ICCV 2025 论文列表

Generative videos have the potential to revolutionize game development by autonomously creating new content. In this paper, we present GameFactory, a framework for action-controlled scene-generalizable game video generation. We first address the fundamental challenge of action controllability by introducing GF-Minecraft, an action-annotated game video dataset without human bias, and developing an action control module that enables precise control over both keyboard and mouse inputs. We further extend to support autoregressive generation for unlimited-length interactive videos.More importantly, GameFactory tackles the critical challenge of scene-generalizable action control, which most existing methods fail to address. To enable the creation of entirely new and diverse games beyond fixed styles and scenes, we leverage the open-domain generative priors from pre-trained video diffusion models. To bridge the domain gap between open-domain priors and small-scale game datasets, we propose a multi-phase training strategy with a domain adapter that decouples game style learning from action control. This decoupling ensures that action control learning is no longer bound to specific game styles, thereby achieving scene-generalizable action control. Experimental results demonstrate that GameFactory effectively generates open-domain action-controllable game videos, representing a significant step forward in AI-driven game generation.

Modality exploration has been repeatedly mentioned in gait recognition, evolving from silhouette to parsing, mesh, point clouds, etc. These latest modalities agree that silhouette is less affected by background and clothing noises, but argue it loses too much valuable discriminative information. They seek to retain the strengths of silhouette while extracting more semantic or structural information through upstream estimation for better recognition. We agree with this principle but argue that these upstream estimations are usually unstable and the resulted modalities rely on pre-defined design. Moreover, the crucial aspect of modality generalization remains underexplored. To address this, we propose Gait-X to explore how to flexibly and stably develop a gait-specific generalized X modality from a frequency perspective. Specifically, 1) We replace upstream estimation with stable frequency decomposition and conduct a comprehensive analysis of how different frequencies impact modality and within-/cross-domain performance; 2) To enable flexible modality customization and mitigate the influence of noise and domain variations, we propose to remove irrelevant low-frequency noise and suppress high-frequency domain-specific information to form our X modality; 3) To further improve model generalization, we expand the representation across multiple frequencies to guide the model in balancing whole frequencies for enhanced generalization. Extensive experiments on CCPG, SUSTech1K, and CASIA-B datasets show superior generalization.

While most images shared on the web and social media platforms are encoded in standard dynamic range (SDR), many displays now can accommodate high dynamic range (HDR) content. Additionally, modern cameras can capture images in an HDR format but convert them to SDR to ensure maximum compatibility with existing workflows and legacy displays. To support both SDR and HDR, new encoding formats are emerging that store additional metadata in SDR images in the form of a gain map. When applied to the SDR image, the gain map recovers the HDR version of the image as needed. These gain maps, however, are typically down-sampled and encoded using standard image compression, such as JPEG and HEIC, which can result in unwanted artifacts. In this paper, we propose to use a lightweight multi-layer perceptron (MLP) network to encode the gain map. The MLP is optimized using the SDR image information as input and provides superior performance in terms of HDR reconstruction. Moreover, the MLP-based approach uses a fixed memory footprint (10 KB) and requires no additional adjustments to accommodate different image sizes or encoding parameters. We conduct extensive experiments on various MLP based HDR embedding strategies and demonstrate that our approach outperforms the current state-of-the-art.

We present GaSLight, a method that generates spatially-varying lighting from regular images. Our method proposes using HDR Gaussian Splats as light source representation, marking the first time regular images can serve as light sources in a 3D renderer. Our two-stage process first enhances the dynamic range of images plausibly and accurately by leveraging the priors embedded in diffusion models. Next, we employ Gaussian Splats to model 3D lighting, achieving spatially variant lighting. Our approach yields state-of-the-art results on HDR estimations and their applications in illuminating virtual objects and scenes. To facilitate the benchmarking of images as light sources, we introduce a novel dataset of calibrated and unsaturated HDR captures to evaluate images as light sources. We assess our method using a combination of our dataset and an existing dataset from the literature. The code to reproduce our method is available at https://lvsn.github.io/gaslight/.

We propose a 3D Gaussian splatting-based framework for outdoor relighting that leverages intrinsic image decomposition to precisely integrate sunlight, sky radiance, and indirect lighting from unconstrained photo collections. Unlike prior methods that compress the per-image global illumination into a single latent vector, our approach enables simultaneously diverse shading manipulation and the generation of dynamic shadow effects. This is achieved through three key innovations: (1) a residual-based sun visibility extraction method to accurately separate direct sunlight effects, (2) a region-based supervision framework with a structural consistency loss for physically interpretable and coherent illumination decomposition, and (3) a ray-tracing-based technique for realistic shadow simulation. Extensive experiments demonstrate that our framework synthesizes novel views with competitive fidelity against state-of-the-art relighting solutions and produces more natural and multifaceted illumination and shadow effects.

Training robot policies within a learned world model is trending due to the inefficiency of real-world interactions. The established image-based world models and policies have shown prior success, but lack robust geometric information that requires consistent spatial and physical understanding of the three-dimensional world, even pre-trained on internet-scale video sources. To this end, we propose a novel branch of world model named Gaussian World Model (GWM) for robotic manipulation, which reconstructs the future state by inferring the propagation of Gaussian primitives under the effect of robot actions. At its core is a latent Diffusion Transformer (DiT) combined with a 3D variational autoencoder, enabling fine-grained scene-level future state reconstruction with Gaussian Splatting. GWM can not only enhance the visual representation for imitation learning agent by self-supervised future prediction training, but can serve as a neural simulator that supports model-based reinforcement learning. Both simulated and real-world experiments depict that GWM can precisely predict future scenes conditioned on diverse robot actions, and can be further utilized to train policies that outperform the state-of-the-art by impressive margins, showcasing the initial data scaling potential of 3D world model.

Generalizing metric monocular depth estimation presents a significant challenge due to its ill-posed nature, while the entanglement between camera parameters and depth amplifies issues further, hindering multi-dataset training and zero-shot accuracy. This challenge is particularly evident in autonomous vehicles and mobile robotics, where data is collected with fixed camera setups, limiting the geometric diversity. Yet, this context also presents an opportunity: the fixed relationship between the camera and the ground plane imposes additional perspective geometry constraints, enabling depth regression via vertical image positions of objects. However, this cue is highly susceptible to overfitting, thus we propose a novel canonical representation that maintains consistency across varied camera setups, effectively disentangling depth from specific parameters and enhancing generalization across datasets. We also propose a novel architecture that adaptively and probabilistically fuses depths estimated via object size and vertical image position cues. A comprehensive evaluation demonstrates the effectiveness of the proposed approach on five autonomous driving datasets, achieving accurate metric depth estimation for varying resolutions, aspect ratios and camera setups. Notably, we achieve comparable accuracy to existing zero-shot methods, despite training on a single dataset with a single-camera setup. Project website: https://unizgfer-lamor.github.io/gvdepth/

Reconstructing a high-quality, animatable 3D human avatar with expressive facial and hand motions from a single image has gained significant attention due to its broad application potential. 3D human avatar reconstruction typically requires multi-view or monocular videos and training on individual IDs, which is both complex and time-consuming. Furthermore, limited by SMPLX's expressiveness, these methods often focus on body motion but struggle with facial expressions. To address these challenges, we first introduce an expressive human model (EHM) to enhance facial expression capabilities and develop an accurate tracking method. Based on this template model, we propose GUAVA, the first framework for fast animatable upper-body 3D Gaussian avatar reconstruction. We leverage inverse texture mapping and projection sampling techniques to infer Ubody (upper-body) Gaussians from a single image. The rendered images are refined through a neural refiner. Experimental results demonstrate that GUAVA significantly outperforms previous methods in rendering quality and offers significant speed improvements, with reconstruction times in the sub-second range ( 0.1s), and supports real-time animation and rendering.

Reinforcement learning with verifiable outcome rewards (RLVR) has effectively scaled up chain-of-thought (CoT) reasoning in large language models (LLMs). Yet, its efficacy in training vision-language model (VLM) agents for goal-directed action reasoning in visual environments is less established. This work investigates this problem through extensive experiments on complex card games, such as 24 points, and embodied tasks from ALFWorld. We find that when rewards are based solely on action outcomes, RL fails to incentivize CoT reasoning in VLMs, instead leading to a phenomenon we termed thought collapse, characterized by a rapid loss of diversity in the agent's thoughts, state-irrelevant and incomplete reasoning, and subsequent invalid actions, resulting in negative rewards. To counteract thought collapse, we highlight the necessity of process guidance and propose an automated corrector that evaluates and refines the agent's reasoning at each RL step. This simple and scalable GTR (Guided Thought Reinforcement) framework trains reasoning and action simultaneously without the need for dense, per-step human labeling. Our experiments demonstrate that GTR significantly enhances the performance and generalization of the LLaVA-7B model across various visual environments, achieving 3-5 times higher task success rates compared to SoTA models with notably smaller model sizes.

Low-light image enhancement (LLIE) aims to improve the visual quality of images captured under poor lighting conditions. In supervised LLIE tasks, there exists a significant yet often overlooked inconsistency between the overall brightness of an enhanced image and its ground truth counterpart, referred to as brightness mismatch in this study. Brightness mismatch negatively impact supervised LLIE models by misleading model training. However, this issue is largely neglected in current research. In this context, we propose the GT-mean loss, a simple yet effective loss function directly modeling the mean values of images from a probabilistic perspective.The GT-mean loss is flexible, as it extends existing supervised LLIE loss functions into the GT-mean form with minimal additional computational costs. Extensive experiments demonstrate that the incorporation of the GT-mean loss results in consistent performance improvements across various methods and datasets.

Timestamp prediction aims to determine when an image was captured using only visual information, supporting applications such as metadata correction, retrieval, and digital forensics. In outdoor scenarios, hourly estimates rely on cues like brightness, hue, and shadow positioning, while seasonal changes and weather inform date estimation. However, these visual cues significantly depend on geographic context, closely linking timestamp prediction to geo-localization. To address this interdependence, we introduce GT-Loc, a novel retrieval-based method that jointly predicts the capture time (hour and month) and geo-location (GPS coordinates) of an image. Our approach employs separate encoders for images, time, and location, aligning their embeddings within a shared high-dimensional feature space. Recognizing the cyclical nature of time, instead of conventional contrastive learning with hard positives and negatives, we propose a temporal metric-learning objective providing soft targets by modeling pairwise time differences over a cyclical toroidal surface. We present new benchmarks demonstrating that our joint optimization surpasses previous time prediction methods, even those using the ground-truth geo-location as an input during inference. Additionally, our approach achieves competitive results on standard geo-localization tasks, and the unified embedding space facilitates compositional and text-based image retrieval.

Image-based 3D generation has vast applications in robotics and gaming, where high-quality, diverse outputs and consistent 3D representations are crucial. However, existing methods have limitations: 3D diffusion models are limited by dataset scarcity and the absence of strong pre-trained priors, while 2D diffusion-based approaches struggle with geometric consistency. We propose a method that leverages 2D diffusion models' implicit 3D reasoning ability while ensuring 3D consistency via Gaussian-splatting-based geometric distillation. Specifically, the proposed Gaussian Splatting Decoder enforces 3D consistency by transforming SV3D latent outputs into an explicit 3D representation. Unlike SV3D, which only relies on implicit 2D representations for video generation, Gaussian Splatting explicitly encodes spatial and appearance attributes, enabling multi-view consistency through geometric constraints. These constraints correct view inconsistencies, ensuring robust geometric consistency. As a result, our approach simultaneously generates high-quality, multi-view-consistent images and accurate 3D models, providing a scalable solution for single-image-based 3D generation and bridging the gap between 2D Diffusion diversity and 3D structural coherence. Experimental results demonstrate state-of-the-art multi-view consistency and strong generalization across diverse datasets. Our code is available at https://github.com/MOMOYATW/GSV3D.

Generalizable surface reconstruction aims to recover the surface the scene from a sparse set of images in a feed-forward manner. Existing volume rendering-based methods evaluate numerous points along camera rays to infer the geometry, resulting in inefficient reconstruction. Recently, 3D Gaussian Splatting offers an alternative efficient scene representation and has inspired a series of surface reconstruction methods. However, these methods require dense views and cannot be generalized to new scenes. In this paper, we propose a novel surface reconstruction method with Gaussian splatting, named GSRecon, which leverages the advantages of rasterization-based rendering to achieve efficient reconstruction. To obtain accurate geometry representation, we propose a geometry-aware cross-view enhancement module to improve the unreliable geometry estimation in the current view by incorporating accurate geometric information from other views. To generate the fine-grained Gaussian primitives, we propose a hybrid cross-view feature aggregation module that integrates an efficient voxel branch and a fine-grained point branch to jointly capture cross-view geometric information. Subsequently, per-view depth maps are rendered using these Gaussian primitives and fused to obtain the final 3D surface. Extensive experiments on the DTU, BlendedMVS, and Tanks and Temples datasets validate that GSRecon achieves state-of-the-art performance efficiently. Code is available at https://github.com/hyangwinter/GSRecon.

In this paper, we present a novel benchmark, GSOT3D, that aims at facilitating development of generic 3D single object tracking (SOT) in the wild. Specifically, GSOT3D offers 620 sequences with 123K frames, and covers a wide selection of 54 object categories. Each sequence is offered with multiple modalities, including the point cloud (PC), RGB image, and depth. This allows GSOT3D to support various 3D tracking tasks, such as single-modal 3D SOT on PC and multi-modal 3D SOT on RGB-PC or RGB-D, and thus greatly broadens research directions for 3D object tracking. To provide high-quality per-frame 3D annotations, all sequences are labeled manually with multiple rounds of meticulous inspection and refinement. To our best knowledge, GSOT3D is the largest benchmark dedicated to various generic 3D object tracking tasks. To understand how existing 3D trackers perform and to provide comparisons for future research on GSOT3D, we assess eight representative point cloud-based tracking models. Our evaluation results exhibit that these models heavily degrade on GSOT3D, and more efforts are required for robust and generic 3D object tracking. Besides, to encourage future research, we present a simple yet effective generic 3D tracker, named PROT3D, that localizes the target object via a progressive spatial-temporal network and outperforms all current solutions by a large margin. By releasing GSOT3D, we expect to advance further 3D tracking in future research and applications. Our benchmark and model as well as the evaluation toolkit and results are publicly available at https://github.com/ailovejinx/GSOT3D.

Occupancy is crucial for autonomous driving, providing essential geometric priors for perception and planning. However, existing methods predominantly rely on LiDAR-based occupancy annotations, which limits scalability and prevents leveraging vast amounts of potential crowdsourced data for auto-labeling. To address this, we propose GS-Occ3D, a scalable vision-only framework that directly reconstructs occupancy. Vision-only occupancy reconstruction poses significant challenges due to sparse viewpoints, dynamic scene elements, severe occlusions, and long-horizon motion. Existing vision-based methods primarily rely on mesh representation, which suffer from incomplete geometry and additional post-processing, limiting scalability. To overcome these issues, GS-Occ3D optimizes an explicit occupancy representation using an Octree-based Gaussian Surfel formulation, ensuring efficiency and scalability. Additionally, we decompose scenes into static background, ground, and dynamic objects, enabling tailored modeling strategies: (1) Ground is explicitly reconstructed as a dominant structural element, significantly improving large-area consistency; (2) Dynamic vehicles are separately modeled to better capture motion-related occupancy patterns. Extensive experiments on the Waymo dataset demonstrate that GS-Occ3D achieves state-of-the-art geometry reconstruction results. By curating vision-only binary occupancy labels from diverse urban scenes, we show their effectiveness for downstream occupancy models on Occ3D-Waymo and superior zero-shot generalization on Occ3D-nuScenes. It highlights the potential of large-scale vision-based occupancy reconstruction as a new paradigm for scalable auto-labeling. Project Page: https://gs-occ3d.github.io/

In this paper, we introduce GS-LIVM, a real-time photo-realistic LiDAR-Inertial-Visual mapping framework with Gaussian Splatting tailored for outdoor scenes. Compared to existing methods based on Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), our approach enables real-time photo-realistic mapping while ensuring high-quality image rendering in large-scale unbounded outdoor environments. In this work, Gaussian Process Regression (GPR) is employed to mitigate the issues resulting from sparse and unevenly distributed LiDAR observations. The voxel-based 3D Gaussians map representation facilitates real-time dense mapping in large outdoor environments with acceleration governed by custom CUDA kernels. Moreover, the overall framework is designed in a covariance-centered manner, where the estimated covariance is used to initialize the scale and rotation of 3D Gaussians, as well as update the parameters of the GPR. We evaluate our algorithm on several outdoor datasets, and the results demonstrate that our method achieves state-of-the-art performance in terms of mapping efficiency and rendering quality. The source code is available on GitHub.

Gaussian Splatting (GS) has emerged as an effective representation for photorealistic rendering, but the underlying geometry, material, and lighting remain entangled, hindering scene editing. Existing GS-based methods struggle to disentangle these components under non-Lambertian conditions, especially in the presence of specularities and shadows. We propose GS-ID, an end-to-end framework for illumination decomposition that integrates adaptive light aggregation with diffusion-based material priors. In addition to a learnable environment map for ambient illumination, we model spatially-varying local lighting using anisotropic spherical Gaussian mixtures (SGMs) that are jointly optimized with scene content. To better capture cast shadows, we associate each splat with a learnable unit vector that encodes shadow directions from multiple light sources, further improving material and lighting estimation. By combining SGMs with intrinsic priors from diffusion models, GS-ID significantly reduces ambiguity in light-material-geometry interactions and achieves state-of-the-art performance on inverse rendering and relighting benchmarks. Experiments also demonstrate the effectiveness of GS-ID for downstream applications such as relighting and scene composition.

Sign Language Video Generation (SLVG) aims to transform sign language sequences into natural and fluent sign language videos. Existing SLVG methods lack geometric modeling of human anatomical structures, leading to anatomically implausible and temporally inconsistent generation. To address these challenges, we propose a novel SLVG framework: Geometry-Aware Region Refinement (GReg). GReg uses 3D geometric information (such as normal maps and gradient maps) from the SMPL-X model to ensure anatomical and temporal consistency.To fully leverage the 3D geometric priors, we propose two novel methods: 1) Regional Prior Generation, which uses regional expert networks to generate target-structured regions as generation priors; 2) Gradient-Enhanced Refinement, which guides the refinement of detailed structures in key regions using gradient features.Furthermore, we enhance visual realism in key regions through adversarial training on both these regions and their gradient maps.Experimental results demonstrate that GReg achieves state-of-the-art performance with superior structural accuracy and temporal consistency.