论文检索

Ondrej Tybl, Lukas Neumann

Deep learning has revolutionized computer vision, but it achieved its tremendous success using deep network architectures which are mostly hand-crafted and therefore likely suboptimal. Neural Architecture Search (NAS) aims to bridge this gap by following a well-defined optimization paradigm which systematically looks for the best architecture, given objective criterion such as maximal classification accuracy. The main limitation of NAS is however its astronomical computational cost, as it typically requires training each candidate network architecture from scratch.In this paper, we aim to alleviate this limitation by proposing a novel training-free proxy for image classification accuracy based on Fisher Information. The proposed proxy has a strong theoretical background in statistics and it allows estimating expected image classification accuracy of a given deep network without training the network, thus significantly reducing computational cost of standard NAS algorithms. Our training-free proxy achieves state-of-the-art results on three public datasets and in two search spaces, both when evaluated using previously proposed metrics, as well as using a new metric that we propose which we demonstrate is more informative for practical NAS applications. The source code is publicly available.

Wei Wu, Xi Guo, Weixuan Tang, Tingxuan Huang, Chiyu Wang, Chenjing Ding

Recent advancements in generative models offer promising solutions for synthesizing realistic driving videos, aiding in training autonomous driving perception models. However, existing methods often struggle with high-resolution multi-view generation, mainly due to the significant memory and computational overhead caused by simultaneously inputting multi-view videos into denoising diffusion models.In this paper, we propose a driving video generation framework based on multi-view feature fusion named DriveScape for multi-view 3D condition-guided video generation. We introduce a Bi-Directional Modulated Transformer (BiMoT) module to encode, fuse and inject multi-view features along with various 3D road structures and objects, which enables high-resolution multi-view generation. Consequently, our approach allows precise control over video generation, greatly enhancing realism and providing a robust solution for creating high-quality, multi-view driving videos.Our framework achieves state-of-the-art results on the nuScenes dataset, demonstrating impressive generative quality metrics with an FID score of 8.34 and an FVD score of 76.39, as well as superior performance across various perception tasks. This lays the foundation for more accurate environment simulation in autonomous driving. We plan to make our code and pre-trained model publicly available.Please refer to index.html webpage in the supplementary materials for more visualization results.

Yuanqi Li, Jingcheng Huang, Hongshen Wang, Peiyuan Lv, Yansong Liu, Jiuming Zheng, Jie Guo, Yanwen Guo

The proliferation of Light Detection and Ranging (LiDAR) technology has facilitated the acquisition of three-dimensional point clouds, which are integral to applications in VR, AR, and Digital Twin. Oriented normals, critical for 3D reconstruction and scene analysis, cannot be directly extracted from scenes using LiDAR due to its operational principles. Previous traditional or learning-based methods are prone to inaccuracies due to uneven distribution and noise due to the dependence on local geometry features. This paper addresses the challenge of estimating oriented point normals by introducing a point cloud normal estimation framework via hybrid angular and Euclidean distance encoding (HAE). Our method overcomes the limitations of local geometric information by combining angular and Euclidean spaces to extract features from both point cloud coordinates and light rays, leading to more accurate normal estimation. The core of our network consists of an angular distance encoding module, which leverages both ray directions and point coordinates for unoriented normal refinement, and a ray feature fusion module for normal orientation, that is robust to noise. We also provide a point cloud dataset with ground truth normals, generated a virtual scanner, which reflects real scanning distributions and noise profiles.

Qingtao Yu, Jaskirat Singh, Zhaoyuan Yang, Peter Henry Tu, Jing Zhang, Hongdong Li, Richard Hartley, Dylan Campbell

Diffusion models indirectly estimate the probability density over a data space, which can be used to study its structure. In this work, we show that geodesics can be computed in diffusion latent space, where the norm induced by the spatially-varying inner product is inversely proportional to the probability density. In this formulation, a path that traverses a high density (that is, probable) region of image latent space is shorter than the equivalent path through a low density region. We present algorithms for solving the associated initial and boundary value problems and show how to compute the probability density along the path and the geodesic distance between two points. Using these techniques, we analyze how closely video clips approximate geodesics in a pre-trained image diffusion space. Finally, we demonstrate how these techniques can be applied to training-free image sequence interpolation and extrapolation, given a pre-trained image diffusion model.

Ji Du, Fangwei Hao, Mingyang Yu, Desheng Kong, Jiesheng Wu, Bin Wang, Jing Xu, Ping Li

Camouflaged Object Detection (COD) seeks to distinguish objects from their highly similar backgrounds. Existing work has essentially focused on isolating camouflaged objects from the environment, demonstrating ever-improving performance but at the cost of extensive annotations and complex optimizations. In this paper, we diverge from this paradigm and shift the lens to isolating the salient environment from the camouflaged object. We introduce EASE, an Environment-Aware unSupErvised COD framework that identifies the environment by referencing an environment prototype library and detects camouflaged objects by inverting the retrieved environmental features. Specifically, our approach (DiffPro) uses large multimodal models, diffusion models, and vision-foundation models to construct the environment prototype library. To retrieve environments from the library and refrain from confusing foreground and background, we incorporate three retrieval schemes: Kernel Density Estimation-based Adaptive Threshold (KDE-AT), Global-to-Local pixel-level retrieval (G2L), and Self-Retrieval (SR). Our experiments demonstrate significant improvements over current unsupervised methods, with EASE achieving an average gain of over 10% on the COD10K dataset. When integrated with SAM, EASE surpasses prompt-based segmentation approaches and performs competitively with state-of-the-art fully-supervised methods. Code is available at https://github.com/xiaohainku/EASE.

Xuesong Chen, Linjiang Huang, Tao Ma, Rongyao Fang, Shaoshuai Shi, Hongsheng Li

The integration of Vision-Language Models (VLMs) into autonomous driving systems has shown promise in addressing key challenges such as learning complexity, interpretability, and common-sense reasoning. However, existing approaches often struggle with efficient integration and real-time decision-making due to computational demands. In this paper, we introduce SOLVE, an innovative framework that synergizes VLMs with end-to-end (E2E) models to enhance autonomous vehicle planning. Our approach emphasizes knowledge sharing at the feature level through a shared visual encoder, enabling comprehensive interaction between VLM and E2E components. We propose a Trajectory Chain-of-Thought (T-CoT) paradigm, which progressively refines trajectory predictions, reducing uncertainty and improving accuracy. By employing a temporal decoupling strategy, SOLVE achieves efficient asynchronous cooperation, aligning high-quality VLM outputs with E2E real-time performance. Evaluated on the nuScenes dataset, our method demonstrates significant improvements in trajectory prediction accuracy, paving the way for more robust and reliable autonomous driving systems.

Ting Liu, Siyuan Li

Recent advances in zero-shot referring image segmentation (RIS), driven by models such as the Segment Anything Model (SAM) and CLIP, have made substantial progress in aligning visual and textual information. Despite these successes, the extraction of precise and high-quality mask region representations remains a critical challenge, limiting the full potential of RIS tasks. In this paper, we introduce a training-free, hybrid global-local feature extraction approach that integrates detailed mask-specific features with contextual information from the surrounding area, enhancing mask region representation. To further strengthen alignment between mask regions and referring expressions, we propose a spatial guidance augmentation strategy that improves spatial coherence, which is essential for accurately localizing described areas. By incorporating multiple spatial cues, this approach facilitates more robust and precise referring segmentation. Extensive experiments on standard RIS benchmarks demonstrate that our method significantly outperforms existing zero-shot referring segmentation models, achieving substantial performance gains. We believe our approach advances RIS tasks and establishes a versatile framework for region-text alignment, offering broader implications for cross-modal understanding and interaction. The code will be publicly available.

Yifan Liu, Keyu Fan, Weihao Yu, Chenxin Li, Hao Lu, Yixuan Yuan

Recent advances in generalizable 3D Gaussian Splatting have demonstrated promising results in real-time high-fidelity rendering without per-scene optimization, yet existing approaches still struggle to handle unfamiliar visual content during inference on novel scenes due to limited generalizability. To address this challenge, we introduce MonoSplat, a novel framework that leverages rich visual priors from pre-trained monocular depth foundation models for robust Gaussian reconstruction. Our approach consists of two key components: a Mono-Multi Feature Adapter that transforms monocular features into multi-view representations, coupled with an Integrated Gaussian Prediction module that effectively fuses both feature types for precise Gaussian generation. Through the Adapter's lightweight attention mechanism, features are seamlessly aligned and aggregated across views while preserving valuable monocular priors, enabling the Prediction module to generate Gaussian primitives with accurate geometry and appearance. Through extensive experiments on diverse real-world datasets, we convincingly demonstrate that MonoSplat achieves superior reconstruction quality and generalization capability compared to existing methods while maintaining computational efficiency with minimal trainable parameters. Codes are available at \href https://github.com/CUHK-AIM-Group/MonoSplat https://github.com/CUHK-AIM-Group/MonoSplat .

Fanding Huang, Jingyan Jiang, Qinting Jiang, Hebei Li, Faisal Nadeem Khan, Zhi Wang

Recent vision-language models (VLMs) face significant challenges in test-time adaptation to novel domains. While cache-based methods show promise by leveraging historical information, they struggle with both caching unreliable feature-label pairs and indiscriminately using single-class information during querying, significantly compromising adaptation accuracy. To address these limitations, we propose COSMIC (\underline C lique-\underline O riented \underline S emantic \underline M ulti-space \underline I ntegration for \underline C LIP), a robust test-time adaptation framework that enhances adaptability through multi-granular, cross-modal semantic caching and graph-based querying mechanisms. Our framework introduces two key innovations: Dual Semantics Graph (DSG) and Clique Guided Hyper-class (CGH). The Dual Semantics Graph constructs complementary semantic spaces by incorporating textual features, coarse-grained CLIP features, and fine-grained DINOv2 features to capture rich semantic relationships. Building upon these dual graphs, the Clique Guided Hyper-class component leverages structured class relationships to enhance prediction robustness through correlated class selection. Extensive experiments demonstrate COSMIC's superior performance across multiple benchmarks, achieving significant improvements over state-of-the-art methods: 15.81% gain on out-of-distribution tasks and 5.33% on cross-domain generation with CLIP RN-50.

Jinhui Yi, Syed Talal Wasim, Yanan Luo, Muzammal Naseer, Juergen Gall

We present an efficient encoder-free approach for video-language understanding that achieves competitive performance while significantly reducing computational overhead. Current video-language models typically rely on heavyweight image encoders (300M-1.1B parameters) or video encoders (1B-1.4B parameters), creating a substantial computational burden when processing multi-frame videos. Our method introduces a novel Spatio-Temporal Alignment Block (STAB) that directly processes video inputs without requiring pre-trained encoders while using only 45M parameters for visual processing - at least a 6.5x reduction compared to traditional approaches. The STAB architecture combines Local Spatio-Temporal Encoding for fine-grained feature extraction, efficient spatial downsampling through learned attention and separate mechanisms for modeling frame-level and video-level relationships. Our model achieves comparable or superior performance to encoder-based approaches for open-ended video question answering on standard benchmarks. The fine-grained video question-answering evaluation demonstrates our model's effectiveness, outperforming the encoder-based approaches Video-ChatGPT and Video-LLaVA in key aspects like correctness and temporal understanding. Extensive ablation studies validate our architectural choices and demonstrate the effectiveness of our spatio-temporal modeling approach while achieving 3-4x faster processing speeds than previous methods. Code is available at https://jh-yi.github.io/Video-Panda.

Xinting Hu, Haoran Wang, Jan Eric Lenssen, Bernt Schiele

We introduce PersonaHOI, a training- and tuning-free framework that fuses a general StableDiffusion model with a personalized face diffusion (PFD) model to generate identity-consistent human-object interaction (HOI) images. While existing PFD models have advanced significantly, they often overemphasize facial features at the expense of full-body coherence, PersonaHOI introduces an additional StableDiffusion (SD) branch guided by HOI-oriented text inputs. By incorporating cross-attention constraints in the PFD branch and spatial merging at both latent and residual levels, PersonaHOI preserves personalized facial details while ensuring interactive non-facial regions. Experiments, validated by a novel interaction alignment metric, demonstrate the superior realism and scalability of PersonaHOI, establishing a new standard for practical personalized face with HOI generation. Code is available at https://github.com/JoyHuYY1412/PersonaHOI.

Yiming Qin, Zhu Xu, Yang Liu

Recent text-to-3D generation models have demonstrated remarkable abilities in producing high-quality 3D assets. Despite their great advancements, current models struggle to generate satisfying 3D objects with complex attributes. The difficulty for such complex attributes 3D generation arises from two aspects: (1) existing text-to-3D approaches typically lift text-to-image models to extract semantics via text encoders, while the text encoder exhibits limited comprehension ability for long descriptions, leading to deviated cross-attention focus, subsequently wrong attribute binding in generated results. (2) Objects with complex attributes often exhibit occlusion relationships between different parts, which demands a reasonable generation order as well as explicit disentanglement of different parts to enable structural coherent and attribute following results. Though some works introduce manual efforts to alleviate the above issues, their quality is unstable and highly reliant on manual information. To tackle above problems, we propose a automated method Hierarchical-Chain-of-Generation (HCoG). It leverages a large language model to analyze the long description, decomposes it into several blocks representing different object parts, and organizes an optimal generation order from in to out according to the occlusion relationship between parts, turning the whole generation process into a hierarchical chain. For optimization within each block, we first generate the necessary components coarsely, then bind their attributes precisely by target region localization and corresponding 3D Gaussian kernel optimization. For optimization between blocks, we introduce Gaussian Extension and Label Elimination to seamlessly generate new parts by extending new Gaussian kernels, re-assigning semantic labels, and eliminating unnecessary kernels, ensuring that only relevant parts are added without disrupting previously optimized parts. Experiments validate HCoG's effectiveness in handling complex attributes 3D assets and witnesses high-quality results. The code is available at https://github.com/Wakals/GASCOL.

Dongkun Zhang, Jiaming Liang, Ke Guo, Sha Lu, Qi Wang, Rong Xiong, Zhenwei Miao, Yue Wang

Trajectory planning is vital for autonomous driving, ensuring safe and efficient navigation in complex environments. While recent learning-based methods, particularly reinforcement learning (RL), have shown promise in specific scenarios, RL planners struggle with training inefficiencies and managing large-scale, real-world driving scenarios.In this paper, we introduce CarPlanner, a Consistent auto-regressive Planner that uses RL to generate multi-modal trajectories. The auto-regressive structure enables efficient large-scale RL training, while the incorporation of consistency ensures stable policy learning by maintaining coherent temporal consistency across time steps. Moreover, CarPlanner employs a generation-selection framework with an expert-guided reward function and an invariant-view module, simplifying RL training and enhancing policy performance.Extensive analysis demonstrates that our proposed RL framework effectively addresses the challenges of training efficiency and performance enhancement, positioning CarPlanner as a promising solution for trajectory planning in autonomous driving.To the best of our knowledge, we are the first to demonstrate that the RL-based planner can surpass both IL- and rule-based state-of-the-arts (SOTAs) on the challenging large-scale real-world dataset nuPlan. Our proposed CarPlanner surpasses RL-, IL-, and rule-based SOTA approaches within this demanding dataset.

Harsh Rangwani, Aishwarya Agarwal, Kuldeep Kulkarni, R. Venkatesh Babu, Srikrishna Karanam

Image composition and generation are processes where the artists need control over various parts of the generated images. However, the current state-of-the-art generation models, like Stable Diffusion, cannot handle fine-grained part-level attributes in the text prompts. Specifically, when additional attribute details are added to the base text prompt, these text-to-image models either generate an image vastly different from the image generated from the base prompt or ignore the attribute details. To mitigate these issues, we introduce PartComposer, a training-free method that enables image generation based on fine-grained part-level attributes specified for objects in the base text prompt. This allows more control for artists and enables novel object compositions by combining distinctive object parts. PartComposer first localizes object parts by denoising the object region from a specific diffusion process. This enables each part token to be localized to the right region. After obtaining part masks, we run a localized diffusion process in each part region based on fine-grained part attributes and combine them to produce the final image. All stages of PartComposer are based on repurposing a pre-trained diffusion model, which enables it to generalize across domains. We demonstrate the effectiveness of part-level control provided by PartComposer through qualitative visual examples and quantitative comparisons with contemporary baselines.

Jie Liu, Tiexin Qin, Hui Liu, Yilei Shi, Lichao Mou, Xiao Xiang Zhu, Shiqi Wang, Haoliang Li

In this work, we address the challenge of adaptive pediatric Left Ventricular Ejection Fraction (LVEF) assessment. While Test-time Training (TTT) approaches show promise for this task, they suffer from two significant limitations. Existing TTT works are primarily designed for classification tasks rather than continuous value regression, and they lack mechanisms to handle the quasi-periodic nature of cardiac signals. To tackle these issues, we propose a novel Quasi-Periodic Adaptive Regression with Test-time Training (Q-PART) framework. In the training stage, the proposed Quasi-Period Network decomposes the echocardiogram into periodic and aperiodic components within latent space by combining parameterized helix trajectories with Neural Controlled Differential Equations. During inference, our framework further employs a variance minimization strategy across image augmentations that simulate common quality issues in echocardiogram acquisition, along with differential adaptation rates for periodic and aperiodic components. Theoretical analysis is provided to demonstrate that our variance minimization objective effectively bounds the regression error under mild conditions. Furthermore, extensive experiments across three pediatric age groups demonstrate that Q-PART not only significantly outperforms existing approaches in pediatric LVEF prediction, but also exhibits strong clinical screening capability with high mAUROC scores (up to 0.9747) and maintains gender-fair performance across all metrics, validating its robustness and practical utility in pediatric echocardiography analysis.

Jack Saunders, Charlie Hewitt, Yanan Jian, Marek Kowalski, Tadas Baltrusaitis, Yiye Chen, Darren Cosker, Virginia Estellers, Nicholas Gydé, Vinay P. Namboodiri 等

Gaussian Splatting has changed the game for real-time photo-realistic rendering. One of the most popular applications of Gaussian Splatting is to create animatable avatars, known as Gaussian Avatars. Recent works have pushed the boundaries of quality and rendering efficiency but suffer from two main limitations. Either they require expensive multi-camera rigs to produce avatars with free-view rendering, or they can be trained with a single camera but only rendered at high quality from this fixed viewpoint. An ideal model would be trained using a short monocular video or image from available hardware, such as a webcam, and rendered from any view. To this end, we propose GASP: Gaussian Avatars with Synthetic Priors. To overcome the limitations of existing datasets, we exploit the pixel-perfect nature of synthetic data to train a Gaussian Avatar prior. By fitting this prior model to a single photo or videoand fine-tuning it, we get a high-quality Gaussian Avatar, which supports 360^\circ rendering. Our prior is only required for fitting, not inference, enabling real-time application. Through our method, we obtain high-quality, animatable Avatars from limited data which can be animated and rendered at 70fps on commercial hardware.

Dingcheng Zhen, Shunshun Yin, Shiyang Qin, Hou Yi, Ziwei Zhang, Siyuan Liu, Gan Qi, Ming Tao

In this work, we introduce the first autoregressive framework for real-time, audio-driven portrait animation, a.k.a, talking head. Beyond the challenge of lengthy animation times, a critical challenge in realistic talking head generation lies in preserving the natural movement of diverse body parts. To this end, we propose Teller, the first streaming audio-driven protrait animation framework with autoregressive motion generation. Specifically, Teller first decomposes facial and body detail animation into two components: Facial Motion Latent Generation (FMLG) based on an autoregressive transfromer, and movement authenticity refinement using a Efficient Temporal Module (ETM).Concretely, FMLG employs a Residual VQ model to map the facial motion latent from the implicit keypoint-based model into discrete motion tokens, which are then temporally sliced with audio embeddings. This enables the AR tranformer to learn real-time, stream-based mappings from audio to motion.Furthermore, Teller incorporate ETM to capture finer motion details. This module ensures the physical consistency of body parts and accessories, such as neck muscles and earrings, improving the realism of these movements.Teller is designed to be efficient, surpassing the inference speed of diffusion-based models (Hallo 20.93s vs. Teller 0.92s for one second video generation), and achieves a real-time streaming performance of up to 25 FPS. Extensive experiments demonstrate that our method outperforms recent audio-driven portrait animation models, especially in small movements, as validated by human evaluations with a significant margin in quality and realism.

Tao Tan, Qiulei Dong

Self-supervised 6D object pose estimation has received increasing attention in computer vision recently. Some typical works in literature attempt to translate the synthetic images with object pose labels generated by object CAD models into the real domain, and then use the translated data for training. However, their performance is generally limited, since (i) there still exists a domain gap between the translated images and the real images and (ii) the translated images can not sufficiently reflect occlusions that exist in many real images. To address these problems, we propose an Occlusion-Aware Neural Domain Adaptation method for self-supervised 6D object Pose estimation, called ONDA-Pose. The proposed method comprises three main steps. Firstly, by utilizing both the training real images without pose labels and a CAD model, we explore a CAD-like radiance field for rendering corresponding synthetic images that have similar textures to those generated by the CAD model. Then, a backbone pose estimator trained on the synthetic data is employed to provide initial pose estimations for the synthetic images rendered from the CAD-like radiance field, and the initial object poses are refined by a global object pose refiner to generate pseudo object pose labels. Finally, the backbone pose estimator is further self-supervised as the final pose estimator by jointly utilizing the real images with pseudo object pose labels and the synthetic images rendered from the CAD-like radiance field. Experimental results on three public datasets demonstrate that ONDA-Pose significantly outperforms the comparative state-of-the-art methods in most cases.

Qiang Hu, Zihan Zheng, Houqiang Zhong, Sihua Fu, Li Song, Xiaoyun Zhang, Guangtao Zhai, Yanfeng Wang

3D Gaussian Splatting (3DGS) has substantial potential for enabling photorealistic Free-Viewpoint Video (FVV) experiences. However, the vast number of Gaussians and their associated attributes poses significant challenges for storage and transmission. Existing methods typically handle dynamic 3DGS representation and compression separately, neglecting motion information and the rate-distortion (RD) trade-off during training, leading to performance degradation and increased model redundancy. To address this gap, we propose 4DGC, a novel rate-aware 4D Gaussian compression framework that significantly reduces storage size while maintaining superior RD performance for FVV. Specifically, 4DGC introduces a motion-aware dynamic Gaussian representation that utilizes a compact motion grid combined with sparse compensated Gaussians to exploit inter-frame similarities. This representation effectively handles large motions, preserving quality and reducing temporal redundancy. Furthermore, we present an end-to-end compression scheme that employs differentiable quantization and a tiny implicit entropy model to compress the motion grid and compensated Gaussians efficiently. The entire framework is jointly optimized using a rate-distortion trade-off. Extensive experiments demonstrate that 4DGC supports variable bitrates and consistently outperforms existing methods in RD performance across multiple datasets.

Zhiwei Dong, Ran Ding, Wei Li, Peng Zhang, Guobin Tang, Jia Guo

Latest trajectory prediction models in real-world autonomous driving systems often rely on online High-Definition (HD) maps to understand the road environment.However, online HD maps suffer from perception errors and feature redundancy, which hinder the performance of HD map-based trajectory prediction models.To address these issues, we introduce a framework, termed SD map-Augmented Trajectory Prediction (SATP), which leverages Standard-Definition (SD) maps to enhance HD map-based trajectory prediction models.First, we propose an SD-HD fusion approach to leverage SD maps across the diverse range of HD map-based trajectory prediction models. Second, we design a novel AlignNet to align the SD map with the HD map, further improving the effectiveness of SD maps. Experiments on real-world autonomous driving benchmarks demonstrate that SATP not only improves the performance of HD map-based trajectory prediction up to 25% in real-world scenarios using online HD maps but also brings benefits in ideal scenarios with ground-truth HD maps.