bridge diffusion, the network can translate images from structure control while exclusively conditioned on the exemplar style, leading to more robust training and inference processes. We illustrate the superiority of our method over competing approaches through comprehensive benchmark evaluations and visual results."

"Event cameras, with their high dynamic range and temporal resolution, are ideally suited for object detection in scenarios with motion blur and challenging lighting conditions. However, while most existing approaches prioritize optimizing spatiotemporal representations with advanced detection backbones and early aggregation functions, the crucial issue of adaptive event sampling remains largely unaddressed. Spiking Neural Networks (SNNs), operating on an event-driven paradigm, align closely with the behavior of an ideal temporal event sampler. Motivated by this, we propose a novel adaptive sampling module that leverages recurrent convolutional SNNs enhanced with temporal memory, facilitating a fully end-to-end learnable framework for event-based detection. Additionally, we introduce Residual Potential Dropout (RPD) and Spike-Aware Training (SAT) to regulate potential distribution and address performance degradation encountered in spike-based sampling modules. Empirical evaluation on neuromorphic detection datasets demonstrates that our approach outperforms existing state-of-the-art spike-based methods with significantly fewer parameters and time steps. For instance, our method yields a 4.4% mAP improvement on the Gen1 dataset, while requiring 38% fewer parameters and only three time steps. Moreover, the applicability and effectiveness of our adaptive sampling methodology extend beyond SNNs, as demonstrated through further validation on conventional non-spiking models. Code is available at Github."

"Recently, 3D Gaussian splatting (3D-GS) has gained popularity in novel-view scene synthesis. It addresses the challenges of lengthy training times and slow rendering speeds associated with Neural Radiance Fields (NeRFs). Through rapid, differentiable rasterization of 3D Gaussians, 3D-GS achieves real-time rendering and accelerated training. They, however, demand substantial memory resources for both training and storage, as they require millions of Gaussians in their point cloud representation for each scene. We present a technique utilizing quantized embeddings to significantly reduce per-point memory storage requirements and a coarse-to-fine training strategy for a faster and more stable optimization of the Gaussian point clouds. Our approach develops a pruning stage which results in scene representations with fewer Gaussians, leading to faster training times and rendering speeds for real-time rendering of high resolution scenes. We reduce storage memory by more than an order of magnitude all while preserving the reconstruction quality. We validate the effectiveness of our approach on a variety of datasets and scenes preserving the visual quality while consuming 10-20× less memory and faster training/inference speed. Code is available here."

"Scene text segmentation aims at cropping texts from scene images, which is usually used to help generative models edit or remove texts. The existing text segmentation methods tend to involve various text-related supervisions for better performance. However, most of them ignore the importance of text edges, which are significant for downstream applications. In this paper, we propose Edge-Aware Transformers, termed EAFormer, to segment texts more accurately, especially at the edge of texts. Specifically, we first design a text edge extractor to detect edges and filter out edges of non-text areas. Then, we propose an edge-guided encoder to make the model focus more on text edges. Finally, an MLP-based decoder is employed to predict text masks. We have conducted extensive experiments on commonly-used benchmarks to verify the effectiveness of EAFormer. The experimental results demonstrate that the proposed method can perform better than previous methods, especially on the segmentation of text edges. Considering that the annotations of several benchmarks (e.g., COCO TS and MLT S) are not accurate enough to fairly evaluate our methods, we have relabeled these datasets. Through experiments, we observe that our method can achieve a higher performance improvement when more accurate annotations are used for training. The code and datasets are available at bluehttps://hyangyu.github.io/EAFormer/."

"Understanding the content of events occurring in the video and their inherent temporal logic is crucial for video-text retrieval. However, web-crawled pre-training datasets often lack sufficient event information, and the widely adopted video-level cross-modal contrastive learning also struggles to capture detailed and complex video-text event alignment. To address these challenges, we make improvements from both data and model perspectives. In terms of pre-training data, we focus on supplementing the missing specific event content and event temporal transitions with the proposed event augmentation strategies. Based on the event-augmented data, we construct a novel Event-Aware Video-Text Retrieval model, , EA-VTR, which achieves powerful video-text retrieval ability through superior video event awareness. EA-VTR can efficiently encode frame-level and video-level visual representations simultaneously, enabling detailed event content and complex event temporal cross-modal alignment, ultimately enhancing the comprehensive understanding of video events. Our method not only significantly outperforms existing approaches on multiple datasets for Text-to-Video Retrieval and Video Action Recognition tasks, but also demonstrates superior event content perceive ability on Multi-event Video-Text Retrieval and Video Moment Retrieval tasks, as well as outstanding event temporal logic understanding ability on Test of Time task."

"Accurately estimating energy expenditure (EE) is crucial for optimizing athletic training, monitoring daily activity levels, and preventing sports-related injuries. Estimating energy expenditure based on video (E3 V) is an appealing research direction. This paper introduces E3V-K5, an authentic dataset of sports videos that significantly enhances the accuracy of EE estimation. The dataset comprises 16,526 video clips from various categories and intensity of sports with continuous calorie readings obtained from the COSMED K5 indirect calorimeter, recognized as the most reliable standard in sports research. Augmented with the heart rate and physical attributes of each subject, the volume, diversity, and authenticity of E3V-K5 surpass all previous video datasets in E3 V, making E3V-K5 a cornerstone in this field and facilitating future research. Furthermore, we propose E3SFormer, a novel approach specifically designed for the E3V-K5 dataset, focusing on EE estimation using human skeleton data. E3SFormer consists of two Transformer branches for simultaneous action recognition and EE regression. The attention of joints from the action recognition branch is utilized in assisting the EE regression branch. Extensive experimentation validates E3SFormer’s effectiveness, demonstrating its superior performance to existing skeleton-based action recognition models. Our dataset and code are publicly available at https://github.com/zsxm1998/E3V."

"Spatio-temporal video grounding aims to localize the spatio-temporal tube in a video according to the given language query. To eliminate the annotation costs, we make a first exploration to tackle spatio-temporal video grounding in a zero-shot manner. Our method dispenses with the need for any training videos or annotations; instead, it localizes the target object by leveraging pre-trained vision-language models and optimizing within the video and text query during the test time. To enable spatio-temporal comprehension, we introduce a multimodal modulation that integrates the spatio-temporal context into both visual and textual representation. On the visual side, we devise a context-based visual modulation that enhances the visual representation by propagation and aggregation of the contextual semantics. Concurrently, on the textual front, we propose a prototype-based textual modulation to refine the textual representations using visual prototypes, effectively mitigating the cross-modal discrepancy. In addition, to overcome the interleaved spatio-temporal dilemma, we propose an expectation maximization (EM) framework to optimize the process of temporal relevance estimation and spatial region identification in an alternating way. Comprehensive experiments validate that our zero-shot approach achieves superior performance in comparison to several state-of-the-art methods with stronger supervision. The code is available at https://github.com/baopj/E3M."

"Stories and emotions in movies emerge through the effect of well-thought-out directing decisions, in particular camera placement and movement over time. Crafting compelling camera trajectories remains a complex iterative process, even for skilful artists. To tackle this, in this paper, we propose a dataset called the Exceptional Trajectories (E.T.) with camera trajectories along with character information and textual captions encompassing descriptions of both camera and character. To our knowledge, this is the first dataset of its kind. To show the potential applications of the E.T. dataset, we propose a diffusion-based approach, named Director, which generates complex camera trajectories from textual captions that describe the relation and synchronisation between the camera and characters. To ensure robust and accurate evaluations, we train on the E.T. dataset CLaTr, a Contrastive Language-Trajectory embedding for evaluation metrics. We posit that our proposed dataset and method significantly advance the democratization of cinematography, making it more accessible to common users."

"CNNs are increasingly deployed across different hardware, dynamic environments, and low-power embedded devices. This has led to the design and training of CNN architectures with the goal of maximizing accuracy subject to such variable deployment constraints. As the number of deployment scenarios grows, there is a need to find scalable solutions to design and train specialized CNNs. Once-for-all training has emerged as a scalable approach that jointly co-trains many models (subnets) at once with a constant training cost and finds specialized CNNs later. The scalability is achieved by training the full model and simultaneously reducing it to smaller subnets that share model weights (weight-shared shrinking). However, existing once-for-all training approaches incur huge training costs reaching 1200 GPU hours. We argue this is because they either start the process of shrinking the full model too early or too late. Hence, we propose Delayed ϵ-Shrinking () that starts the process of shrinking the full model when it is partially trained (∼ 50%), which leads to training cost improvement and better in-place knowledge distillation to smaller models. The proposed approach also consists of novel heuristics that dynamically adjust subnet learning rates incrementally (ϵ), leading to improved weight-shared knowledge distillation from larger to smaller subnets as well. As a result, outperforms state-of-the-art once-for-all training techniques across different datasets including CIFAR10/100, ImageNet-100, and ImageNet-1k on accuracy and cost. It achieves 1.83% higher ImageNet-1k top1 accuracy or the same accuracy with 1.3x reduction in FLOPs and 2.5x drop in training cost (GPU*hrs). Code is released at https://github.com/gatech-sysml/deps."

"This paper explores the problem of reconstructing temporally consistent surfaces from a 3D point cloud sequence without correspondence. To address this challenging task, we propose DynoSurf, an unsupervised learning framework integrating a template surface representation with a learnable deformation field. Specifically, we design a coarse-to-fine strategy for learning the template surface based on the deformable tetrahedron representation. Furthermore, we propose a learnable deformation representation based on the learnable control points and blending weights, which can deform the template surface non-rigidly while maintaining the consistency of the local shape. Experimental results demonstrate the significant superiority of DynoSurf over current state-of-the-art approaches, showcasing its potential as a powerful tool for dynamic mesh reconstruction. The code is publicly available at https://github.com/yaoyx689/DynoSurf."