Javier Romero

Wojciech Zielonka, Timur Bagautdinov, Shunsuke Saito et al.

We present Drivable 3D Gaussian Avatars (D3GA), a multi-layered 3D controllable model for human bodies that utilizes 3D Gaussian primitives embedded into tetrahedral cages. The advantage of using cages compared to commonly employed linear blend skinning (LBS) is that primitives like 3D Gaussians are naturally re-oriented and their kernels are stretched via the deformation gradients of the encapsulating tetrahedron. Additional offsets are modeled for the tetrahedron vertices, effectively decoupling the low-dimensional driving poses from the extensive set of primitives to be rendered. This separation is achieved through the localized influence of each tetrahedron on 3D Gaussians, resulting in improved optimization. Using the cage-based deformation model, we introduce a compositional pipeline that decomposes an avatar into layers, such as garments, hands, or faces, improving the modeling of phenomena like garment sliding. These parts can be conditioned on different driving signals, such as keypoints for facial expressions or joint-angle vectors for garments and the body. Our experiments on two multi-view datasets with varied body shapes, clothes, and motions show higher-quality results. They surpass PSNR and SSIM metrics of other SOTA methods using the same data while offering greater flexibility and compactness.

Susana Hahn, Cedric Martens, Amade Nemes et al.

We are interested in automating reasoning with and about study regulations, catering to various stakeholders, ranging from administrators, over faculty, to students at different stages. Our work builds on an extensive analysis of various study programs at the University of Potsdam. The conceptualization of the underlying principles provides us with a formal account of study regulations. In particular, the formalization reveals the properties of admissible study plans. With these at end, we propose an encoding of study regulations in Answer Set Programming that produces corresponding study plans. Finally, we show how this approach can be extended to a generic user interface for exploring study plans.

Leire Benito-Del-Valle, Artzai Picón, Daniel Mugica et al.

Herbicide field trials require accurate identification of plant species and assessment of herbicide-induced damage across diverse environments. While general-purpose vision foundation models have shown promising results in complex visual domains, their performance can be limited in agriculture, where fine-grained distinctions between species and damage types are critical. In this work, we adapt a general-purpose vision foundation model to herbicide trial characterization. Trained using a self-supervised learning approach on a large, curated agricultural dataset, the model learns rich and transferable representations optimized for herbicide trials images. Our domain-specific model significantly outperforms the best general-purpose foundation model in both species identification (F1 score improvement from 0.91 to 0.94) and damage classification (from 0.26 to 0.33). Under unseen conditions (new locations and other time), it achieves even greater gains (species identification from 0.56 to 0.66; damage classification from 0.17 to 0.27). In domain-shift scenarios, such as drone imagery, it maintains strong performance (species classification from 0.49 to 0.60). Additionally, we show that domain-specific pretraining enhances segmentation accuracy, particularly in low-annotation regimes. An annotation-efficiency analysis reveals that, under unseen conditions, the domain-specific model achieves 5.4% higher F1 score than the general-purpose model, while using 80% fewer labeled samples. These results demonstrate the generalization capabilities of domain-specific foundation models and their potential to significantly reduce manual annotation efforts, offering a scalable and automated solution for herbicide trial analysis.

Lukas Balles, Javier Romero, Philipp Hennig

Mini-batch stochastic gradient descent and variants thereof have become standard for large-scale empirical risk minimization like the training of neural networks. These methods are usually used with a constant batch size chosen by simple empirical inspection. The batch size significantly influences the behavior of the stochastic optimization algorithm, though, since it determines the variance of the gradient estimates. This variance also changes over the optimization process; when using a constant batch size, stability and convergence is thus often enforced by means of a (manually tuned) decreasing learning rate schedule. We propose a practical method for dynamic batch size adaptation. It estimates the variance of the stochastic gradients and adapts the batch size to decrease the variance proportionally to the value of the objective function, removing the need for the aforementioned learning rate decrease. In contrast to recent related work, our algorithm couples the batch size to the learning rate, directly reflecting the known relationship between the two. On popular image classification benchmarks, our batch size adaptation yields faster optimization convergence, while simultaneously simplifying learning rate tuning. A TensorFlow implementation is available.

Evonne Ng, Javier Romero, Timur Bagautdinov et al.

We present a framework for generating full-bodied photorealistic avatars that gesture according to the conversational dynamics of a dyadic interaction. Given speech audio, we output multiple possibilities of gestural motion for an individual, including face, body, and hands. The key behind our method is in combining the benefits of sample diversity from vector quantization with the high-frequency details obtained through diffusion to generate more dynamic, expressive motion. We visualize the generated motion using highly photorealistic avatars that can express crucial nuances in gestures (e.g. sneers and smirks). To facilitate this line of research, we introduce a first-of-its-kind multi-view conversational dataset that allows for photorealistic reconstruction. Experiments show our model generates appropriate and diverse gestures, outperforming both diffusion- and VQ-only methods. Furthermore, our perceptual evaluation highlights the importance of photorealism (vs. meshes) in accurately assessing subtle motion details in conversational gestures. Code and dataset available online.

Zhaoxi Chen, Gyeongsik Moon, Kaiwen Guo et al.

Existing photorealistic relightable hand models require extensive identity-specific observations in different views, poses, and illuminations, and face challenges in generalizing to natural illuminations and novel identities. To bridge this gap, we present URHand, the first universal relightable hand model that generalizes across viewpoints, poses, illuminations, and identities. Our model allows few-shot personalization using images captured with a mobile phone, and is ready to be photorealistically rendered under novel illuminations. To simplify the personalization process while retaining photorealism, we build a powerful universal relightable prior based on neural relighting from multi-view images of hands captured in a light stage with hundreds of identities. The key challenge is scaling the cross-identity training while maintaining personalized fidelity and sharp details without compromising generalization under natural illuminations. To this end, we propose a spatially varying linear lighting model as the neural renderer that takes physics-inspired shading as input feature. By removing non-linear activations and bias, our specifically designed lighting model explicitly keeps the linearity of light transport. This enables single-stage training from light-stage data while generalizing to real-time rendering under arbitrary continuous illuminations across diverse identities. In addition, we introduce the joint learning of a physically based model and our neural relighting model, which further improves fidelity and generalization. Extensive experiments show that our approach achieves superior performance over existing methods in terms of both quality and generalizability. We also demonstrate quick personalization of URHand from a short phone scan of an unseen identity.

Shaofei Wang, Tomas Simon, Igor Santesteban et al.

We propose Relightable Full-Body Gaussian Codec Avatars, a new approach for modeling relightable full-body avatars with fine-grained details including face and hands. The unique challenge for relighting full-body avatars lies in the large deformations caused by body articulation and the resulting impact on appearance caused by light transport. Changes in body pose can dramatically change the orientation of body surfaces with respect to lights, resulting in both local appearance changes due to changes in local light transport functions, as well as non-local changes due to occlusion between body parts. To address this, we decompose the light transport into local and non-local effects. Local appearance changes are modeled using learnable zonal harmonics for diffuse radiance transfer. Unlike spherical harmonics, zonal harmonics are highly efficient to rotate under articulation. This allows us to learn diffuse radiance transfer in a local coordinate frame, which disentangles the local radiance transfer from the articulation of the body. To account for non-local appearance changes, we introduce a shadow network that predicts shadows given precomputed incoming irradiance on a base mesh. This facilitates the learning of non-local shadowing between the body parts. Finally, we use a deferred shading approach to model specular radiance transfer and better capture reflections and highlights such as eye glints. We demonstrate that our approach successfully models both the local and non-local light transport required for relightable full-body avatars, with a superior generalization ability under novel illumination conditions and unseen poses.

Jinhyung Park, Javier Romero, Shunsuke Saito et al.

Parametric body models offer expressive 3D representation of humans across a wide range of poses, shapes, and facial expressions, typically derived by learning a basis over registered 3D meshes. However, existing human mesh modeling approaches struggle to capture detailed variations across diverse body poses and shapes, largely due to limited training data diversity and restrictive modeling assumptions. Moreover, the common paradigm first optimizes the external body surface using a linear basis, then regresses internal skeletal joints from surface vertices. This approach introduces problematic dependencies between internal skeleton and outer soft tissue, limiting direct control over body height and bone lengths. To address these issues, we present ATLAS, a high-fidelity body model learned from 600k high-resolution scans captured using 240 synchronized cameras. Unlike previous methods, we explicitly decouple the shape and skeleton bases by grounding our mesh representation in the human skeleton. This decoupling enables enhanced shape expressivity, fine-grained customization of body attributes, and keypoint fitting independent of external soft-tissue characteristics. ATLAS outperforms existing methods by fitting unseen subjects in diverse poses more accurately, and quantitative evaluations show that our non-linear pose correctives more effectively capture complex poses compared to linear models.

Arvid Becker, Pedro Cabalar, Martin Diéguez et al.

We develop a computational approach to Metric Answer Set Programming (ASP) to allow for expressing quantitative temporal constrains, like durations and deadlines. A central challenge is to maintain scalability when dealing with fine-grained timing constraints, which can significantly exacerbate ASP's grounding bottleneck. To address this issue, we leverage extensions of ASP with difference constraints, a simplified form of linear constraints, to handle time-related aspects externally. Our approach effectively decouples metric ASP from the granularity of time, resulting in a solution that is unaffected by time precision.

Javier Romero, Torsten Schaub, Klaus Strauch

The representation of a dynamic problem in ASP usually boils down to using copies of variables and constraints, one for each time stamp, no matter whether it is directly encoded or via an action or temporal language. The multiplication of variables and constraints is commonly done during grounding and the solver is completely ignorant about the temporal relationship among the different instances. On the other hand, a key factor in the performance of today's ASP solvers is conflict-driven constraint learning. Our question is now whether a constraint learned for particular time steps can be generalized and reused at other time stamps, and ultimately whether this enhances the overall solver performance on temporal problems. Knowing full well the domain of time, we study conditions under which learned dynamic constraints can be generalized. We propose a simple translation of the original logic program such that, for the translated programs, the learned constraints can be generalized to other time points. Additionally, we identify a property of temporal problems that allows us to generalize all learned constraints to all time steps. It turns out that this property is satisfied by many planning problems. Finally, we empirically evaluate the impact of adding the generalized constraints to an ASP solver. Under consideration in Theory and Practice of Logic Programming (TPLP).

Javier Romero, Dimitrios Tzionas, Michael J. Black

Humans move their hands and bodies together to communicate and solve tasks. Capturing and replicating such coordinated activity is critical for virtual characters that behave realistically. Surprisingly, most methods treat the 3D modeling and tracking of bodies and hands separately. Here we formulate a model of hands and bodies interacting together and fit it to full-body 4D sequences. When scanning or capturing the full body in 3D, hands are small and often partially occluded, making their shape and pose hard to recover. To cope with low-resolution, occlusion, and noise, we develop a new model called MANO (hand Model with Articulated and Non-rigid defOrmations). MANO is learned from around 1000 high-resolution 3D scans of hands of 31 subjects in a wide variety of hand poses. The model is realistic, low-dimensional, captures non-rigid shape changes with pose, is compatible with standard graphics packages, and can fit any human hand. MANO provides a compact mapping from hand poses to pose blend shape corrections and a linear manifold of pose synergies. We attach MANO to a standard parameterized 3D body shape model (SMPL), resulting in a fully articulated body and hand model (SMPL+H). We illustrate SMPL+H by fitting complex, natural, activities of subjects captured with a 4D scanner. The fitting is fully automatic and results in full body models that move naturally with detailed hand motions and a realism not seen before in full body performance capture. The models and data are freely available for research purposes in our website (http://mano.is.tue.mpg.de).

Soubhik Sanyal, Alex Vorobiov, Timo Bolkart et al.

Synthesizing images of a person in novel poses from a single image is a highly ambiguous task. Most existing approaches require paired training images; i.e. images of the same person with the same clothing in different poses. However, obtaining sufficiently large datasets with paired data is challenging and costly. Previous methods that forego paired supervision lack realism. We propose a self-supervised framework named SPICE (Self-supervised Person Image CrEation) that closes the image quality gap with supervised methods. The key insight enabling self-supervision is to exploit 3D information about the human body in several ways. First, the 3D body shape must remain unchanged when reposing. Second, representing body pose in 3D enables reasoning about self occlusions. Third, 3D body parts that are visible before and after reposing, should have similar appearance features. Once trained, SPICE takes an image of a person and generates a new image of that person in a new target pose. SPICE achieves state-of-the-art performance on the DeepFashion dataset, improving the FID score from 29.9 to 7.8 compared with previous unsupervised methods, and with performance similar to the state-of-the-art supervised method (6.4). SPICE also generates temporally coherent videos given an input image and a sequence of poses, despite being trained on static images only.

Roland Kaminski, Javier Romero, Torsten Schaub et al.

Answer Set Programming (ASP) has become a popular and quite sophisticated approach to declarative problem solving. This is arguably due to its attractive modeling-grounding-solving workflow that provides an easy approach to problem solving, even for laypersons outside computer science. Unlike this, the high degree of sophistication of the underlying technology makes it increasingly hard for ASP experts to put ideas into practice. For addressing this issue, this tutorial aims at enabling users to build their own ASP-based systems. More precisely, we show how the ASP system CLINGO can be used for extending ASP and for implementing customized special-purpose systems. To this end, we propose two alternatives. We begin with a traditional AI technique and show how meta programming can be used for extending ASP. This is a rather light approach that relies on CLINGO's reification feature to use ASP itself for expressing new functionalities. Unlike this, the major part of this tutorial uses traditional programming (in PYTHON) for manipulating CLINGO via its application programming interface. This approach allows for changing and controlling the entire model-ground-solve workflow of ASP. Central to this is CLINGO's new Application class that allows us to draw on CLINGO's infrastructure by customizing processes similar to the one in CLINGO. For instance, we may engage manipulations to programs' abstract syntax trees, control various forms of multi-shot solving, and set up theory propagators for foreign inferences. Another cross-sectional structure, spanning meta as well as application programming, is CLINGO's intermediate format, ASPIF, that specifies the interface among the underlying grounder and solver. We illustrate the aforementioned concepts and techniques throughout this tutorial by means of examples and several non-trivial case-studies.

Pedro Cabalar, Jorge Fandinno, Javier Garea et al.

We describe eclingo, a solver for epistemic logic programs under Gelfond 1991 semantics built upon the Answer Set Programming system clingo. The input language of eclingo uses the syntax extension capabilities of clingo to define subjective literals that, as usual in epistemic logic programs, allow for checking the truth of a regular literal in all or in some of the answer sets of a program. The eclingo solving process follows a guess and check strategy. It first generates potential truth values for subjective literals and, in a second step, it checks the obtained result with respect to the cautious and brave consequences of the program. This process is implemented using the multi-shot functionalities of clingo. We have also implemented some optimisations, aiming at reducing the search space and, therefore, increasing eclingo's efficiency in some scenarios. Finally, we compare the efficiency of eclingo with two state-of-the-art solvers for epistemic logic programs on a pair of benchmark scenarios and show that eclingo generally outperforms their obtained results. Under consideration for acceptance in TPLP.

Anurag Ranjan, Javier Romero, Michael J. Black

The optical flow of humans is well known to be useful for the analysis of human action. Given this, we devise an optical flow algorithm specifically for human motion and show that it is superior to generic flow methods. Designing a method by hand is impractical, so we develop a new training database of image sequences with ground truth optical flow. For this we use a 3D model of the human body and motion capture data to synthesize realistic flow fields. We then train a convolutional neural network to estimate human flow fields from pairs of images. Since many applications in human motion analysis depend on speed, and we anticipate mobile applications, we base our method on SpyNet with several modifications. We demonstrate that our trained network is more accurate than a wide range of top methods on held-out test data and that it generalizes well to real image sequences. When combined with a person detector/tracker, the approach provides a full solution to the problem of 2D human flow estimation. Both the code and the dataset are available for research.

Julieta Martinez, Rayat Hossain, Javier Romero et al.

Following the success of deep convolutional networks, state-of-the-art methods for 3d human pose estimation have focused on deep end-to-end systems that predict 3d joint locations given raw image pixels. Despite their excellent performance, it is often not easy to understand whether their remaining error stems from a limited 2d pose (visual) understanding, or from a failure to map 2d poses into 3-dimensional positions. With the goal of understanding these sources of error, we set out to build a system that given 2d joint locations predicts 3d positions. Much to our surprise, we have found that, with current technology, "lifting" ground truth 2d joint locations to 3d space is a task that can be solved with a remarkably low error rate: a relatively simple deep feed-forward network outperforms the best reported result by about 30\% on Human3.6M, the largest publicly available 3d pose estimation benchmark. Furthermore, training our system on the output of an off-the-shelf state-of-the-art 2d detector (\ie, using images as input) yields state of the art results -- this includes an array of systems that have been trained end-to-end specifically for this task. Our results indicate that a large portion of the error of modern deep 3d pose estimation systems stems from their visual analysis, and suggests directions to further advance the state of the art in 3d human pose estimation.

Julieta Martinez, Michael J. Black, Javier Romero

Human motion modelling is a classical problem at the intersection of graphics and computer vision, with applications spanning human-computer interaction, motion synthesis, and motion prediction for virtual and augmented reality. Following the success of deep learning methods in several computer vision tasks, recent work has focused on using deep recurrent neural networks (RNNs) to model human motion, with the goal of learning time-dependent representations that perform tasks such as short-term motion prediction and long-term human motion synthesis. We examine recent work, with a focus on the evaluation methodologies commonly used in the literature, and show that, surprisingly, state-of-the-art performance can be achieved by a simple baseline that does not attempt to model motion at all. We investigate this result, and analyze recent RNN methods by looking at the architectures, loss functions, and training procedures used in state-of-the-art approaches. We propose three changes to the standard RNN models typically used for human motion, which result in a simple and scalable RNN architecture that obtains state-of-the-art performance on human motion prediction.

Christoph Lassner, Javier Romero, Martin Kiefel et al.

3D models provide a common ground for different representations of human bodies. In turn, robust 2D estimation has proven to be a powerful tool to obtain 3D fits "in-the- wild". However, depending on the level of detail, it can be hard to impossible to acquire labeled data for training 2D estimators on large scale. We propose a hybrid approach to this problem: with an extended version of the recently introduced SMPLify method, we obtain high quality 3D body model fits for multiple human pose datasets. Human annotators solely sort good and bad fits. This procedure leads to an initial dataset, UP-3D, with rich annotations. With a comprehensive set of experiments, we show how this data can be used to train discriminative models that produce results with an unprecedented level of detail: our models predict 31 segments and 91 landmark locations on the body. Using the 91 landmark pose estimator, we present state-of-the art results for 3D human pose and shape estimation using an order of magnitude less training data and without assumptions about gender or pose in the fitting procedure. We show that UP-3D can be enhanced with these improved fits to grow in quantity and quality, which makes the system deployable on large scale. The data, code and models are available for research purposes.