论文检索

Meng Wang, Changqun Xia, Yuze Wang, Junyi Wang, Wantong Duan, Xinxiong Xie, Yue Qi

Recently, 3D Gaussian Splatting (3DGS) has revolutionized radiance field reconstruction, enabling efficient and high-fidelity novel view synthesis. However, seamless integration of both aerial and street view images to model urban scenes remains a significant challenge for 3DGS. This joint setting suffers from extreme view coverage disparity, complex multi-scale details, and imbalanced viewpoint distributions.In this work, we present Urban-GS, a novel framework built upon Gaussian Splatting for the compact unified reconstruction and high-fidelity rendering of urban scenes from both aerial and street views. Specifically, we first develop an Aerial-Street Joint Adaptive Densification method to resolve the densification conflicts arising from large view coverage disparity. We then introduce a Contribution-based Anchor Pruning strategy to effectively mitigate the storage overhead from capturing multi-scale scene details. Furthermore, we propose a Global-to-Local Optimization strategy to refine the reconstruction of under-optimized regions resulting from imbalanced view distributions. Experiments across diverse urban scene datasets demonstrate that Urban-GS significantly outperforms the state-of-the-art method in novel-view rendering quality, while simultaneously reducing storage overhead by an average of 41%.

Yujuan Zhang, Qing Li, Ziyu Li, Xiuxing Li, Zhuo Wang, Mengrui Xu, Xia Wu

Random frame-level data missing is a critical challenge in multimodal sentiment analysis. Existing methods are largely limited to passive completion via single-pass feedforward connections and static cross-modal fusion, which struggle to generate high-quality completed features. However, the brain is not a passive recipient of external information but a dynamic system for active perceptual inference. Its core lies in the dynamic nested recurrents formed by intra-cortical recurrent completion mechanisms and corticothalamic circuits, which iteratively perform perceptual inference. Inspired by this, we propose the Dynamic Nested Recurrent Network (DNRNet). It is the first to introduce recurrent inference into the data completion task, achieving a paradigm shift from passive completion to active perceptual inference. Its local recurrent loop simulates intra-cortical recurrent pattern completion to perform perceptual inference and generate local correction features. The global recurrent loop simulates the modulatory function of the thalamus, calculating modality confidence to dynamically weight and integrate cross-modal information, generating global correction features. The local and global correction features are fused to obtain the completion signal, which is then combined with the input features of the current iteration to serve as the input for the next iteration. Experiments on the MOSI, MOSEI, and SIMS datasets demonstrate that DNRNet achieves an average accuracy improvement of 1.5%-2.0% over baseline models across all missing rates, validating the superiority of the brain-inspired approach in complex missing data scenarios.

Jiasen Lu, Liangchen Song, Mingze Xu, Byeongjoo Ahn, Yanjun Wang, Chen Chen, Afshin Dehghan, Yinfei Yang

We present AToken, the first unified visual tokenizer that achieves both high-fidelity reconstruction and semantic understanding across images, videos, and 3D assets. Unlike existing tokenizers that specialize in either reconstruction or understanding for single modalities, AToken encodes these diverse visual inputs into a shared 4D latent space, unifying both tasks and modalities in a single framework. Specifically, we introduce a pure transformer architecture with 4D rotary position embeddings to process visual inputs of arbitrary resolutions and temporal durations. To ensure stable training, we introduce an adversarial-free training objective that combines perceptual and Gram matrix losses, achieving state-of-the-art reconstruction quality. By employing a progressive training curriculum, AToken gradually expands from single images, videos, and 3D, and supports both continuous and discrete latent tokens. AToken achieves 0.21 rFID with 82.2% ImageNet accuracy for images, 3.01 rFVD with 40.2% MSRVTT retrieval for videos, and 28.28 PSNR with 90.9% classification accuracy for 3D.. In downstream applications, AToken enables both visual generation tasks (e.g., image generation with continuous and discrete tokens, text-to-video generation, image-to-3D synthesis) and understanding tasks (e.g., multimodal LLMs), achieving competitive performance across all benchmarks. These results shed light on the next-generation multimodal AI systems built upon unified visual tokenization.

Shawn Huang, Brian Price, Yifei Fan, Bryan Morse

Automatic album organization has been studied extensively over the past decades due to significant progress in digital photography. Recent vision-language models (VLMs) have shown strong performance on multi-image understanding, making them natural candidates for automating album organization workflows. While VLMs' abilities in multi-image understanding have been widely studied, their performance on album organization remains underexplored. To bridge this gap, we introduce AlbumBench, the first comprehensive benchmark for automatic album organization. Specifically, we (1) define album organization tasks as photo selection for album-specific user objectives, photo rating according to how well user intents are fulfilled, and album-specific photo grouping given a user query which requires contextual understanding of the album; (2) establish AlbumBench, a benchmark dataset containing 27051 images across 641 albums with 5 annotations per image; and (3) evaluate mainstream open-source and proprietary VLMs on AlbumBench. We show that AlbumBench presents unique challenges compared to traditional multi-image understanding benchmarks due to its requirement for understanding album context and user intent. Our findings reveal a significant performance gap between open-source and proprietary VLMs on album organization tasks. Despite this gap, even the best-performing proprietary models sometimes struggle with tasks that humans find relatively easy. We hope that AlbumBench can serve as a foundation for unifying album organization research and motivate improvements in VLMs' performance on these tasks.

Simon Boeder, Fabian Gigengack, Simon Roesler, Holger Caesar, Benjamin Risse

Recent progress in self- and weakly supervised occupancy estimation has largely relied on 2D projection or rendering-based supervision, which suffers from geometric inconsistencies and severe depth bleeding.We thus introduce ShelfOcc, a vision-only method that overcomes these limitations without relying on LiDAR.ShelfOcc brings supervision into native 3D space by generating metrically consistent semantic voxel labels from video, enabling true 3D supervision without any additional sensors or manual 3D annotations.While recent vision-based 3D geometry foundation models provide a promising source of prior knowledge, they do not work out of the box as a prediction due to sparse or noisy and inconsistent geometry, especially in dynamic driving scenes.Our method introduces a dedicated framework that mitigates these issues by filtering and accumulating static geometry consistently across frames, handling dynamic content and propagating semantic information into a stable voxel representation.This data-centric shift in supervision for weakly/shelf-supervised occupancy estimation allows the use of essentially any SOTA occupancy model architecture without relying on LiDAR data.We argue that such high-quality supervision is essential for robust occupancy learning and constitutes an important complementary avenue to architectural innovation.On the Occ3D-nuScenes benchmark, ShelfOcc substantially outperforms all previous weakly/shelf-supervised methods (up to a 34% relative improvement), establishing a new data-driven direction for LiDAR-free 3D scene understanding.

Maisha Maliha, Dean F. Hougen

Vision Transformers often rely on spurious background correlations rather than foreground object features. While prior model pruning approaches focus solely on improving accuracy, they lack interpretability and fail to verify whether predictions are actually made by focusing on the main foreground object, providing no causal validation of which components drive spurious behavior. We introduce Causal Information Gain Mechanistic Attribution (CIGMA), a general framework for explaining the internal computation of Vision Transformers. CIGMA provides a mechanistic, information theoretic explanation by quantifying the importance of each attention head and determining whether it supports the main object or routes spurious background cues. It ranks attention heads by measuring object versus context reliance with Jensen Shannon based information gain computed from the model's full predictive distributions after two complementary edits, removing the object region and removing the surrounding context, which reveals a spurious subnet that carries background signals and a complementary set of evidence aligned heads. Evaluated on CIFAR-10, CIFAR-100, and Tiny-ImageNet across three VLM architectures (InternVL2-26B, LLaVA-1.6, LLaVA-1.5-13B), CIGMA improves accuracy by 7.6 to 24.8 percentage points over unmodified models while reducing background reliance by 79.5% to 88.1%, substantially outperforming all baselines, demonstrating that causal head-level interventions enable more effective spurious correlation mitigation than token pruning or retraining approaches.

Liyuan Zhu, Manjunath Narayana, Michal Stary, Will Hutchcroft, Gordon Wetzstein, Iro Armeni

We present GaussFusion, a novel approach for improving 3D Gaussian splatting (3DGS) reconstructions in the wild through geometry-informed video generation. GaussFusion mitigates common 3DGS artifacts, including floaters, flickering, and blur caused by camera pose errors, incomplete coverage, and noisy geometry initialization. Unlike prior RGB-based approaches limited to a single reconstruction pipeline, our method introduces a geometry-informed video-to-video generator that refines 3DGS renderings across both optimization-based and feed-forward methods. Given an existing reconstruction, we render a Gaussian primitive video buffer encoding depth, normals, opacity, and covariance, which the generator refines to produce temporally coherent, artifact-free frames. We further introduce an artifact synthesis pipeline that simulates diverse degradation patterns, ensuring robustness and generalization. GaussFusion achieves state-of-the-art performance on novel-view synthesis benchmarks, and an efficient variant runs in real time at 21 FPS while maintaining similar performance, enabling interactive 3D applications.

Minkyung Kwon, Jinhyeok Choi, Jiho Park, Seonghu Jeon, Jinhyuk Jang, Junyoung Seo, Minseop Kwak, Jin-Hwa Kim, Seungryong Kim

Multi-view diffusion models have recently emerged as a powerful paradigm for novel view synthesis, yet the underlying mechanism that enables their view consistency remains unclear. In this work, we first verify that the attention maps of these models acquire geometric correspondence throughout training, attending to the geometrically corresponding regions across reference and target views for view-consistent generation. However, this correspondence signal remains incomplete, with its accuracy degrading under large viewpoint changes. Building on these findings, we introduce CAMEO, a simple yet effective training technique that directly supervises attention maps using geometric correspondence to enhance both the training efficiency and generation quality of multi-view diffusion models. Notably, supervising a single attention layer is sufficient to guide the model toward learning precise correspondences, thereby preserving the geometry and structure of reference images, accelerating convergence, and improving novel view synthesis performance. CAMEO reduces the number of training iterations required for convergence by half while achieving superior performance at the same iteration counts. We further demonstrate that CAMEO is model-agnostic and can be applied to any multi-view diffusion model. Project page is available at https://cvlab-kaist.github.io/CAMEO/.

Zihao Luo, Shaohao Rui, Zhenyu Tang, Guotai Wang, Xiaosong Wang

Continual self-supervised learning (CSSL) in medical imaging trains a foundation model sequentially, alleviating the need for collecting multi-modal images for joint training and offering promising improvements in downstream performance while preserving data privacy. However, most existing methods still rely on replaying data from previous stages to prevent catastrophic forgetting, which compromises privacy and limits their applicability in real-world scenarios where data transfer across sites is often restricted. In this work, we propose InvCoSS, an inversion-driven continual self-supervised learning framework for medical multi-modal image pre-training. Specifically, after training on a previous task, InvCoSS inverts the pre-trained self-supervised model to generate synthetic images that approximate the original training distribution. These synthetic images are then combined with data from the new task for joint optimization, which effectively mitigates catastrophic forgetting while strictly adhering to the constraint of no access to previous real data. Furthermore, to improve the fidelity of synthetic images, we introduce a novel InvUNet with a multi-scale fusion architecture to restore both high- and low-frequency components of the inverted images. To enhance diversity and prevent mode collapse, we design a repulsive representation-learning mechanism that encourages a diverse feature space for synthetic images without class guidance. Extensive experiments across nine downstream tasks validate the effectiveness of InvCoSS, achieving performance comparable to or even superior to prior data-replay methods while significantly reducing storage requirements and eliminating data privacy constraints.

Mengmeng Wang, Dengyang Jiang, Liuzhuozheng Li, Yucheng Lin, Guojiang Shen, Xiangjie Kong, Yong Liu, Guang Dai, Jingdong Wang

Denoising-based diffusion transformers, despite their strong generation performance, suffer from inefficient training convergence. Existing methods addressing this issue, such as REPA (relying on external representation encoders) or SRA (requiring dual-model setups), inevitably incur heavy computational overhead during training due to external dependencies. To tackle these challenges, this paper proposes SRA 2, a lightweight intrinsic self-representation alignment framework for efficient diffusion training. SRA 2 leverages off-the-shelf pre-trained Variational Autoencoder (VAE) features: their reconstruction property ensures inherent encoding of visual priors like rich texture details, structural patterns, and basic semantic information. Specifically, SRA 2 aligns the intermediate latent features of diffusion transformers with VAE features via a lightweight projection layer, supervised by a feature alignment loss. This design accelerates training without extra representation encoders or dual-model maintenance, resulting in a simple yet effective pipeline. Extensive experiments demonstrate that SRA 2 improves both generation quality and training convergence speed compared to vanilla diffusion transformers, matches or outperforms state-of-the-art acceleration methods, and incurs merely 4% extra GFLOPs with zero additional cost for external guidance models.

Yuelin Zhang, Sijie Cheng, Chen Li, Zongzhao Li, Yuxin Huang, Yang Liu, Wenbing Huang

Accurately estimating task progress is critical for embodied agents to plan and execute long-horizon, multi-step tasks. Despite promising advances, existing Vision-Language Models (VLMs) based methods primarily leverage their video understanding capabilities, while neglecting their complex reasoning potential. Furthermore, processing long video trajectories with VLMs is computationally prohibitive for real-world deployment. To address these challenges, we propose the Recurrent Reasoning Vision-Language Model (\text R ^2VLM). Our model features a recurrent reasoning framework that processes local video snippets iteratively, maintaining a global context through an evolving Chain of Thought (CoT). This CoT explicitly records task decomposition, key steps, and their completion status, enabling the model to reason about complex temporal dependencies. This design avoids the high cost of processing long videos while preserving essential reasoning capabilities. We train \text R ^2VLM on large-scale, automatically generated datasets from ALFRED and Ego4D. Extensive experiments on progress estimation and downstream applications, including progress-enhanced policy learning, reward modeling for reinforcement learning, and proactive assistance, demonstrate that \text R ^2VLM achieves strong performance and generalization, achieving a new state-of-the-art in long-horizon task progress estimation. The models and benchmarks are publicly available at https://huggingface.co/collections/zhangyuelin/r2vlm.

Mengting Xu, Shi Gu, Peng Lin, De Ma, Huajin Tang, Qian Zheng, Gang Pan

Spiking Neural Networks (SNNs) have attracted increasing attention for their biologically inspired temporal dynamics. As their applications expand, understanding their robustness has become an important research focus. However, little is known about how the intrinsic temporal properties of SNNs affect robustness. In this work, we revisit SNN robustness from an information-theoretic perspective and reveal the pivotal role of temporal dynamics. We establish a theoretical link between robustness error and the mutual information (MI) between inputs and latent representations along the temporal dimension, grounded in the information bottleneck principle. Through an analysis of spike-based information transmission, we show that temporal dynamics inherently compress MI, thereby tightening the robustness error bound. Building on this insight, we propose a Temporal Mutual Information (TMI) regularizer that explicitly exploits temporal characteristics to enhance robustness. Extensive experiments on CIFAR-10, CIFAR-100, DVS-CIFAR10, Tiny-ImageNet, and ImageNet demonstrate that our method consistently improves SNN robustness across various architectures and attack settings.

Yunkai Yang, Yudong Zhang, Kunquan Zhang, Jinxiao Zhang, Xinying Chen, Haohuan Fu, Runmin Dong

With the rapid progress of controllable generation, training data synthesis has become a promising way to expand labeled datasets and alleviate manual annotation in remote sensing (RS). However, the complexity of semantic mask control and the uncertainty of sampling quality often limit the utility of synthetic data in downstream semantic segmentation tasks. To address these challenges, we propose a task-oriented data synthesis framework (TODSynth), including a Multimodal Diffusion Transformer (MM-DiT) with unified triple attention and a plug-and-play sampling strategy guided by task feedback. Built upon the powerful DiT-based generative foundation model, we systematically evaluate different control schemes, showing that a text-image-mask joint attention scheme combined with full fine-tuning of the image and mask branches significantly enhances the effectiveness of RS semantic segmentation data synthesis, particularly in few-shot and complex-scene scenarios. Furthermore, we propose a control-rectify flow matching (CRFM) method, which dynamically adjusts sampling directions guided by semantic loss during the early high-plasticity stage, mitigating the instability of generated images and bridging the gap between synthetic data and downstream segmentation tasks. Extensive experiments demonstrate that our approach consistently outperforms state-of-the-art controllable generation methods, producing more stable and task-oriented synthetic data for RS semantic segmentation.

Ting-Hsuan Chen, Ying-Huan Chen, Tao Tu, Jie-Ying Lee, Cho-Ying Wu, Fangzhou Lin, Hengyuan Zhang, David Paz, Xinyu Huang, Yuliang Guo 等

Generating complete digital twins from videos requires precise camera control, global scene coverage, and strict spatial-temporal consistency--constraints that remain challenging for perspective video generators due to their limited field of view (FoV). Their narrow FoV forces long or multi-view trajectories, amplifying cross-view inconsistency and temporal drift.We argue that 360deg video generation offers a natural solution: panoramic coverage simplifies trajectory design and provides strong global context for maintaining coherence. We introduce Pantheon360: Taming Digital Twin Generation via 3D-Aware 360deg Video Diffusion, a controllable 360deg video generation framework that synthesizes high-fidelity videos from sparse 360deg inputs. The key idea is an explicit 3D Cache, reconstructed from the input, which serves as a geometric scaffold for any user-defined camera path. This allows the diffusion model to focus on photorealistic texture refinement while the 3D Cache enforces global geometric consistency.Experiments show that Pantheon360 achieves superior visual quality and unmatched geometric coherence, enabling reliable and flexible 360deg scene generation for downstream simulation and digital-twin applications.

Chenhui Gou, Ziyu Ma, Zicheng Duan, Haoyu He, Feng Chen, Akide Liu, Bohan Zhuang, Jianfei Cai, Hamid Rezatofighi

Taking advantage of large-scale data and pretrained language models, Video Large Language Models (Video-LLMs) have shown strong capabilities in answering video questions. However, most existing efforts focus on improving performance, with limited attention to understanding their internal mechanisms. This paper aims to bridge this gap through a systematic empirical study. To interpret existing VideoLLMs, we adopt attention knockouts as our primary analytical tool and design three variants: Video Temporal Knockout, Video Spatial Knockout, and Language-to-Video Knockout. Then, we apply these three knockouts on different numbers of layers (window of layers). By carefully controlling the window of layers and types of knockouts, we provide two settings: a global setting and a fine-grained setting. Our study reveals three key findings: (1) Global setting indicates Video information extraction primarily occurs in early layers, forming a clear two-stage process--lower layers focus on perceptual encoding, while higher layers handle abstract reasoning; (2) In the fine-grained setting, certain intermediate layers exert an outsized impact on video question answering, acting as critical outliers, whereas most other layers contribute minimally; (3) In both settings, we observe that spatial-temporal modeling relies more on language-guided retrieval than on intra- and inter-frame self-attention among video tokens, despite the latter's high computational cost. Finally, we demonstrate that these insights can be leveraged to reduce attention computation in Video-LLMs. To our knowledge, this is the first work to systematically uncover how Video-LLMs internally process and understand video content, offering interpretability and efficiency perspectives for future research.

Gui Wang, Zehao Zhong, YongSong Zhou, Yudong Li, Ende Wu, Wooi Ping Cheah, Rong Qu, Jianfeng Ren, Linlin Shen

Despite significant progress in Multi-modal Large Language Models (MLLMs), their clinical reasoning capacity for multi-modal diagnosis remains largely unexamined. Current benchmarks, mostly single-modality data, can't evaluate progressive reasoning and cross-modal integration essential for clinical practice. We introduce the Cross-Modality Progressive Clinical Reasoning (X-PCR) benchmark, the first comprehensive evaluation of MLLMs through a complete ophthalmology diagnostic workflow, with two reasoning tasks: 1) a six-stage progressive reasoning chain spanning image quality assessment to clinical decision-making, and 2) a cross-modality reasoning task integrating six imaging modalities. The benchmark comprises 26,415 images and 177,868 expert-verified VQA pairs curated from 51 public datasets, covering 52 ophthalmic diseases. Evaluation of 21 MLLMs reveals critical gaps in progressive reasoning and cross-modal integration. Dataset and code: https://github.com/CVI-SZU/X-PCR.

Xingjian Bai, Guande He, Zhengqi Li, Eli Shechtman, Xun Huang, Zongze Wu

Causality--referring to temporal, uni-directional cause-effect relationships between components--underlies many complex generative processes, including videos, language, and robot trajectories.Current causal diffusion models entangle temporal reasoning with iterative denoising, applying causal attention across all layers, at every denoising step, and over the entire context.In this paper, we show that the causal computation in these models is separable from the multi-step denoising process.Through systematic probing of autoregressive video diffusers, we uncover two key regularities:(1) early blocks produce highly similar features across denoising steps, indicating redundant computation along the diffusion trajectory; and(2) deeper blocks exhibit sparse cross-frame attention and primarily perform intra-frame rendering.Motivated by these findings, we introduce Separable Causal Diffusion (SCD), a new architecture that explicitly decouples once-per-frame temporal reasoning, via a causal transformer encoder, from multi-step frame-wise rendering, via a lightweight diffusion decoder.Extensive experiments on both pretraining and post-training tasks across synthetic and real benchmarks show that CSD significantly improves throughput and latency while matching or surpassing the generation quality of strong causal diffusion baselines.

Zhen Zhou, Jian Liu, Biwen Lei, Jing Xu, Haohan Weng, Yiling Zhu, Zhuo Chen, Junfeng Fan, Yunkai Ma, Dazhao Du 等

Reinforcement learning (RL) has demonstrated remarkable success in text and image generation, yet its potential in 3D generation remains largely unexplored. Existing attempts typically rely on offline direct preference optimization (DPO) method, which suffers from low training efficiency and limited generalization. In this work, we aim to enhance both the training efficiency and generation quality of RL in 3D mesh generation. Specifically, (1) we design the first asynchronous online RL framework tailored for 3D mesh generation post-training efficiency improvement, which is 3.75xfaster than synchronous RL. (2) We propose Advantage-guided Ranking Preference Optimization (ARPO), a novel RL algorithm that achieves a better trade-off between training efficiency and generalization than current RL algorithms designed for 3D mesh generation, such as DPO and group relative policy optimization (GRPO). (3) Based on asynchronous ARPO, we propose Mesh-Pro, which additionally introduces a novel diagonal-aware mixed triangular-quadrilateral tokenization for mesh representation and a ray-based reward for geometric integrity. Mesh-Pro achieves state-of-the-art performance on artistic and dense meshes.

Shuoshuo Zhang, Yizhen Zhang, Jingjing Fu, Lei Song, Jiang Bian, Yujiu Yang, Rui Wang

Large vision-language models (VLMs) often benefit from intermediate visual cues, either injected via external tools or generated as latent visual tokens during reasoning, but these mechanisms still overlook fine-grained visual evidence (e.g., polylines in charts), generalize poorly across domains, and incur high inference-time cost. In this paper, we propose Bi-directional Perceptual Shaping (BiPS), which transforms question-conditioned masked views into bidirectional where-to-look signals that shape perception during training. BiPS first applies a KL-consistency constraint between the original image and an evidence-preserving view that keeps only question-relevant regions, encouraging coarse but complete coverage of supporting pixels. It then applies a KL-separation constraint between the original and an evidence-ablated view where critical pixels are masked so the image no longer supports the original answer, discouraging text-only shortcuts (i.e., answering from text alone) and enforcing fine-grained visual reliance. Across eight benchmarks, BiPS boosts Qwen2.5-VL-7B by 8.2% on average and shows strong out-of-domain generalization to unseen datasets and image types.

Saar Huberman, Or Patashnik, Omer Dahary, Ron Mokady, Daniel Cohen-Or

Text-to-image diffusion models excel at generating high-quality, diverse images from natural language prompts. However, they often fail to produce semantically accurate results when the prompt contains concept combinations that contradict their learned priors. We define this failure mode as contextual contradiction, where one concept implicitly negates another due to entangled associations learned during training. To address this, we propose a stage-aware prompt decomposition framework that guides the denoising process using a sequence of proxy prompts. Each proxy prompt is constructed to match the semantic content expected to emerge at a specific stage of denoising, while ensuring contextual coherence. To construct these proxy prompts, we leverage a large language model (LLM) to analyze the target prompt, identify contradictions, and generate alternative expressions that preserve the original intent while resolving contextual conflicts. By aligning prompt information with the denoising progression, our method enables fine-grained semantic control and accurate image generation in the presence of contextual contradictions. Experiments across a variety of challenging prompts show substantial improvements in alignment to the textual prompt.