CVPR 2025 Papers

Novel-view synthesis techniques achieve impressive results for static scenes but struggle when faced with the inconsistencies inherent to casual capture settings: varying illumination, scene motion, and other unintended effects that are difficult to model explicitly. We present an approach for leveraging generative video models to simulate the inconsistencies in the world that can occur during capture. We use this process, along with existing multi-view datasets, to create synthetic data for training a multi-view harmonization network that is able to reconcile inconsistent observations into a consistent 3D scene. We demonstrate that our world-simulation strategy significantly outperforms traditional augmentation methods in handling real-world scene variations, thereby enabling highly accurate static 3D reconstructions in the presence of a variety of challenging inconsistencies.

Text-based 3D human motion editing is a critical yet challenging task in computer vision and graphics. While training-free approaches have been explored, the recent release of the MotionFix dataset, which includes source-text-motion triplets, has opened new avenues for training, yielding promising results. However, existing methods struggle with precise control, often leading to misalignment between motion semantics and language instructions. In this paper, we introduce a related task --- motion similarity prediction --- and propose a multi-task training paradigm, where we train the model jointly on motion editing and motion similarity prediction to foster the learning of semantically meaningful representations. To complement this task, we design an advanced Diffusion-Transformer-based architecture that separately handles motion similarity prediction and motion editing. Extensive experiments demonstrate the state-of-the-art performance of our approach in both editing alignment and fidelity.

Integrating large language models (LLMs) into autonomous driving has attracted significant attention with the hope of improving generalization and explainability. However, existing methods often focus on either driving or vision-language understanding but achieving both high driving performance and extensive language understanding remains challenging. In addition, the dominant approach to tackle vision-language understanding is using visual question answering. However, for autonomous driving, this is only useful if it is aligned with the action space. Otherwise, the model's answers could be inconsistent with its behavior. Therefore, we propose a model that can handle three different tasks: (1) closed-loop driving, (2) vision-language understanding, and (3) language-action alignment. Our model SimLingo is based on a vision language model (VLM) and works using only camera, excluding expensive sensors like LiDAR. SimLingo obtains state-of-the-art performance on the widely used CARLA simulator on the Bench2Drive benchmark and is the winning entry at the CARLA challenge 2024. Additionally, we achieve strong results in a wide variety of language-related tasks while maintaining high driving performance.

While modern visual recognition systems have made significant advancements, many continue to struggle with the open problem of learning from few exemplars. This paper focuses on the task of object detection in the setting where object classes follow a natural long-tailed distribution. Existing methods for long-tailed detection resort to external ImageNet labels to augment the low-shot training instances. However, such dependency on a large labeled database has limited utility in practical scenarios. We propose a versatile and scalable approach to leverage optional unlabeled images, which are easy to collect without the burden of human annotations. Our SimLTD framework is straightforward and intuitive, and consists of three simple steps: (1) pre-training on abundant head classes; (2) transfer learning on scarce tail classes; and (3) fine-tuning on a sampled set of both head and tail classes. Our approach can be viewed as an improved head-to-tail model transfer paradigm without the added complexities of meta-learning or knowledge distillation, as was required in past research. By harnessing supplementary unlabeled images, without extra image labels, SimLTD establishes new record results on the challenging LVIS v1 benchmark across both supervised and semi-supervised settings.

We introduce SimAvatar, a framework designed to generate simulation-ready clothed 3D human avatars from a text prompt. Current text-driven human avatar generation methods either model hair, clothing and human body using a unified geometry or produce hair and garments that are not easily adaptable for simulation within existing graphics pipelines. The primary challenge lies in representing the hair and garment geometry in a way that allows leveraging established prior knowledge from foundational image diffusion models (e.g., Stable Diffusion) while being simulation-ready using either physics or neural simulators. To address this task, we propose a two-stage framework that combines the flexibility of 3D Gaussians with simulation-ready hair strands and garment meshes. Specifically, we first leverage two text-conditioned diffusion models to generate garment mesh and hair strands from the given text prompt. To leverage prior knowledge from foundational diffusion models, we attach 3D Gaussians to the body mesh, garment mesh, as well as hair strands and learn the avatar appearance through optimization. To drive the avatar given a pose sequence, we first apply physics simulators onto the garment meshes and hair strands. We then transfer the motion onto 3D Gaussians through carefully designed mechanism for different body parts. As a result, our synthesized avatars have vivid texture and realistic dynamic motion. To the best of our knowledge, our method is the first to produce highly realistic, fully simulation-ready 3D avatars, surpassing the capabilities of current approaches.

Modeling spatial-temporal interactions among neighboring agents is at the heart of multi-agent problems such as motion forecasting and crowd navigation. Despite notable progress, it remains unclear to which extent modern representations can capture the causal relationships behind agent interactions. In this work, we take an in-depth look at the causal awareness of these representations, from computational formalism to real-world practice. First, we revisit the notion of non-causal robustness studied in the recent CausalAgents benchmark. We show that existing representations are already partially resilient to perturbations of non-causal agents, and yet modeling indirect causal effects involving mediator agents remains challenging. To address this challenge, we introduce a metric learning approach that regularizes latent representations with causal annotations. Our controlled experiments show that this approach not only leads to higher degrees of causal awareness but also yields stronger out-of-distribution robustness. To further operationalize it in practice, we propose a sim-to-real causal transfer method via cross-domain multi-task learning. Experiments on trajectory prediction datasets show that our method can significantly boost generalization, even in the absence of real-world causal annotations, where we acquire higher prediction accuracy by only using 25% of real-world data. We hope our work provides a new perspective on the challenges and potential pathways toward causally-aware representations of multi-agent interactions. Our code is available in supplementary materials. Our code is available at https://github.com/vita-epfl/CausalSim2Real.

Text-to-image diffusion models have achieved remarkable success in generating high-quality contents from text prompts. However, their reliance on publicly available data and the growing trend of data sharing for fine-tuning make these models particularly vulnerable to data poisoning attacks. In this work, we introduce the Silent Branding Attack, a novel data poisoning method that manipulates text-to-image diffusion models to generate images containing specific brand logos or symbols without any text triggers. We find that when certain visual patterns are repeatedly in the training data, the model learns to reproduce them naturally in its outputs, even without prompt mentions. Leveraging this, we develop an automated data poisoning algorithm that unobtrusively injects logos into original images, ensuring they blend naturally and remain undetected. Models trained on this poisoned dataset generate images containing logos without degrading image quality or text alignment. We experimentally validate our silent branding attack across two realistic settings on large-scale high-quality image datasets and style personalization datasets, achieving high success rates even without a specific text trigger. Human evaluation and quantitative metrics including logo detection show that our method can stealthily embed logos.

Advances in talking-head animation based on Latent Diffusion Models (LDM) enable the creation of highly realistic, synchronized videos. These fabricated videos are indistinguishable from real ones, increasing the risk of potential misuse for scams, political manipulation, and misinformation. Hence, addressing these ethical concerns has become a pressing issue in AI security. Recent proactive defense studies focused on countering LDM-based models by adding perturbations to portraits. However, these methods are ineffective at protecting reference portraits from advanced image-to-video animation. The limitations are twofold: 1) they fail to prevent images from being manipulated by audio signals, and 2) diffusion-based purification techniques can effectively eliminate protective perturbations. To address these challenges, we propose Silencer, a two-stage method designed to proactively protect the privacy of portraits. First, a nullifying loss is proposed to ignore audio control in talking-head generation. Second, we apply anti-purification loss in LDM to optimize the inverted latent feature to generate robust perturbations. Extensive experiments demonstrate the effectiveness of Silencer in proactively protecting portrait privacy. We hope this work will raise awareness among the AI security community regarding critical ethical issues related to talking-head generation techniques. Code: https://github.com/yuangan/Silencer.

Building Graphical User Interface (GUI) assistants holds significant promise for enhancing human workflow productivity. While most agents are language-based, relying on closed-source API with text-rich meta-information (e.g., HTML or accessibility tree), they show limitations in perceiving UI visuals as humans do, highlighting the need for GUI visual agents.In this work, we develop a vision-language-action model in the digital world, namely "Our Model," which features the following innovations:1. **UI-Guided Visual Token Selection** to reduce computational costs by formulating screenshots as a UI-connected graph, adaptively identifying their redundant relationships and serving as the criteria for token selection during self-attention blocks. 2. **Interleaved Vision-Language-Action Streaming** that flexibly unifies diverse needs within GUI tasks, enabling effective management of visual-action history in navigation or pairing multi-turn query-action sequences per screenshot to enhance training efficiency. 3. **Small-Scale High-Quality GUI Instruction-Following Datasets** by careful data curation and employing a resampling strategy to address significant data type imbalances. With the above components, our model, a lightweight 2B model using 256K data, achieves a strong 75.1% accuracy in zero-shot screenshot grounding. Its UI-guided token selection further reduces 33% of redundant visual tokens during training and speeds up performance by 1.4x. Navigation experiments across web, mobile, and online environments further underscore the effectiveness and potential of our model in advancing GUI visual agents.

Reconstructing dynamic radiance fields from video clips is challenging, especially when entertainment videos like TV shows are given. Many challenges make the reconstruction difficult due to (1) actors occluding with each other and having diverse facial expressions, (2) cluttered stages, and (3) small baseline views or sudden shot changes. To address these issues, we present ShowMak3r, a comprehensive reconstruction pipeline that allows the editing of scenes like how video clips are made in a production control room. In ShowMak3r, a 3DLocator module locates recovered actors on the stage using depth prior, and estimates unseen human poses via interpolation. The proposed ShotMatcher module then tracks the actors under shot changes. Furthermore, ShowMak3r introduces a face-fitting network that dynamically recovers the actors' expressions. Experiments on Sitcoms3D dataset show that our pipeline can reassemble TV show scenes with new cameras at different timestamps. We also demonstrate that ShowMak3r enables interesting applications such as synthetic shot-making, actor relocation, insertion, deletion, and pose manipulation. Project page : https://nstar1125.github.io/showmak3r

The goal of this work is to generate step-by-step visual instructions in the form of a sequence of images, given an input image that provides the scene context and the sequence of textual instructions. This is a challenging problem as it requires generating multi-step image sequences to achieve a complex goal while being grounded in a specific environment. Part of the challenge stems from the lack of large-scale training data for this problem. The contribution of this work is thus three-fold. First, we introduce an automatic approach for collecting large step-by-step visual instruction training data from instructional videos. We apply this approach to one million videos and create a large-scale, high-quality dataset of 0.6M sequences of image-text pairs. Second, we develop and train ShowHowTo, a video diffusion model capable of generating step-by-step visual instructions consistent with the provided input image. Third, we evaluate the generated image sequences across three dimensions of accuracy (step, scene, and task) and show our model achieves state-of-the-art results on all of them. Our code, dataset, and trained models are publicly available.

Modern deep neural networks have now reached human-level performance across a variety of tasks. However, unlike humans they lack the ability to explain their decisions by showing where and telling what concepts guided them. In this work, we present a unified framework for transforming any vision neural network into a spatially and conceptually interpretable model. We introduce a spatially-aware concept bottleneck layer that projects "black-box" features of pre-trained backbone models into interpretable concept maps, without requiring human labels. By training a classification layer over this bottleneck, we obtain a self-explaining model that articulates which concepts most influenced its prediction, along with heatmaps that ground them in the input image. Accordingly, we name this method "Spatially-Aware and Label-Free Concept Bottleneck Model" (SALF-CBM). Our results show that the proposed SALF-CBM: (1) Outperforms non-spatial CBM methods, as well as the original backbone, on a variety of classification tasks; (2) Produces high-quality spatial explanations, outperforming widely used heatmap-based methods on a zero-shot segmentation task; (3) Facilitates model exploration and debugging, enabling users to query specific image regions and refine the model's decisions by locally editing its concept maps.

Medical image segmentation remains challenging due to the vast diversity of anatomical structures, imaging modalities, and segmentation tasks. While deep learning has made significant advances, current approaches struggle to generalize as they require task-specific training or fine-tuning on unseen classes. We present Iris, a novel In-context Reference Image guided Segmentation framework that enables flexible adaptation to novel tasks through the use of reference examples without fine-tuning. At its core, Iris features a lightweight context task encoding module that distills task-specific information from reference context image-label pairs. This rich context embedding information is used to guide the segmentation of target objects. Given a decoupled architecture on 3D data processing, Iris supports diverse inference strategies including one-shot inference, context example ensemble, object-level context example retrieval, and in-context tuning. Through comprehensive evaluation across twelve datasets, we demonstrate that Iris performs strongly compared to specialized supervised models on in-distribution tasks. On seven held-out dataset, Iris shows superior generalization to out-of-distribution data and unseen classes. Further, Iris's task encoding module can automatically discover anatomical relationships across datasets and modalities, offering insights into cross-modality medical objects without explicit anatomical supervision.

Current diffusion-based text-to-video methods are limited to producing short video clips of a single shot and lack the capability to generate multi-shot videos with discrete transitions where the same character performs distinct activities across the same or different backgrounds. To address this limitation we propose a framework that includes a dataset collection pipeline and architectural extensions to video diffusion models to enable text-to-multi-shot video generation. Our approach enables generation of multi-shot videos as a single video with full attention across all frames of all shots, ensuring character and background consistency, and allows users to control the number, duration, and content of shots through shot-specific conditioning. This is achieved by incorporating a transition token into the text-to-video model to control at which frames a new shot begins and a local attention masking strategy which controls the transition token's effect and allows shot-specific prompting. To obtain training data we propose a novel data collection pipeline to construct a multi-shot video dataset from existing single-shot video datasets. Extensive experiments demonstrate that fine-tuning a pre-trained text-to-video model for a few thousand iterations is enough for the model to subsequently be able to generate multi-shot videos with shot-specific control, outperforming the baselines. You can find more details in our webpage.

While virtual try-on for clothes and shoes with diffusion models has gained attraction, virtual try-on for ornaments, such as bracelets, rings, earrings, and necklaces, remains largely unexplored. Due to the intricate tiny patterns and repeated geometric sub-structures in most ornaments, it is much more difficult to guarantee identity and appearance consistency under large pose and scale variances between ornaments and models. This paper proposes the task of virtual try-on for ornaments and presents a method to improve the geometric and appearance preservation of ornament virtual try-ons. Specifically, we estimate an accurate wearing mask to improve the alignments between ornaments and models in an iterative scheme alongside the denoising process. To preserve structure details, we further regularize attention layers to map the reference ornament mask to the wearing mask in an implicit way. Experiment results demonstrate that our method successfully wears ornaments from reference images onto target models, handling substantial differences in scale and pose while preserving identity and achieving realistic visual effects.

Camouflaged Object Detection (COD) seeks to distinguish objects from their highly similar backgrounds. Existing work has essentially focused on isolating camouflaged objects from the environment, demonstrating ever-improving performance but at the cost of extensive annotations and complex optimizations. In this paper, we diverge from this paradigm and shift the lens to isolating the salient environment from the camouflaged object. We introduce EASE, an Environment-Aware unSupErvised COD framework that identifies the environment by referencing an environment prototype library and detects camouflaged objects by inverting the retrieved environmental features. Specifically, our approach (DiffPro) uses large multimodal models, diffusion models, and vision-foundation models to construct the environment prototype library. To retrieve environments from the library and refrain from confusing foreground and background, we incorporate three retrieval schemes: Kernel Density Estimation-based Adaptive Threshold (KDE-AT), Global-to-Local pixel-level retrieval (G2L), and Self-Retrieval (SR). Our experiments demonstrate significant improvements over current unsupervised methods, with EASE achieving an average gain of over 10% on the COD10K dataset. When integrated with SAM, EASE surpasses prompt-based segmentation approaches and performs competitively with state-of-the-art fully-supervised methods. Code is available at https://github.com/xiaohainku/EASE.

We propose SharpDepth, a novel approach to monocular metric depth estimation that combines the metric accuracy of discriminative depth estimation methods (e.g., Metric3D, UniDepth) with the fine-grained boundary sharpness typically achieved by generative methods (e.g., Marigold, Lotus). Traditional discriminative models trained on real-world data with sparse ground-truth depth can accurately predict metric depth but often produce over-smoothed or low-detail depth maps. Generative models, in contrast, are trained on synthetic data with dense ground truth, generating depth maps with sharp boundaries yet only providing relative depth with low accuracy. Our approach bridges these limitations by integrating metric accuracy with detailed boundary preservation, resulting in depth predictions that are both metrically precise and visually sharp. Our extensive zero-shot evaluations on standard depth estimation benchmarks confirm SharpDepth's effectiveness, showing its ability to achieve both high depth accuracy and detailed representation, making it well-suited for applications requiring high-quality depth perception across diverse, real-world environments.

Advancements in text-to-image diffusion models have led to significant progress in fast 3D content creation. One common approach is to generate a set of multi-view images of an object, and then reconstruct it into a 3D model. However, this approach bypasses the use of a native 3D representation of the object and is hence prone to geometric artifacts and limited in controllability and manipulation capabilities. An alternative approach involves native 3D generative models that directly produce 3D representations. These models, however, are typically limited in their resolution, resulting in lower quality 3D objects. In this work, we bridge the quality gap between methods that directly generate 3D representations and ones that reconstruct 3D objects from multi-view images. We introduce a multi-view to multi-view diffusion model called Sharp-It, which takes a 3D consistent set of multi-view images rendered from a low-quality object and enriches its geometric details and texture. The diffusion model operates on the multi-view set in parallel, in the sense that it shares features across the generated views. A high-quality 3D model can then be reconstructed from the enriched multi-view set. By leveraging the advantages of both 2D and 3D approaches, our method offers an efficient and controllable method for high-quality 3D content creation. We demonstrate that Sharp-It enables various 3D applications, such as fast synthesis, editing, and controlled generation, while attaining high-quality assets.