ICCV 2025 Papers

The real value of knowledge lies not just in its accumulation, but in its potential to be harnessed effectively to conquer the unknown. Although recent multimodal large language models (MLLMs) exhibit impressing multimodal capabilities, they often fail in rarely encountered domain-specific tasks due to limited relevant knowledge. To explore this, we adopt visual game cognition as a testbed and select "Monster Hunter: World" as the target to construct a multimodal knowledge graph (MH-MMKG), which incorporates multi-modalities and intricate entity relations. We also design a series of challenging queries based on MH-MMKG to evaluate the models' ability for complex knowledge retrieval and reasoning. Furthermore, we propose a multi-agent retriever that enables a model to autonomously search relevant knowledge without additional training. Experimental results show that our approach significantly enhances the performance of MLLMs, providing a new perspective on multimodal knowledge-augmented reasoning and laying a solid foundation for future research.

Pansharpening, a pivotal task in remote sensing for fusing high-resolution panchromatic and multispectral imagery, has garnered significant research interest. Recent advancements employing diffusion models based on stochastic differential equations (SDEs) have demonstrated state-of-the-art performance. However, the inherent multi-step sampling process of SDEs imposes substantial computational overhead, hindering practical deployment. While existing methods adopt efficient samplers, knowledge distillation, or retraining to reduce sampling steps (e.g., from 1,000 to fewer steps), such approaches often compromise fusion quality.In this work, we propose the Optimal Transport Flow Matching (OTFM) framework, which integrates the dual formulation of unbalanced optimal transport (UOT) to achieve one-step, high-quality pansharpening. Unlike conventional OT formulations that enforce rigid distribution alignment, UOT relaxes marginal constraints to enhance modeling flexibility, accommodating the intrinsic spectral and spatial disparities in remote sensing data. Furthermore, we incorporate task-specific regularization into the UOT objective, enhancing the robustness of the flow model.The OTFM framework enables simulation-free training and single-step inference while maintaining strict adherence to pansharpening constraints. Experimental evaluations across multiple datasets demonstrate that OTFM matches or exceeds the performance of previous regression-based models and leading diffusion-based methods while only needing one sampling step.

Open-Vocabulary Segmentation (OVS) aims at segmenting images from free-form textual concepts without predefined training classes. While existing vision-language models such as CLIP can generate segmentation masks by leveraging coarse spatial information from Vision Transformers, they face challenges in spatial localization due to their global alignment of image and text features. Conversely, self-supervised visual models like DINO excel in fine-grained visual encoding but lack integration with language. To bridge this gap, we present Talk2DINO, a novel hybrid approach that combines the spatial accuracy of DINOv2 with the language understanding of CLIP. Our approach aligns the textual embeddings of CLIP to the patch-level features of DINOv2 through a learned mapping function without the need to fine-tune the underlying backbones. At training time, we exploit the attention maps of DINOv2 to selectively align local visual patches with textual embeddings. We show that the powerful semantic and localization abilities of Talk2DINO can enhance the segmentation process, resulting in more natural and less noisy segmentations, and that our approach can also effectively distinguish foreground objects from the background. Experimental results demonstrate that Talk2DINO achieves state-of-the-art performance across several unsupervised OVS benchmarks.

Spatial awareness is key to enable embodied multimodal AI systems. Yet, without vast amounts of spatial supervision, current Multimodal Large Language Models (MLLMs) struggle at this task. In this paper, we introduce TWIST & SCOUT, a framework that equips pre-trained MLLMs with visual grounding ability without forgetting their existing image and language understanding skills. To this end, we propose TWIST, a twin-expert stepwise tuning module that modifies the decoder of the language model using one frozen module pre-trained on image understanding tasks and another learnable one for visual grounding tasks. This allows the MLLM to retain previously learned knowledge and skills, while acquiring what is missing. To fine-tune the model effectively, we generate a high-quality synthetic dataset we call SCOUT, which mimics human reasoning in visual grounding. This dataset provides rich supervision signals, describing a step-by-step multimodal reasoning process, thereby simplifying the task of visual grounding. We evaluate our approach on several standard benchmark datasets, encompassing grounded image captioning, zero-shot localization, and visual grounding tasks. Our method consistently delivers strong performance across all tasks, while retaining the pre-trained image understanding capabilities.

Deep Neural Networks (DNNs) have been successfully applied in various computer tasks. However, they remain vulnerable to adversarial attacks, which could lead to severe security risks. In recent years, robust neural architecture search (NAS) has gradually become an emerging direction for designing adversarially robust architectures. However, existing robust NAS methods rely on repeatedly training numerous DNNs to evaluate robustness, which makes the search process extremely expensive. In this paper, we propose a training-free robust NAS method (TRNAS) that significantly reduces search costs. First, we design a zero-cost proxy model (R-Score) that formalizes adversarial robustness evaluation by exploring the theory of DNN's linear activation capability and feature consistency. This proxy only requires initialized weights for evaluation, thereby avoiding expensive adversarial training costs. Secondly, we introduce a multi-objective selection (MOS) strategy to save candidate architectures with robustness and compactness. Experimental results show that TRNAS only requires 0.02 GPU days to find a promising robust architecture in a vast search space including approximately 10^ 20 networks. TRNAS surpasses other state-of-the-art robust NAS methods under both white-box and black-box attacks. Finally, we summarize a few meaningful conclusions for designing the robust architecture and promoting the development of robust NAS field.

Dynamic Scene Graph Generation (DSGG) aims to create a scene graph for each video frame by detecting objects and predicting their relationships. Weakly Supervised DSGG (WS-DSGG) reduces annotation workload by using an un- localized scene graph from a single frame per video for training. Existing WS-DSGG methods depend on an off-the- shelf external object detector to generate pseudo labels for subsequent DSGG training. However, detectors trained on static, object-centric images struggle in dynamic, relation- aware scenarios required for DSGG, leading to inaccurate localization and low-confidence proposals. To address the challenges posed by external object detectors in WS-DSGG, we propose a Temporal-enhanced Relation-aware Knowl- edge Transferring (TRKT) method, which leverages knowl- edge to enhance detection in relation-aware dynamic sce- narios. TRKT is built on two key components: (1) Relation-aware knowledge mining: we first employ object and re- lation class decoders that generate category-specific atten- tion maps to highlight both object regions and interactive areas. Then we propose an Inter-frame Attention Augmen- tation strategy that exploits optical flow for neighboring frames to enhance the attention maps, making them motion- aware and robust to motion blur. This step yields relation- and motion-aware knowledge mining for WS-DSGG. (2) we introduce a Dual-stream Fusion Module that integrates category-specific attention maps into external detections to refine object localization and boost confidence scores for object proposals. Extensive experiments demonstrate that TRKT achieves state-of-the-art performance on Ac- tion Genome dataset. Our code is avaliable at https: //github.com/XZPKU/TRKT.git.

Diffusion models have emerged as the mainstream approach for visual generation. However, these models typically suffer from sample inefficiency and high training costs. Consequently, methods for efficient finetuning, inference and personalization were quickly adopted by the community. However, training these models in the first place still remains very costly. While several recent approaches--including masking, distillation, and architectural modifications--have been proposed to improve training efficiency, each of these methods comes with its own tradeoffs: some achieve enhanced performance at the expense of increased computational cost. In contrast, this work aims to improve training efficiency as well as generative performance at the same time through routes that act as transport mechanism for randomly selected tokens from early layers to deeper layers of the model. Our method is not limited to the common transformer-based model - it can also be applied to state-space models and achieves this without architectural modifications or additional parameters. Finally, we show that TREAD reduces the computational cost and simultaneously boosts model performance on the standard benchmark ImageNet-256 in class-conditional synthesis. Both of these benefits multiply to a convergence speedup of 14x at 400K training iterations compared to DiT and 37x compared to the best benchmark performance of DiT at 7M training iterations. Further, we achieve a competitive FID of 2.09 in a guided and 3.93 in an unguided setting which improves upon the DiT, without architectural changes. We will release our code.

Recent advances in text-to-image diffusion models enable photorealistic image generation, but they also risk producing malicious content, such as NSFW images. To mitigate risk, concept erasure methods are studied to facilitate the model to unlearn specific concepts. However, current studies struggle to fully erase malicious concepts implicitly embedded in prompts (e.g., metaphorical expressions or adversarial prompts) while preserving the model's normal generation capability. To address this challenge, our study proposes TRCE, using a two-stage concept erasure strategy to achieve an effective trade-off between reliable erasure and knowledge preservation. Firstly, TRCE starts by erasing the malicious semantics implicitly embedded in textual prompts. By identifying a critical mapping objective(i.e., the [EoT] embedding), we optimize the cross-attention layers to map malicious prompts to contextually similar prompts but with safe concepts. This step prevents the model from being overly influenced by malicious semantics during the denoising process. Following this, considering the deterministic properties of the sampling trajectory of the diffusion model, TRCE further steers the early denoising prediction toward the safe direction and away from the unsafe one through contrastive learning, thus further avoiding the generation of malicious content. Finally, we conduct comprehensive evaluations of TRCE on multiple malicious concept erasure benchmarks, and the results demonstrate its effectiveness in erasing malicious concepts while better preserving the model's original generation ability.

In this paper, we aim to model 3D scene geometry, appearance, and physical information just from dynamic multi-view videos in the absence of any human labels. By leveraging physics-informed losses as soft constraints or integrating simple physics models into neural networks, existing works often fail to learn complex motion physics, or doing so requires additional labels such as object types or masks. In this paper, we propose a new framework named **TRACE** to model the motion physics of complex dynamic 3D scenes. The key novelty of our approach is that, by formulating each 3D point as a rigid particle with size and orientation in space, we choose to directly learn a translation rotation dynamics system for each particle, explicitly estimating a complete set of physical parameters to govern the particle's motion over time. Extensive experiments on three existing dynamic datasets and one newly created challenging synthetic datasets demonstrate the extraordinary performance of our method over baselines in the task of future frame extrapolation. A nice property of our framework is that multiple objects or parts can be easily segmented just by clustering the learned physical parameters. Our datasets and code will be released at https://github.com/.

Large pre-trained models achieve remarkable performance in vision tasks but are impractical for fine-tuning due to high computational and storage costs. Parameter-Efficient Fine-Tuning (PEFT) methods mitigate this issue by updating only a subset of parameters; however, most existing approaches are task-agnostic, failing to fully exploit task-specific adaptations, which leads to suboptimal efficiency and performance. To address this limitation, we propose Task-Relevant Parameter and Token Selection (TR-PTS), a task-driven framework that enhances both computational efficiency and accuracy. Specifically, we introduce Task-Relevant Parameter Selection, which utilizes the Fisher Information Matrix (FIM) to identify and fine-tune only the most informative parameters in a layer-wise manner, while keeping the remaining parameters frozen. Simultaneously, Task-Relevant Token Selection dynamically preserves the most informative tokens and merges redundant ones, reducing computational overhead. By jointly optimizing parameters and tokens, TR-PTS enables the model to concentrate on task-discriminative information. We evaluate TR-PTS on benchmark, including FGVC and VTAB-1k, where it achieves state-of-the-art performance, surpassing full fine-tuning by 3.40% and 10.35%, respectively. The code are available at https://github.com/synbol/TR-PTS.

X-ray imaging, based on penetration, enables detailed visualization of internal structures. Building on this capability, existing implicit 3D reconstruction methods have adapted the NeRF model and its variants for internal CT reconstruction. However, these approaches often neglect the significance of objects' anatomical priors for implicit learning, limiting both reconstruction precision and learning efficiency, particularly in ultra-sparse view scenarios. To address these challenges, we propose a novel 3D CT reconstruction framework that employs a 'target prior' derived from the object's projection data to enhance implicit learning. Our approach integrates positional and structural encoding to facilitate voxel-wise implicit reconstruction, utilizing the target prior to guide voxel sampling and enrich structural encoding. This dual strategy significantly boosts both learning efficiency and reconstruction quality. Additionally, we introduce a CUDA-based algorithm for rapid estimation of high-quality 3D target priors from sparse-view projections. Experiments utilizing projection data from a complex abdominal dataset demonstrate that the proposed model substantially enhances learning efficiency, outperforming the current leading model, NAF, by a factor of ten. In terms of reconstruction quality, it also exceeds the most accurate model, NeRP, achieving PSNR improvements of 3.57 dB, 5.42 dB, and 5.70 dB with 10, 20, and 30 projections, respectively. The code is available upon request.

Pedestrian trajectory prediction is crucial for many intelligent tasks. While existing methods predict future trajectories from fixed-frame historical observations, they are limited by the observational perspective and the need for extensive historical information, resulting in prediction delays and inflexible generalization in real-time systems. In this paper, we propose a novel task called Transferable Online Pedestrian Trajectory Prediction (TOTP), which synchronously predicts future trajectories with variable observations and enables effective task transfer under different observation constraints. To advance TOTP modeling, we propose a Temporal-Adaptive Mamba Latent Diffusion (TAMLD) model. It utilizes the Social-Implicit Mamba Synthesizer to extract motion states with social interaction and refine temporal representations through Temporal-Aware Distillation. A Trend-Conditional Mamba Decomposer generates the motion latent distribution of the future motion trends and predicts future motion trajectories through sampling decomposition. We utilize Motion-Latent Mamba Diffusion to reconstruct the latent space disturbed by imbalanced temporal noise. Our method achieves state-of-the-art results on multiple datasets and tasks, showcasing temporal adaptability and generalization ability.

We address the problem of video question answering (video QA) with temporal grounding in a weakly supervised setup, without any temporal annotations. Given a video and a question, we generate an open-ended answer grounded with the start and end time. For this task, we propose TOGA: a vision-language model for Temporally Grounded Open-Ended Video QA with Weak Supervision. We instruct-tune TOGA to jointly generate the answer and the temporal grounding. We operate in a weakly supervised setup where the temporal grounding annotations are not available.We generate pseudo labels for temporal grounding and ensure the validity of these labels by imposing a consistency constraint between the question of a grounding response and the response generated by a question referring to the same temporal segment. We notice that jointly generating the answers with the grounding improves performance on question answering as well as grounding.We evaluate TOGA on grounded QA and open-ended QA tasks. For grounded QA, we consider the NExT-GQA benchmark which is designed to evaluate weakly supervised grounded open-ended question answering.For open-ended QA, we consider the MSVD-QA and ActivityNet-QA benchmarks. We achieve state-of-the-art performance for both tasks on these benchmarks.

Video Frame Interpolation (VFI) aims to predict the intermediate frame I_n (we use n to denote time in videos to avoid notation overload with the timestep t in diffusion models) based on two consecutive neighboring frames I_0 and I_1. Recent approaches apply diffusion models (both image-based and video-based) in this task and achieve strong performance. However, image-based diffusion models are unable to extract temporal information and are relatively inefficient compared to non-diffusion methods. Video-based diffusion models can extract temporal information, but they are too large in terms of training scale, model size, and inference time. To mitigate the above issues, we propose Temporal-Aware Latent Brownian Bridge Diffusion for Video Frame Interpolation (TLB-VFI), an efficient video-based diffusion model. By extracting rich temporal information from video inputs through our proposed 3D-wavelet gating and temporal-aware autoencoder, our method achieves 20% improvement in FID on the most challenging datasets over recent SOTA of image-based diffusion models. Meanwhile, due to the existence of rich temporal information, our method achieves strong performance while having 3xfewer parameters. Such a parameter reduction results in 2.3xspeed up. By incorporating optical flow guidance, our method requires 9000xless training data and achieves over 20xfewer parameters than video-based diffusion models.

We focus on the source-free domain adaptive object detection (SFDAOD) problem when source data is unavailable during adaptation and the model must adapt to the unlabeled target domain. The majority of approaches for the problem employ a self-supervised approach using a student-teacher (ST) framework where pseudo-labels are generated via a source-pretrained model for further fine-tuning. We observe that the performance of a student model often degrades drastically, due to the collapse of the teacher model, primarily caused by high noise in pseudo-labels, resulting from domain bias, discrepancies, and a significant domain shift across domains. To obtain reliable pseudo-labels, we propose a Target-based Iterative Query-Token Adversarial Network (TITAN) which separates the target images into two subsets that are similar to the source (easy) and those that are dissimilar (hard). We propose a strategy to estimate variance to partition the target domain. This approach leverages the insight that higher detection variances correspond to higher recall and greater similarity to the source domain. Also, we incorporate query-token based adversarial modules into a student-teacher baseline framework to reduce the domain gaps between two feature representations. Experiments conducted on four natural imaging datasets and two challenging medical datasets have substantiated the superior performance of TITAN compared to existing state-of-the-art (SOTA) methodologies. We report a map improvement of +22.7, +22.2, +21.1, and +3.7 percent over the current SOTA on C2F, C2B, S2C, and K2C benchmarks, respectively. Code is available at https://github.com/Tajamul21/TITAN

In the recent development of conditional diffusion models still require heavy supervised fine-tuning for performing control on a category of tasks. Training-free conditioning via guidance with off-the-shelf models is a favorable alternative to avoid further fine-tuning on the base model. However, the existing training-free guidance frameworks either have heavy memory requirements or offer sub-optimal control due to rough estimation. These shortcomings limit the applicability to control diffusion models that require intense computation, such as Text-to-Video (T2V) diffusion models. In this work, we propose Taming Inference Time Alignment for Guided Text-to-Video Diffusion Model, so-called TITAN-Guide, which overcomes memory space issues, and provides more optimal control in the guidance process compared to the counterparts. In particular, we develop an efficient method for optimizing diffusion latents without backpropagation from a discriminative guiding model. In particular, we study forward gradient descents for guided diffusion tasks with various options on directional directives. In our experiments, we demonstrate the effectiveness of our approach in efficiently managing memory during latent optimization, while previous methods fall short. Our proposed approach not only minimizes memory requirements but also significantly enhances T2V performance across a range of diffusion guidance benchmarks. Code, models, and demo are available at https://titanguide.github.io.

Video generation models are revolutionizing content creation, with image-to-video models drawing increasing attention due to their enhanced controllability, visual consistency, and practical applications. However, despite their popularity, these models rely on user-provided text and image prompts, and there is currently no dedicated dataset for studying these prompts. In this paper, we introduce TIP-I2V, the first large-scale dataset of over 1.70 million unique user-provided Text and Image Prompts specifically for Image-to-Video generation. Additionally, we provide the corresponding generated videos from five state-of-the-art image-to-video models. We begin by outlining the time-consuming and costly process of curating this large-scale dataset. Next, we compare TIP-I2V to two popular prompt datasets, VidProM (text-to-video) and DiffusionDB (text-to-image), highlighting differences in both basic and semantic information. This dataset enables advancements in image-to-video research. For instance, to develop better models, researchers can use the prompts in TIP-I2V to analyze user preferences and evaluate the multi-dimensional performance of trained models; and to enhance model safety, they may focus on addressing the misinformation issue caused by image-to-video models. The new research inspired by TIP-I2V and the differences with existing datasets emphasize the importance of a specialized image-to-video prompt dataset. The project is available at https://tip-i2v.github.io/.

Text-and-Image-To-Image (TI2I), an extension of Text-To-Image (T2I), integrates image inputs with textual instructions to enhance image generation. Existing methods often partially utilize image inputs, focusing on specific elements like objects or styles, or they experience a decline in generation quality with complex, multi-image instructions. To overcome these challenges, we introduce Training-Free Text-and-Image-to-Image (TF-TI2I), which adapts cutting-edge T2I models such as SD3 without the need for additional training. Our method capitalizes on the MM-DiT architecture, in which we point out that textual tokens can implicitly learn visual information from vision tokens. We enhance this interaction by extracting a condensed visual representation from reference images, facilitating selective information sharing through Reference Contextual Masking--this technique confines the usage of contextual tokens to instruction-relevant visual information. Additionally, our Winner-Takes-All module mitigates distribution shifts by prioritizing the most pertinent references for each vision token. Addressing the gap in TI2I evaluation, we also introduce the FG-TI2I Bench, a comprehensive benchmark tailored for TI2I and compatible with existing T2I methods. Our approach shows robust performance across various benchmarks, confirming its effectiveness in handling complex image-generation tasks.

Long-term temporal information is crucial for event-based perception tasks, as raw events only encode pixel brightness changes. Recent works show that when trained from scratch, recurrent models achieve better results than feedforward models in these tasks. However, when leveraging self-supervised pre-trained weights, feedforward models can outperform their recurrent counterparts. Current self-supervised learning (SSL) methods for event-based pre-training largely mimic RGB image-based approaches. They pre-train feedforward models on raw events within a short time interval, ignoring the temporal information of events. In this work, we introduce TESPEC, a self-supervised pre-training framework tailored for learning spatio-temporal information. TESPEC is well-suited for recurrent models, as it is the first framework to leverage long event sequences during pre-training. TESPEC employs the masked image modeling paradigm with a new reconstruction target. We design a novel method to accumulate events into pseudo grayscale videos containing high-level semantic information about the underlying scene, which is robust to sensor noise and reduces motion blur. Reconstructing this target thus requires the model to reason about long-term history of events. Extensive experiments demonstrate our state-of-the-art results in downstream tasks, including object detection, semantic segmentation, and monocular depth estimation. Project webpage: https://mhdmohammadi.github.io/TESPEC_webpage.