CVPR 2025 Papers

In scene graph generation (SGG), the accurate prediction of unseen triples is essential for its effectiveness in downstream vision-language tasks. We hypothesize that the predicates of unseen triples can be viewed as transformations of seen predicates in feature space, and the essence of the zero-shot task is to bridge the gap caused by this transformation. Traditional models, however, have difficulty addressing this challenge, which we attribute to their inability to model the predicates equivariant. To overcome this limitation, we introduce a novel framework based on capsule networks (CAPSGG). We propose a Three-Stream Pipeline that generates modality-specific representations for predicates, while building low-level predicate capsules of these modalities. Then these capsules are aggregated into high-level predicate capsules using a Routing Capsule Layer. In addition, we introduce GroupLoss to aggregate capsules with the same predicate label into groups. This replaces the global loss with the intra-group loss, effectively balancing the learning of predicate invariance and equivariant features, while mitigating the impact of the severe long-tail distribution of the predicate categories. Our extensive experiments demonstrate the notable superiority of our approach over state-of-the-art methods, with zero-shot indicators outperforming up to 132.26% on SGCls task than the T-CAR [21]. Our code will be available upon publication.

In recent text-video retrieval, the use of additional captions from vision-language models has shown promising effects on the performance. However, existing models using additional captions often have struggled to capture the rich semantics, including temporal changes, inherent in the video. In addition, incorrect information caused by generative models can lead to inaccurate retrieval. To address these issues, we propose a new framework, Narrating the Video (NarVid), which strategically leverages the comprehensive information available from frame-level captions, the narration. The proposed NarVid exploits narration in multiple ways: 1) feature enhancement through cross-modal interactions between narration and video, 2) query-aware adaptive filtering to suppress irrelevant or incorrect information, 3) dual-modal matching score by adding query-video similarity and query-narration similarity, and 4) hard-negative loss to learn discriminative features from multiple perspectives using the two similarities from different views. Experimental results demonstrate that NarVid achieves state-of-the-art performance on various benchmark datasets.

Visual language models (VLMs) have made significant advances in accuracy in recent years. However, their efficiency has received much less attention. This paper introduces NVILA, a family of open VLMs designed to optimize both efficiency and accuracy. Building on top of VILA, we improve its model architecture by first scaling up the spatial and temporal resolutions, and then compressing visual tokens. This "scale-then-compress" approach enables NVILA to efficiently process high-resolution images and long videos. We also conduct a systematic investigation to enhance the efficiency of NVILA throughout its entire lifecycle, from training to deployment. NVILA matches or surpasses the accuracy of many leading open and proprietary VLMs across a wide range of image and video benchmarks. At the same time, it reduces training costs by 1.9-5.1X, prefilling latency by 1.6-2.2X, and decoding latency by 1.2-2.8X.

Recent advancements in generative models have significantly improved novel view synthesis (NVS) from multi-view data. However, existing methods depend on external multi-view alignment processes, such as explicit pose estimation or pre-reconstruction, which limits their flexibility and accessibility, especially when alignment is unstable due to insufficient overlap or occlusions between views. In this paper, we propose NVComposer, a novel approach that eliminates the need for explicit external alignment. NVComposer enables the generative model to implicitly infer spatial and geometric relationships between multiple conditional views by introducing two key components: 1) an image-pose dual-stream diffusion model that simultaneously generates target novel views and condition camera poses, and 2) a geometry-aware feature alignment module that distills geometric priors from dense stereo models during training. Extensive experiments demonstrate that NVComposer achieves state-of-the-art performance in generative multi-view NVS tasks, removing the reliance on external alignment and thus improving model accessibility. Our approach shows substantial improvements in synthesis quality as the number of unposed input views increases, highlighting its potential for more flexible and accessible generative NVS systems.

Thermal infrared imaging enables a non-invasive measurement of the surface temperature of objects with all-weather applicability. Leveraging such techniques for 3D reconstruction can accurately reflect the temperature distribution of a scene, thereby supporting applications such as building monitoring and energy management. However, existing approaches predominantly focus on static 3D reconstruction for a single time period, overlooking the dynamic nature of thermal radiation phenomena, and failing to predict or analyze temperature variations over time. In this paper, we introduce a novel method, termed NTR-Gaussian, grounded in thermodynamics to address the challenge of nighttime dynamic thermal reconstruction using 4D Gaussian Splatting. Specifically, We utilize neural networks to predict thermodynamic parameters, such as emissivity, convective heat transfer coefficient, and heat capacity, etc. By means of integration, we numerically solve the infrared temperature of the scene at each moment during the night, so as to predict the temperature of the nighttime scene more accurately. To further advance research in this domain, we release a comprehensive dataset of dynamic thermal reconstruction spanning four distinct regions. Extensive experiments demonstrate that NTR-Gaussian significantly outperforms comparison methods in thermal reconstruction, achieving a predicted temperature error within 1 degree Celsius.

The growing use of deep learning necessitates efficient network design and deployment, making neural predictors vital for estimating attributes such as accuracy and latency. Recently, Graph Neural Networks (GNNs) and transformers have shown promising performance in representing neural architectures. However, each method has its disadvantages. GNNs lack the capabilities to represent complicated features, while transformers face poor generalization when the depth of architecture grows. To mitigate the above problems, we rethink neural architecture topology and show that sibling nodes are pivotal while overlooked in previous research. Thus we propose a novel predictor leveraging the strengths of GNNs and transformers to learn the enhanced topology. We introduce a novel token mixer that considers siblings, and a new channel mixer named bidirectional graph isomorphism feed-forward network. Our approach consistently achieves promising performance in both accuracy and latency prediction, providing valuable insights for learning Directed Acyclic Graph (DAG) topology. The code is available at https://github.com/XuRuihan/NNFormer.

Designing effective neural architectures poses a significant challenge in deep learning. While Neural Architecture Search (NAS) automates the search for optimal architectures, existing methods are often constrained by predetermined search spaces and may miss critical neural architectures. In this paper, we introduce NADER (Neural Architecture Design via multi-agEnt collaboRation), a novel framework that formulates neural architecture design (NAD) as a LLM-based multi-agent collaboration problem. NADER employs a team of specialized agents to enhance a base architecture through iterative modification. Current LLM-based NAD methods typically operate independently, lacking the ability to learn from past experiences, which results in repeated mistakes and inefficient exploration. To address this issue, we propose the Reflector, which effectively learns from immediate feedback and long-term experiences. Additionally, unlike previous LLM-based methods that use code to represent neural architectures, we utilize a graph-based representation. This approach allows agents to focus on design aspects without being distracted by coding. We demonstrate the effectiveness of NADER in discovering high-performing architectures beyond predetermined search spaces through extensive experiments on benchmark tasks, showcasing its advantages over state-of-the-art methods.

Multi-Object Tracking (MOT) has been a long-standing challenge in video understanding. A natural and intuitive approach is to split this task into two parts: object detection and association. Most mainstream methods employ meticulously crafted heuristic techniques to maintain trajectory information and compute cost matrices for object matching. Although these methods can achieve notable tracking performance, they often require a series of elaborate handcrafted modifications while facing complicated scenarios. We believe that manually assumed priors limit the method's adaptability and flexibility in learning optimal tracking capabilities from domain-specific data. Therefore, we introduce a new perspective that treats Multiple Object Tracking as an in-context ID Prediction task, transforming the aforementioned object association into an end-to-end trainable task. Based on this, we propose a simple yet effective method termed MOTIP. Given a set of trajectories carried with ID information, MOTIP directly decodes the ID labels for current detections to accomplish the association process. Without using tailored or sophisticated architectures, our method achieves state-of-the-art results across multiple benchmarks by solely leveraging object-level features as tracking cues. The simplicity and impressive results of MOTIP leave substantial room for future advancements, thereby making it a promising baseline for subsequent research. Our code and checkpoints are released at https://github.com/MCG-NJU/MOTIP.

Neural Radiance Fields (NeRF) have shown impressive performances in the rendering of 3D scenes from arbitrary viewpoints. While RGB images are widely preferred for training volume rendering models, the interest in other radiance modalities is also growing. However, the capability of the underlying implicit neural models to learn and transfer information across heterogeneous imaging modalities has seldom been explored, mostly due to the limited training data availability. For this purpose, we present MultimodalStudio (MMS): it encompasses MMS-DATA and MMS-FW. MMS-DATA is a multimodal multi-view dataset containing 32 scenes acquired with 5 different imaging modalities: RGB, monochrome, near-infrared, polarization and multispectral. MMS-FW is a novel modular multimodal NeRF framework designed to handle multimodal raw data and able to support an arbitrary number of multi-channel devices. Through extensive experiments, we demonstrate that MMS-FW trained on MMS-DATA can transfer information between different imaging modalities and produce higher quality renderings than using single modalities alone. We publicly release the dataset and the framework, to promote the research on multimodal volume rendering and beyond.

Efficiently retrieving and synthesizing information from large-scale multimodal collections has become a critical challenge. However, existing video retrieval datasets suffer from scope limitations, primarily focusing on matching descriptive but vague queries with small collections of professionally edited, English-centric videos. To address this gap, we introduce MultiVENT 2.0, a large-scale, multilingual event-centric video retrieval benchmark featuring a collection of more than 218,000 news videos and over 3,900 queries targeting specific world events. These queries specifically target information found in the visual content, audio, embedded text, and text metadata of the videos, requiring systems leverage all these sources to succeed at the task. Preliminary results show that state-of-the-art vision-language models struggle significantly with this task, and while alternative approaches show promise, they are still insufficient to adequately address this problem. These findings underscore the need for more robust multimodal retrieval systems, as effective video retrieval is a crucial step towards multimodal content understanding and generation.

We present MultiMorph, a fast and efficient method for constructing anatomical atlases on the fly. Atlases capture the canonical structure of a collection of images and are essential for quantifying anatomical variability across populations. However, current atlas construction methods often require days to weeks of computation, thereby discouraging rapid experimentation. As a result, many scientific studies rely on suboptimal, precomputed atlases from mismatched populations, negatively impacting downstream analyses. MultiMorph addresses these challenges with a feedforward model that rapidly produces high-quality, population-specific atlases in a single forward pass for any 3D brain dataset, without any fine-tuning or optimization. MultiMorph is based on a linear group-interaction layer that aggregates and shares features within the group of input images. Further, by leveraging auxiliary synthetic data, MultiMorph generalizes to new imaging modalities and population groups at test-time. Experimentally, MultiMorph outperforms state-of-the-art optimization-based and learning-based atlas construction methods in both small and large population settings, with a 100-fold reduction in time. This makes MultiMorph an accessible framework for biomedical researchers without machine learning expertise, enabling rapid, high-quality atlas generation for diverse studies.

This paper investigates the research task of reconstructing the 3D clothed human body from a monocular image. Due to the inherent ambiguity of single-view input, existing approaches leverage pre-trained SMPL(-X) estimation models or generative models to provide auxiliary information for human reconstruction. However, these methods capture only the general human body geometry and overlook specific geometric details, leading to inaccurate skeleton reconstruction, incorrect joint positions, and unclear cloth wrinkles. In response to these issues, we propose a multi-level geometry learning framework. Technically, we design three key components: skeleton-level enhancement, joint-level augmentation, and wrinkle-level refinement modules. Specifically, we effectively integrate the projected 3D Fourier features into a Gaussian reconstruction model, introduce perturbations to improve joint depth estimation during training, and refine the human coarse wrinkles by resembling the de-noising process of the diffusion model. Extensive quantitative and qualitative experiments on two test sets show the superior performance of our approach compared to state-of-the-art (SOTA) methods.

This paper aims to reconstruct the scene geometry from multi-view images with strong robustness and high quality. Previous learning-based methods incorporate neural networks into the multi-view stereo matching and have shown impressive reconstruction results. However, due to the reliance on matching across input images, they typically suffer from high GPU memory consumption and tend to fail in sparse view scenarios. To overcome this problem, we develop a new pipeline, named Murre, for multi-view geometry reconstruction of 3D scenes based on SfM-guided monocular depth estimation. For input images, Murre first recover the SfM point cloud that captures the global scene structure, and then use it to guide a conditional diffusion model to produce multi-view metric depth maps for the final TSDF fusion. By predicting the depth map from a single image, Murre bypasses the multi-view matching step and naturally resolves the issues of previous MVS-based methods. In addition, the diffusion-based model can easily leverage the powerful priors of 2D foundation models, achieving good generalization ability across diverse real-world scenes. To obtain multi-view consistent depth maps, our key design is providing effective guidance on the diffusion model through the SfM point cloud, which is a condensed form of multi-view information, highlighting the scene's salient structure, and can be readily transformed into point maps to drive the image-space estimation process. We evaluate the reconstruction quality of Murre in various types of real-world datasets including indoor, streetscapes, and aerial scenes, surpassing state-of-the-art MVS-based and implicit neural reconstruction-based methods. The code and supplementary materials are available at https://zju3dv.github.io/murre/.

Video personalization methods allow us to synthesize videos with specific concepts such as people, pets, and places. However, existing methods often focus on limited domains, require time-consuming optimization per subject, or support only a single subject. We present Video Alchemist--a video model with built-in multi-subject, open-set personalization capabilities for both foreground objects and background, eliminating the need for time-consuming test-time optimization. Our model is built on a new Diffusion Transformer module that fuses each conditional reference image and its corresponding subject-level text prompt with cross-attention layers. Developing such a large model presents two main challenges: dataset and evaluation. First, as paired datasets of reference images and videos are extremely hard to collect, we sample selected video frames as reference images and synthesize a clip of the target video. However, while models can easily denoise training videos given reference frames, they fail to generalize to new contexts. To mitigate this issue, we design a new automatic data construction pipeline with extensive image augmentations. Second, evaluating open-set video personalization is a challenge in itself. To address this, we introduce a personalization benchmark that focuses on accurate subject fidelity and supports diverse personalization scenarios. Finally, our extensive experiments show that our method significantly outperforms existing personalization methods in both quantitative and qualitative evaluations.

The rapid development of diffusion models has fueled a growing demand for customized image generation. However, current customization methods face several limitations: 1) typically accept either image or text conditions alone; 2) customization in complex visual scenarios often leads to subject leakage or confusion; 3) image-conditioned outputs tend to suffer from inconsistent backgrounds; and 4) high computational costs. To address these issues, this paper introduces Multi-party Collaborative Attention Control (MCA-Ctrl), a tuning-free approach that enables high-quality image customization under both text and complex visual conditions. Specifically, MCA-Ctrl leverages two key operations within the self-attention layer to coordinate multiple parallel diffusion processes and guide the target image generation. This approach allows MCA-Ctrl to capture the content and appearance of specific subjects while maintaining semantic consistency with the conditional input. Additionally, to mitigate subject leakage and confusion issues common in complex visual scenarios, we introduce a Subject Localization Module that extracts precise subject and editable image layers based on user instructions. Extensive quantitative and human evaluation experiments demonstrate that MCA-Ctrl outperforms previous methods in zero-shot image customization, effectively addressing the aforementioned issues.

The rapid development of spatial transcriptomics (ST) allows researchers to measure the spatial-level gene expression in tissues. Although powerful, the cost for collecting the ST data is expensive, and thus several studies aim to predict gene expression in ST by utilizing their corresponding H/E stained pathology images. The existing ST based gene expression prediction models either adopt the pre-trained networks or rely on the handcrafted features to describe the pathology images, which still lack a systematic way to combine them together to define a spot-level representation that can reflect the topological profiles of different spots. On the other hand, all the ST based gene prediction models treat the prediction task for each gene independently, which overlook the fact that the exploration of potential interrelationships among them can help improve the prediction performance for individual genes.To address the above issues, we propose a multi-modal topology-embedded graph learning algorithm guided by prior Gene Ontology similarity information (i.e., M2TGLGO) to predict the spatial resolved genes from pathology image. Specifically, M2TGLGO co-learns the image representation of different spots from both deep and handcrafted features by considering the within-modal and inter-modal interactions. Next, to keep the topological structure among different spots, a spatial-oriented ranking module is also incorporated to preserve their neighborhood similarity information. Finally, we present a Gene Ontology knowledge guided graph neural network for simultaneously predicting multiple gene expressions by considering their functional associations. We evaluate our method on three public available ST datasets, the experimental results show the effectiveness of our M2TGLGO in comparison with the existing studies.

Recent advances in medical AI have shown a clear trend towards large models in healthcare. However, developing large models for multi-modal medical diagnosis remains challenging due to a lack of sufficient modal-complete medical data. Most existing multi-modal diagnostic models are relatively small and struggle with limited feature extraction capabilities. To bridge this gap, we propose **AdaCoMed**, an **ada**ptive **co**llaborative-learning framework that synergistically integrates the off-the-shelf **med**ical single-modal large models with multi-modal small models. Our framework first employs a mixture-of-modality-experts (MoME) architecture to combine features extracted from multiple single-modal medical large models, and then introduces a novel adaptive co-learning mechanism to collaborate with a multi-modal small model. This co-learning mechanism, guided by an adaptive weighting strategy, dynamically balances the complementary strengths between the MoME-fused large model features and the cross-modal reasoning capabilities of the small model. Extensive experiments on two representative multi-modal medical datasets (MIMIC-IV-MM and MMIST ccRCC) across six modalities and four diagnostic tasks demonstrate consistent improvements over state-of-the-art baselines, making it a promising solution for real-world medical diagnosis applications.

Pedestrian trajectory forecasting is crucial in various applications such as autonomous driving and mobile robot navigation. In such applications, camera-based perception enables the extraction of additional modalities (human pose, text) to enhance prediction accuracy. Indeed, we find that textual descriptions play a crucial role in integrating additional modalities into a unified understanding. However, online extraction of text requires the use of VLM, which may not be feasible for resource-constrained systems. To address this challenge, we propose a multi-modal knowledge distillation framework: a student model with limited modality is distilled from a teacher model trained with full range of modalities. The comprehensive knowledge of a teacher model trained with trajectory, human pose, and text is distilled into a student model using only trajectory or human pose as a sole supplement. In doing so, we separately distill the core locomotion insights from intra-agent multi-modality and inter-agent interaction. Our generalizable framework is validated with two state-of-the-art models across three datasets on both ego-view (JRDB, SIT) and BEV-view (ETH/UCY) setups, utilizing both annotated and VLM-generated text captions. Distilled student models show consistent improvement in all prediction metrics for both full and instantaneous observations, improving up to 13%. The code is available at github.com/Jaewoo97/KDTF.