CVPR 2025 Papers

This paper presents LLaMo (Large Language and Human Motion Assistant), a multimodal framework for human motion instruction tuning. In contrast to conventional instruction-tuning approaches that convert non-linguistic inputs, such as video or motion sequences, into language tokens, LLaMo retains motion in its native form for instruction tuning. This method preserves motion-specific details that are often diminished in tokenization, thereby improving the model's ability to interpret complex human behaviors. By processing both video and motion data alongside textual inputs, LLaMo enables a flexible, human-centric analysis. Experimental evaluations across high-complexity domains, including human behaviors and professional activities, indicate that LLaMo effectively captures domain-specific knowledge, enhancing comprehension and prediction in motion-intensive scenarios. We hope LLaMo offers a foundation for future multimodal AI systems with broad applications, from sports analytics to behavioral prediction.

As AI models are increasingly integrated into applications involving human interaction, understanding the alignment between human perception and machine vision has become essential. One example is the estimation of visual motion (optical flow) in dynamic applications such as driving assistance. While there are numerous optical flow datasets and benchmarks with ground truth information, human-perceived flow in natural scenes remains underexplored. We introduce HuPerFlow--a benchmark for human-perceived flow, measured at 2,400 locations across ten optical flow datasets, with 38,400 response vectors collected through online psychophysical experiments. Our data demonstrate that human-perceived flow aligns with ground truth in spatiotemporally smooth locations while also showing systematic errors influenced by various environmental properties. Additionally, we evaluated several optical flow algorithms against human-perceived flow, uncovering both similarities and unique aspects of human perception in complex natural scenes. HuPerFlow is the first large-scale human-perceived flow benchmark for alignment between computer vision models and human perception, as well as for scientific exploration of human motion perception in natural scenes. The HuPerFlow benchmark will be available online upon acceptance.

We present HuMoCon, a novel motion-video understanding framework designed for advanced human behavior analysis. The core of our method is a human motion concept discovery framework that efficiently trains multi-modal encoders to extract semantically meaningful and generalizable features. HuMoCon addresses key challenges in motion concept discovery for understanding and reasoning, including the lack of explicit multi-modality feature alignment and the loss of high-frequency information in masked autoencoding frameworks. Our approach integrates a feature alignment strategy that leverages video for contextual understanding and motion for fine-grained interaction modeling, further with a velocity reconstruction mechanism to enhance high-frequency feature expression and mitigate temporal over-smoothing. Comprehensive experiments on standard benchmarks demonstrate that HuMoCon enables effective motion concept discovery and significantly outperforms state-of-the-art methods in training large models for human motion understanding.

Model merging combines expert models---each finetuned from a shared foundation model on diverse tasks and domains---into a single, more capable base model. However, existing model merging approaches assume all experts to be available simultaneously. In reality, new tasks and domains emerge continuously, prompting the need for a dynamic process of integrating these experts over time, which we call temporal model merging. The temporal dimension introduces unique challenges not addressed in prior work: At each task, should expert training start from merged previous experts or the original base model? Should all models be merged at every time step? Which merging techniques are best suited for temporal merging? Should different strategies be used for the training initialization and deployment phases? To tackle these questions, we propose a unified framework called TIME---Temporal Integration of Model Expertise---that defines temporal model merging across three axes: (1) Initialization Phase, (2) Deployment Phase, and (3) Merging Technique. Utilizing TIME, we study temporal model merging across model sizes, tasks, and compute budgets on the large-scale FoMo-in-Flux benchmark for continual multimodal pretraining. Systematic experiments across TIME and FoMo-in-Flux allow us to arrive at several crucial key insights for temporal model merging to better understand current limits and best practices for successful model merging across time.

We tackle the novel problem of predicting 3D hand motion and contact maps (or Interaction Trajectories) given a single RGB view, action text, and a 3D contact point on the object as input. Our approach consists of (1) Interaction Codebook: a VQVAE model to learn a latent codebook of hand poses and contact points, effectively tokenizing interaction trajectories, (2) Interaction Predictor: a transformer-decoder module to predict the interaction trajectory from test time inputs by using an indexer module to retrieve a latent affordance from the learned codebook. To train our model, we develop a data engine that extracts 3D hand poses and contact trajectories from the diverse HoloAssist dataset. We evaluate our model on a benchmark that is 2.5-10X larger than existing works, in terms of diversity of objects and interactions observed, and test for generalization of the model across object categories, action categories, tasks, and scenes. Experimental results show the effectiveness of our approach over transformer & diffusion baselines across all settings.

We propose a method, HotSpot, for optimizing neural signed distance functions. Existing losses, such as the eikonal loss, act as necessary but insufficient constraints and cannot guarantee that the recovered implicit function represents a true distance function, even if the output minimizes these losses almost everywhere. Furthermore, the eikonal loss suffers from stability issues in optimization. Finally, in conventional methods, regularization losses that penalize surface area distort the reconstructed signed distance function. We address these challenges by designing a loss function using the solution of a screened Poisson equation. Our loss, when minimized, provides an asymptotically sufficient condition to ensure the output converges to a true distance function. Our loss also leads to stable optimization and naturally penalizes large surface areas. We present theoretical analysis and experiments on both challenging 2D and 3D datasets and show that our method provides better surface reconstruction and a more accurate distance approximation.

Seamless integration of both aerial and street view images remains a significant challenge in neural scene reconstruction and rendering. Existing methods predominantly focus on single domain, limiting their applications in immersive environments, which demand extensive free view exploration with large view changes both horizontally and vertically. We introduce Horizon-GS, a novel approach built upon Gaussian Splatting techniques, tackles the unified reconstruction and rendering for aerial and street views. Our method addresses the key challenges of combining these perspectives with a new training strategy, overcoming viewpoint discrepancies to generate high-fidelity scenes. We also curated a high-quality aerial-to-ground view dataset encompassing both synthetic and real-world scene to advance further research. Experiments across diverse urban scene datasets confirms the effectiveness of our method.

Analyses of human motion kinematics have achieved tremendous advances. However, the production mechanism, known as human dynamics, is still undercovered. In this paper, we aim to push data-driven human dynamics understanding forward. We identify a major obstacle to this as the heterogeneity of existing human motion understanding efforts. Specifically, heterogeneity exists in not only the diverse kinematics representations and hierarchical dynamics representations but also in the data from different domains, namely biomechanics and reinforcement learning. With an in-depth analysis of the existing heterogeneity, we propose to emphasize the beneath homogeneity: all of them represent the homogeneous fact of human motion, though from different perspectives. Given this, we propose Homogeneous Dynamics Space (HDyS) as a fundamental space for human dynamics by aggregating heterogeneous data and training a homogeneous latent space with inspiration from the inverse-forward dynamics procedure. Leveraging the heterogeneous representations and datasets, HDyS achieves decent mapping between human kinematics and dynamics. We demonstrate the feasibility of HDyS with extensive experiments and applications. The project page is https://foruck.github.io/HDyS.

In this paper, we present HomoGen, an enhanced video inpainting method based on homography propagation and diffusion models. HomoGen leverages homography registration to propagate contextual pixels as priors for generating missing content in corrupted videos. Unlike previous flow-based propagation methods, which introduce local distortions due to point-to-point optical flows, homography-induced artifacts are typically global structural distortions that preserve semantic integrity. To effectively utilize these priors for generation, we employ a video diffusion model that inherently prioritizes semantic information within the priors over pixel-level details. A content-adaptive control mechanism is proposed to scale and inject the priors into intermediate video latents during iterative denoising. In contrast to existing transformer-based networks that often suffer from artifacts within priors, leading to error accumulation and unrealistic results, our denoising diffusion network can smooth out artifacts and ensure natural outputs. Extensive experiments demonstrate the effectiveness of the proposed method qualitatively and quantitatively.

How can we enable models to comprehend video anomalies occurring over varying temporal scales and contexts?Traditional Video Anomaly Understanding (VAU) methods focus on frame-level anomaly prediction, often missing the interpretability of complex and diverse real-world anomalies. Recent multimodal approaches leverage visual and textual data but lack hierarchical annotations that capture both short-term and long-term anomalies.To address this challenge, we introduce HIVAU-70k, a large-scale benchmark for hierarchical video anomaly understanding across any granularity. We develop a semi-automated annotation engine that efficiently scales high-quality annotations by combining manual video segmentation with recursive free-text annotation using large language models (LLMs). This results in over 70,000 multi-granular annotations organized at clip-level, event-level, and video-level segments.For efficient anomaly detection in long videos, we propose the Anomaly-focused Temporal Sampler (ATS). ATS integrates an anomaly scorer with a density-aware sampler to adaptively select frames based on anomaly scores, ensuring that the multimodal LLM concentrates on anomaly-rich regions, which significantly enhances both efficiency and accuracy.Extensive experiments demonstrate that our hierarchical instruction data markedly improves anomaly comprehension. The integrated ATS and visual-language model outperform traditional methods in processing long videos.Our benchmark and model will be publicly available.

Novel view synthesis has demonstrated impressive progress recently, with 3D Gaussian splatting (3DGS) offering efficient training time and photorealistic real-time rendering. However, reliance on Cartesian coordinates limits 3DGS's performance on distant objects, which is important for reconstructing unbounded outdoor environments. We found that, despite its ultimate simplicity, using homogeneous coordinates, a concept on the projective geometry, for the 3DGS pipeline remarkably improves the rendering accuracies of distant objects. We therefore propose Homogeneous Gaussian Splatting (HoGS) incorporating homogeneous coordinates into the 3DGS framework, providing a unified representation for enhancing near and distant objects. HoGS effectively manages both expansive spatial positions and scales particularly in outdoor unbounded environments by adopting projective geometry principles. Experiments show that HoGS significantly enhances accuracy in reconstructing distant objects while maintaining high-quality rendering of nearby objects, along with fast training speed and real-time rendering capability. Our implementation will be released upon acceptance. Our implementations are available on our project page https://kh129.github.io/hogs/.

Federated learning for pathological whole slide image (WSI) classification allows multiple clients to train a global multiple instance learning (MIL) model without sharing their privacy-sensitive WSIs. To accommodate the non-independent and identically distributed (non-i.i.d.) feature shifts, cross-client style transfer has been popularly used but is subject to two fundamental issues: (1) WSI contains multiple morphological structures, each corresponding to a distinct style. (2) Performing style transfer may potentially shift the region of interests (RoIs) in the augmented WSIs. To address these challenges, we propose HistoFS, a federated learning framework for computational pathology on non-i.i.d. feature shifts in WSI classification. Specifically, we introduce pseudo bag styles that capture multiple style variations within a single WSI. In addition, an authenticity module is introduced to ensure that RoIs are preserved, allowing local models to learn WSIs with diverse styles while maintaining essential RoIs. Extensive experiments validate the superiority of HistoFS over state-of-the-art methods on three clinical datasets. Our code is available at https://lalakitchen.github.io/HistoFS/.

In this work we address various shape matching problems that can be cast as finding cyclic paths in a product graph. This involves for example 2D-3D shape matching, 3D shape matching, or the matching of a contour to a graph. In this context, matchings are typically obtained as the minimum cost cycle in the product graph. Instead, inspired by related works on model-based image segmentation (Schoenemann and Cremers 2009), we consider minimum ratio cycles, which we combine with the recently introduced conjugate product graph in order to allow for higher-order matching costs. With that, on the one hand we avoid the bias of obtaining matchings that involve fewer/shorter edges, while on the other hand we are able to impose powerful geometric regularisation, e.g. to avoid zig-zagging. In our experiments we demonstrate that this not only leads to improved matching accuracy in most cases, but also to significantly reduced runtimes (up to two orders of magnitude, depending on the setting). Our GPU implementations are publicly available: https://github.com/paul0noah/product-graph-cycles/.

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

Recently single-view 3D generation via Gaussian splatting has emerged and developed quickly. They learn 3D Gaussians from 2D RGB images generated from pre-trained multi-view diffusion (MVD) models, and have shown a promising avenue for 3D generation through a single image. Despite the current progress, these methods still suffer from the inconsistency jointly caused by the geometric ambiguity in the 2D images, and the lack of structure of 3D Gaussians, leading to distorted and blurry 3D object generation. In this paper, we propose to fix these issues by GS-RGBN, a new RGBN-volume Gaussian Reconstruction Model designed to generate high-fidelity 3D objects from single-view images. Our key insight is a structured 3D representation can simultaneously mitigate the afore-mentioned two issues. To this end, we propose a novel hybrid Voxel-Gaussian representation, where a 3D voxel representation contains explicit 3D geometric information, eliminating the geometric ambiguity from 2D images. It also structures Gaussians during learning so that the optimization tends to find better local optima. Our 3D voxel representation is obtained by a fusion module that aligns RGB features and surface normal features, both of which can be estimated from 2D images. Extensive experiments demonstrate the superiority of our methods over prior works in terms of high-quality reconstruction results, robust generalization, and good efficiency.

Relightable portrait animation aims to animate a static reference portrait to match the head movements of a driving video while adapting to user-specified or reference lighting conditions. Existing portrait animation methods fail to achieve relightable portraits because they do not separate and manipulate intrinsic (identity and appearance) and extrinsic (pose and lighting) features. In this paper, we present a Lighting Controllable Video Diffusion model (LCVD) for high-fidelity, relightable portrait animation. We address this limitation by distinguishing these feature types through dedicated subspaces within the feature space of a pre-trained image-to-video diffusion model. Specifically, for each frame, we use the 3D mesh of the reference portrait, the pose of the driving frame as well as the specified lighting to render an image called shading hint. While the reference image represents the intrinsic attributes, the shading hint encodes the extrinsic attributes. In the training phase, we employ a reference adapter to map the reference into an intrinsic feature subspace and a shading adapter to map the shading hints into an extrinsic feature subspace. By merging features from these subspaces, the model achieves nuanced control over lighting and pose in generated animations. Extensive evaluations show that LCVD outperforms state-of-the-art methods in lighting realism, image quality, and video consistency, setting a new benchmark in relightable portrait animation. Our project is available at \href https://github.com/MingtaoGuo/Relightable-Portrait-Animation https://github.com/MingtaoGuo/Relightable-Portrait-Animation

Recently, learning signed distance functions (SDFs) from point clouds has become popular for reconstruction. To ensure accuracy, most methods require using high-resolution Marching Cubes for surface extraction. However, this results in redundant mesh elements, making the mesh inconvenient to use. To solve the problem, we propose an adaptive meshing method to extract resolution-adaptive meshes based on surface curvature, enabling the recovery of high-fidelity lightweight meshes. Specifically, we first use point-based representation to perceive implicit surfaces and calculate surface curvature. A vertex generator is designed to produce curvature-adaptive vertices with any specified number on the implicit surface, preserving the overall structure and high-curvature features. Then we develop a Delaunay meshing algorithm to generate meshes from vertices, ensuring geometric fidelity and correct topology. In addition, to obtain accurate SDFs for adaptive meshing and achieve better lightweight reconstruction, we design a hybrid representation combining feature grid and feature tri-plane for better detail capture. Experiments demonstrate that our method can generate high-quality lightweight meshes from point clouds. Compared with methods from various categories, our approach achieves superior results, especially in capturing more details with fewer elements.

Semantic segmentation from RGB cameras is essential to the perception of autonomous flying vehicles. The stability of predictions through the captured videos is paramount to their reliability and, by extension, to the trustworthiness of the agents. In this paper, we propose a lightweight video semantic segmentation approach--suited to onboard real-time inference--achieving high temporal consistency on aerial data through Semantic Similarity Propagation across frames. SSP temporally propagates the predictions of an efficient image segmentation model with global registration alignment to compensate for camera movements. It combines the current estimation and the prior prediction with linear interpolation using weights computed from the features similarities of the two frames. Because data availability is a challenge in this domain, we propose a consistency-aware Knowledge Distillation training procedure for sparsely labeled datasets with few annotations. Using a large image segmentation model as a teacher to train the efficient SSP, we leverage the strong correlations between labeled and unlabeled frames in the same training videos to obtain high-quality supervision on all frames. KD-SSP obtains a significant temporal consistency increase over the base image segmentation model of 12.5% and 6.7% TC on UAVid and RuralScapes respectively, with higher accuracy and comparable inference speed. On these aerial datasets, KD-SSP provides a superior segmentation quality and inference speed trade-off than other video methods proposed for general applications and shows considerably higher consistency. The code will be made publicly available upon acceptance.