论文检索

Hao Chen, Ze Wang, Xiang Li, Ximeng Sun, Fangyi Chen, Jiang Liu, Jindong Wang, Bhiksha Raj, Zicheng Liu, Emad Barsoum

Efficient image tokenization with high compression ratios remains a critical challenge for training generative models.We present SoftVQ-VAE, a continuous image tokenizer that leverages soft categorical posteriors to aggregate multiple codewords into each latent token, substantially increasing the representation capacity of the latent space. When applied to Transformer-based architectures, our approach compresses 256x256 and 512x512 images using only 32 or 64 1-dimensional tokens.Not only does SoftVQ-VAE show consistent and high-quality reconstruction, more importantly, it also achieves state-of-the-art and significantly faster image generation results across different denoising-based generative models. Remarkably, SoftVQ-VAE improves inference throughput by up to 18x for generating 256x256 images and 55x for 512x512 images while achieving competitive FID scores of 1.78 and 2.21 for SiT-XL.It also improves the training efficiency of the generative models by reducing the number of training iterations by 2.3x while maintaining comparable performance. With its fully-differentiable design and semantic-rich latent space, our experiment demonstrates that SoftVQ-VQE achieves efficient tokenization without compromising generation quality, paving the way for more efficient generative models.Code and model will be released.

Lin Bie, Shouan Pan, Siqi Li, Yining Zhao, Yue Gao

Although the fusion of images and LiDAR point clouds is crucial to many applications in computer vision, the relative poses of cameras and LiDAR scanners are often unknown. The general registration pipeline first establishes correspondences and then performs pose estimation based on the generated matches. However, 2D-3D correspondences are inherently challenging to establish due to the large gap between images and LiDAR point clouds. To this end, we build a bridge to alleviate the 2D-3D gap and propose a practical framework to align LiDAR point clouds to the virtual points generated by images. In this way, the modality gap is converted to the domain gap of point clouds. Moreover, we propose a virtual-spherical representation and adaptive distribution sample module to narrow the domain gap between virtual and LiDAR point clouds. Then, we explore the reliable correspondence pattern consistency through a graph-based selection process. We improve the correspondence representation through a graph neural network. Experimental results demonstrate that our method outperforms the state-of-the-art methods by more than 10.77% and 12.53% performance on the KITTI Odometry and nuScenes datasets, respectively. The results demonstrate that our method can effectively solve non-synchronized random frame registration.

Mingzhen Huang, Fu-Jen Chu, Bugra Tekin, Kevin J. Liang, Haoyu Ma, Weiyao Wang, Xingyu Chen, Pierre Gleize, Hongfei Xue, Siwei Lyu 等

We introduce HOIGPT, a token-based generative method that unifies 3D hand-object interactions (HOI) perception and generation, offering the first comprehensive solution for captioning and generating high-quality 3D HOI sequences from a diverse range of conditional signals (e.g. text, objects, partial sequences). At its core, HOIGPT utilizes a large language model to predict the bidrectional transformation between HOI sequences and natural language descriptions. Given text inputs, HOIGPT generates a sequence of hand and object meshes; given (partial) HOI sequences, HOIGPT generates text descriptions and completes the sequences. To facilitate HOI understanding with a large language model, this paper introduces two key innovations: (1) a novel physically grounded HOI tokenizer, the hand-object decomposed VQ-VAE, for discretizing HOI sequences, and (2) a motion-aware language model trained to process and generate both text and HOI tokens. Extensive experiments demonstrate that HOIGPT sets new state-of-the-art performance on both text generation (+2.01% R Precision) and HOI generation (-2.56 FID) across multiple tasks and benchmarks.

Shuling Zhao, Fa-Ting Hong, Xiaoshui Huang, Dan Xu

Talking head video generation aims to generate a realistic talking head video that preserves the person's identity from a source image and the motion from a driving video. Despite the promising progress made in the field, it remains a challenging and critical problem to generate videos with accurate poses and fine-grained facial details simultaneously. Essentially, facial motion is often highly complex to model precisely, and the one-shot source face image cannot provide sufficient appearance guidance during generation due to dynamic pose changes. To tackle the problem, we propose to jointly learn motion and appearance codebooks and perform multi-scale codebook compensation to effectively refine both the facial motion conditions and appearance features for talking face image decoding. Specifically, the designed multi-scale motion and appearance codebooks are learned simultaneously in a unified framework to store representative global facial motion flow and appearance patterns. Then, we present a novel multi-scale motion and appearance compensation module, which utilizes a transformer-based codebook retrieval strategy to query complementary information from the two codebooks for joint motion and appearance compensation. The entire process produces motion flows of greater flexibility and appearance features with fewer distortions across different scales, resulting in a high-quality talking head video generation framework. Extensive experiments on various benchmarks validate the effectiveness of our approach and demonstrate superior generation results from both qualitative and quantitative perspectives when compared to state-of-the-art competitors. The project page is available at https://shaelynz.github.io/synergize-motion-appearance/.

Shaofei Huang, Rui Ling, Tianrui Hui, Hongyu Li, Xu Zhou, Shifeng Zhang, Si Liu, Richang Hong, Meng Wang

Audio-Visual Segmentation (AVS) aims to segment sound-producing objects in video frames based on the associated audio signal. Prevailing AVS methods typically adopt an audio-centric Transformer architecture, where object queries are derived from audio features. However, audio-centric Transformers suffer from two limitations: perception ambiguity caused by the mixed nature of audio, and weakened dense prediction ability due to visual detail loss. To address these limitations, we propose a new Vision-Centric Transformer (VCT) framework that leverages vision-derived queries to iteratively fetch corresponding audio and visual information, enabling queries to better distinguish between different sounding objects from mixed audio and accurately delineate their contours. Additionally, we also introduce a Prototype Prompted Query Generation (PPQG) module within our VCT framework to generate vision-derived queries that are both semantically aware and visually rich through audio prototype prompting and pixel context grouping, facilitating audio-visual information aggregation. Extensive experiments demonstrate that our VCT framework achieves new state-of-the-art performances on three subsets of the AVSBench dataset.

Daiqing Qi, Handong Zhao, Jing Shi, Simon Jenni, Yifei Fan, Franck Dernoncourt, Scott Cohen, Sheng Li

Photographer, curator, and former director of photography at the Museum of Modern Art (MoMA), John Szarkowski remarked in *William Eggleston's Guide*, "While editing directly from life, photographers have found it too difficult to see simultaneously both the blue and the sky." Szarkowski insightfully revealed a notable gap between general and aesthetic visual understanding: while the former emphasizes identifying factual elements in an image (the sky), the latter transcends mere object identification, viewing it instead as an aesthetic component--a pure expanse of blue, valued purely as a color block in visual aesthetics. Such distinctions between general visual understanding (detection, localization, etc.) and aesthetic perception (color, lighting, composition, etc.) pose a significant challenge for existing Multimodal Large Language Models (MLLMs) in comprehending image aesthetics, which is increasingly needed in real-world applications, from image recommendation and enhancement to generation. To fundamentally advance the aesthetic understanding of MLLMs, we introduce a novel dataset, PhotoCritique, derived from extensive discussions among professional photographers and enthusiasts, distinguished by its large scale, expertise, and diversity. Additionally, we propose a new model, PhotoEye, an MLLM featuring a language-guided multi-view vision fusion mechanism for understanding image aesthetics from multiple perspectives. Finally, we introduce PhotoBench, a comprehensive and professional benchmark for aesthetic visual understanding. Our model demonstrates significant advantages over both open-source and commercial models on existing benchmarks and PhotoBench.

Yujie Wang, Praneeth Chakravarthula, Baoquan Chen

3D Gaussian Splatting (3DGS) techniques have recently enabled high-quality 3D scene reconstruction and real-time novel view synthesis. These approaches, however, are limited by the pinhole camera model and lack effective modeling of defocus effects. Departing from this, we introduce DOF-- a new 3DGS-based framework with a finite-aperture camera model and explicit, differentiable defocus rendering, enabling it to function as a post-capture control tool. By training with multi-view images with moderate defocus blur, DOF-GS learns inherent camera characteristics and reconstructs sharp details of the underlying scene, particularly, enabling rendering of varying DOF effects through on-demand aperture and focal distance control, post-capture and optimization. Additionally, our framework extracts circle-of-confusion cues during optimization to identify in-focus regions in input views, enhancing the reconstructed 3D scene details. Experimental results demonstrate that DOF-GS supports post-capture refocusing, adjustable defocus and high-quality all-in-focus rendering, from multi-view images with uncalibrated defocus blur.

Youxin Pang, Ruizhi Shao, Jiajun Zhang, Hanzhang Tu, Yun Liu, Boyao Zhou, Hongwen Zhang, Yebin Liu

In this paper, we introduce ManiVideo, a novel method for generating consistent and temporally coherent bimanual hand-object manipulation videos from given motion sequences of hands and objects. The core idea of ManiVideo is the construction of a multi-layer occlusion (MLO) representation that learns 3D occlusion relationships from occlusion-free normal maps and occlusion confidence maps. By embedding the MLO structure into the UNet in two forms, the model enhances the 3D consistency of dexterous hand-object manipulation. To further achieve the generalizable grasping of objects, we integrate Objaverse, a large-scale 3D object dataset, to address the scarcity of video data, thereby facilitating the learning of extensive object consistency. Additionally, we propose an innovative training strategy that effectively integrates multiple datasets, supporting downstream tasks such as human-centric hand-object manipulation video generation. Through extensive experiments, we demonstrate that our approach not only achieves video generation with plausible hand-object interaction and generalizable objects, but also outperforms existing SOTA methods.

Mingzhen Sun, Weining Wang, Gen Li, Jiawei Liu, Jiahui Sun, Wanquan Feng, Shanshan Lao, Siyu Zhou, Qian He, Jing Liu

The task of video generation requires synthesizing visually realistic and temporally coherent video frames. Existing methods primarily use asynchronous auto-regressive models or synchronous diffusion models to address this challenge. However, asynchronous auto-regressive models often suffer from inconsistencies between training and inference, leading to issues such as error accumulation, while synchronous diffusion models are limited by their reliance on rigid sequence length. To address these issues, we introduce Auto-Regressive Diffusion (AR-Diffusion), a novel model that combines the strengths of auto-regressive and diffusion models for flexible, asynchronous video generation. Specifically, our approach leverages diffusion to gradually corrupt video frames in both training and inference, reducing the discrepancy between these phases. Inspired by auto-regressive generation, we incorporate a non-decreasing constraint on the corruption timesteps of individual frames, ensuring that earlier frames remain clearer than subsequent ones. This setup, together with temporal causal attention, enables flexible generation of videos with varying lengths while preserving temporal coherence. In addition, we design two specialized timestep schedulers: the FoPP scheduler for balanced timestep sampling during training, and the AD scheduler for flexible timestep differences during inference, supporting both synchronous and asynchronous generation. Extensive experiments demonstrate the superiority of our proposed method, by achieving competitive and state-of-the-art results across four challenging benchmarks.

Jinrui Yang, Qing Liu, Yijun Li, Soo Ye Kim, Daniil Pakhomov, Mengwei Ren, Jianming Zhang, Zhe Lin, Cihang Xie, Yuyin Zhou

Recent advancements in large generative models, particularly diffusion-based methods, have significantly enhanced the capabilities of image editing. However, achieving precise control over image composition tasks remains a challenge. Layered representations, which allow for independent editing of image components, are essential for user-driven content creation, yet existing approaches often struggle to decompose image into plausible layers with accurately retained transparent visual effects such as shadows and reflections. We propose LayerDecomp, a generative framework for image layer decomposition which outputs photorealistic clean backgrounds and high-quality transparent foregrounds with faithfully preserved visual effects. To enable effective training, we first introduce a dataset preparation pipeline that automatically scales up simulated multi-layer data with synthesized visual effects. To further enhance real-world applicability, we supplement this simulated dataset with camera-captured images containing natural visual effects. Additionally, we propose a consistency loss which enforces the model to learn accurate representations for the transparent foreground layer when ground-truth annotations are not available. Our method achieves superior quality in layer decomposition, outperforming existing approaches in object removal and spatial editing tasks across several benchmarks and multiple user studies, unlocking various creative possibilities for layer-wise image editing.

Shengze Wang, Xueting Li, Chao Liu, Matthew Chan, Michael Stengel, Henry Fuchs, Shalini De Mello, Koki Nagano

Recent breakthroughs in single-image 3D portrait reconstruction have enabled telepresence systems to stream 3D portrait videos from a single camera in real-time, democratizing telepresence. However, per-frame 3D reconstruction exhibits temporal inconsistency and forgets the user's appearance. On the other hand, self-reenactment methods can render coherent 3D portraits by driving a 3D avatar built from a single reference image but fail to faithfully preserve the user's per-frame appearance (e.g., instantaneous facial expressions and lighting). As a result, neither of these two frameworks is an ideal solution for democratized 3D telepresence. In this work, we address this dilemma and propose a novel solution that maintains both coherent identity and dynamic per-frame appearance to enable the best possible realism. To this end, we propose a new fusion-based method that takes the best of both worlds by fusing a canonical 3D prior from a reference view with dynamic appearance from per-frame input views, producing temporally stable 3D videos with faithful reconstruction of the user's per-frame appearance. Trained only using synthetic data produced by an expression-conditioned 3D GAN, our encoder-based method achieves both state-of-the-art 3D reconstruction and temporal consistency on in-studio and in-the-wild datasets.

Jiahui Fu, Yue Gong, Luting Wang, Shifeng Zhang, Xu Zhou, Si Liu

Collaborative perception aims to address the constraint of single-agent perception by exchanging information among multiple agents. Previous works primarily focus on collaborative object detection, exploring compressed transmission and fusion prediction tailored to sparse object features. However, these strategies are not well-suited for dense features in collaborative BEV semantic segmentation. Therefore, we propose CoGMP, a novel Collaborative framework that leverages Generative Map Priors to achieve efficient compression and robust fusion. CoGMP introduces two key innovations: Element Format Feature Compression (EFFC) and Structure Guided Feature Fusion (SGFF). Specifically, EFFC leverages map element priors from codebook to encode BEV features as discrete element indices for transmitted information compression. Meanwhile, SGFF utilizes a diffusion model with structural priors to coherently integrate multi-agent features, thereby achieving consistent fusion predictions. Evaluations on the OPV2V dataset show that CoGMP achieves a 6.89/7.64 Road/Lane IoU improvement and a 32-fold reduction in communication volume.

Maximilian Rokuss, Yannick Kirchhoff, Seval Akbal, Balint Kovacs, Saikat Roy, Constantin Ulrich, Tassilo Wald, Lukas T. Rotkopf, Heinz-Peter Schlemmer, Klaus Maier-Hein

In this work, we present LesionLocator, a framework for zero-shot longitudinal lesion tracking and segmentation in 3D medical imaging, establishing the first end-to-end model capable of 4D tracking with dense spatial prompts. Our model leverages an extensive dataset of 23,262 annotated medical scans, as well as synthesized longitudinal data across diverse lesion types. The diversity and scale of our dataset significantly enhances model generalizability to real-world medical imaging challenges and addresses key limitations in longitudinal data availability. LesionLocator outperforms all existing promptable models in lesion segmentation by nearly 10 dice points, reaching human-level performance, and achieves state-of-the-art results in lesion tracking, with superior lesion retrieval and segmentation accuracy. LesionLocator not only sets a new benchmark in universal promptable lesion segmentation and automated longitudinal lesion tracking but also provides the first open-access solution of its kind, releasing our synthetic 4D dataset and model to the community, empowering future advancements in medical imaging. Code is available at: www.github.com/MIC-DKFZ/LesionLocator

Zhuoming Liu, Yiquan Li, Khoi Duc Nguyen, Yiwu Zhong, Yin Li

We present PAVE, a framework for adapting pre-trained video large language models (Video-LLMs) to downstream tasks that incorporate side-channel signals, such as audio, camera pose, or high frame rate videos. PAVE introduces a lightweight adaptation strategy called "patching", which adds a small number of parameters and operations to the base model without modifying its architecture or pre-trained weights. We demonstrate that PAVE effectively enhances pre-trained Video-LLMs with the cost of adding <1% additional FLOPs and parameters for diverse tasks, including audio-visual understanding, 3D reasoning, and multi-view video understanding, surpassing state-of-the-art task-specific models. Moreover, when applied to high frame rate videos, PAVE further improves video understanding, enhancing the performance of strong base models. Finally, our experiments show that our framework generalizes well across different Video-LLMs.

Mengmeng Wang, Zeyi Huang, Xiangjie Kong, Guojiang Shen, Guang Dai, Jingdong Wang, Yong Liu

Video action recognition involves interpreting both global context and specific details to accurately identify actions. While previous models are effective at capturing spatiotemporal features, they often lack a focused representation of key action details. To address this, we introduce \nameo, a framework designed for refining video action recognition through integrated global and local feature learning. Inspired by human visual cognition theory, our approach balances the focus on both broad contextual changes and action-specific details, minimizing the influence of irrelevant background noise. We first employ learnable action queries to selectively emphasize action-relevant regions without requiring region-specific labels. Next, these queries are learned by a local action streaming branch that enables progressive query propagation. Moreover, we introduce a parameter-free feature interaction mechanism for effective multi-scale interaction between global and local features with minimal additional overhead. Extensive experiments demonstrate that \name achieves state-of-the-art performance across multiple action recognition datasets, validating its effectiveness and robustness in handling action-relevant details.

Jiahao He, Keren Fu, Xiaohong Liu, Qijun Zhao

Existing salient object detection (SOD) models primarily resort to convolutional neural networks (CNNs) and Transformers. However, the limited receptive fields of CNNs and quadratic computational complexity of transformers both constrain the performance of current models on discovering attention-grabbing objects. The emerging state space model, namely Mamba, has demonstrated its potential to balance global receptive fields and computational complexity. Therefore, we propose a novel unified framework based on the pure Mamba architecture, dubbed saliency Mamba (Samba), to flexibly handle general SOD tasks, including RGB/RGB-D/RGB-T SOD, video SOD (VSOD), and RGB-D VSOD. Specifically, we rethink Mamba's scanning strategy from the perspective of SOD, and identify the importance of maintaining spatial continuity of salient patches within scanning sequences. Based on this, we propose a saliency-guided Mamba block (SGMB), incorporating a spatial neighboring scanning (SNS) algorithm to preserve spatial continuity of salient patches. Additionally, we propose a context-aware upsampling (CAU) method to promote hierarchical feature alignment and aggregations by modeling contextual dependencies. Experimental results show that our Samba outperforms existing methods across five SOD tasks on 21 datasets with lower computational cost, confirming the superiority of introducing Mamba to the SOD areas. Our code is available at https://github.com/Jia-hao999/Samba.

Le Zhang, Qian Yang, Aishwarya Agrawal

How well are unimodal vision and language models aligned? While prior work has explored this question, their assessment methods do not directly translate to practical vision-language tasks. In this paper, we propose a direct assessment method, inspired by linear probing, to evaluate vision-language alignment. We identify that the degree of alignment of SSL vision models depends on their SSL training objective and find that clustering quality of SSL representations impacts alignment performance more than their linear separability. We then introduce Swift Alignment of Image and Language (SAIL), an efficient transfer learning framework that aligns pretrained unimodal vision and language models for downstream tasks. SAIL requires significantly less paired image-text data ( 6%) compared to models like CLIP, which are trained from scratch. It trains with a single A100 GPU in 5 hours and supports a batch size of up to 32,768. SAIL achieves 73.4% zero-shot accuracy on ImageNet (compared to CLIP's 72.7%) and excels in zero-shot retrieval, complex reasoning, and semantic segmentation. SAIL also enhances the language-compatibility of vision encoders, improving the performance of multimodal large language models. The full codebase and model weights are open-source: https://lezhang7.github.io/sail.github.io/

Beilin Chu, Xuan Xu, Xin Wang, Yufei Zhang, Weike You, Linna Zhou

The rapid advancement of diffusion models has significantly improved high-quality image generation, making generated content increasingly challenging to distinguish from real images and raising concerns about potential misuse. In this paper, we observe that diffusion models struggle to accurately reconstruct mid-band frequency information in real images, suggesting the limitation could serve as a cue for detecting diffusion model generated images. Motivated by this observation, we propose a novel method called Frequency-guIded Reconstruction Error (FIRE), which, to the best of our knowledge, is the first to investigate the influence of frequency decomposition on reconstruction error. FIRE assesses the variation in reconstruction error before and after the frequency decomposition, offering a robust method for identifying diffusion model generated images. Extensive experiments show that FIRE generalizes effectively to unseen diffusion models and maintains robustness against diverse perturbations.

Jiahao Shao, Yuanbo Yang, Hongyu Zhou, Youmin Zhang, Yujun Shen, Vitor Guizilini, Yue Wang, Matteo Poggi, Yiyi Liao

This work addresses the challenge of streamed video depth estimation, which expects not only per-frame accuracy but, more importantly, cross-frame consistency. We argue that sharing contextual information between frames or clips is pivotal in fostering temporal consistency. Therefore, we reformulate depth prediction into a conditional generation problem to provide contextual information within a clip and across clips. Specifically, we propose a consistent context-aware training and inference strategy for arbitrarily long videos to provide cross-clip context. We sample independent noise levels for each frame within a clip during training while using a sliding window strategy and initializing overlapping frames with previously predicted frames without adding noise. Moreover, we design an effective training strategy to provide context within a clip. Extensive experimental results validate our design choices and demonstrate the superiority of our approach, dubbed ChronoDepth. Project page: https://xdimlab.github.io/ChronoDepth/.

Chongjian Ge, Chenfeng Xu, Yuanfeng Ji, Chensheng Peng, Masayoshi Tomizuka, Ping Luo, Mingyu Ding, Varun Jampani, Wei Zhan

Recent breakthroughs in text-guided image generation have significantly advanced the field of 3D generation. While generating a single high-quality 3D object is now feasible, generating multiple objects with reasonable interactions within a 3D space, a.k.a. compositional 3D generation, presents substantial challenges. This paper introduces CompGS, a novel generative framework that employs 3D Gaussian Splatting (GS) for efficient, compositional text-to-3D content generation. To achieve this goal, two core designs are proposed: (1) 3D Gaussians Initialization with 2D compositionality: We transfer the well-established 2D compositionality to initialize the Gaussian parameters on an entity-by-entity basis, ensuring both consistent 3D priors for each entity and reasonable interactions among multiple entities; (2) Dynamic Optimization: We propose a dynamic strategy to optimize 3D Gaussians using Score Distillation Sampling (SDS) loss. CompGS first automatically decomposes 3D Gaussians into distinct entity parts, enabling optimization at both the entity and composition levels. Additionally, CompGS optimizes across objects of varying scales by dynamically adjusting the spatial parameters of each entity, enhancing the generation of fine-grained details, particularly in smaller entities. Qualitative comparisons and quantitative evaluations on T3Bench demonstrate the effectiveness of CompGS in generating compositional 3D objects with superior image quality and semantic alignment over existing methods. CompGS can also be easily extended to progressively adding 3D objects, facilitating complex scene generation. We hope CompGS will provide new insights to the compositional 3D generation.