Search Results for author:
Found 34 papers, 17 papers with code
Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars
Finally, we increase robustness by feeding input images with different expressions to our model during training, enabling the reconstruction of 3D head avatars from inconsistent inputs, e. g., an imperfect phone capture with accidental movement, or frames from a monocular video.
Relightable Full-Body Gaussian Codec Avatars
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.
Reasoning about Study Regulations in Answer Set Programming
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.
On the generalization of learned constraints for ASP solving in temporal domains
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.
URHand: Universal Relightable Hands
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.
From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations
We present a framework for generating full-bodied photorealistic avatars that gesture according to the conversational dynamics of a dyadic interaction.
Drivable 3D Gaussian Avatars
We present Drivable 3D Gaussian Avatars (D3GA), the first 3D controllable model for human bodies rendered with Gaussian splats.
Diffusion Shape Prior for Wrinkle-Accurate Cloth Registration
Registering clothes from 4D scans with vertex-accurate correspondence is challenging, yet important for dynamic appearance modeling and physics parameter estimation from real-world data.
Human Body Measurement Estimation with Adversarial Augmentation
Training of BMnet is performed on data from real human subjects, and augmented with a novel adversarial body simulator (ABS) that finds and synthesizes challenging body shapes.
Dressing Avatars: Deep Photorealistic Appearance for Physically Simulated Clothing
The key idea is to introduce a neural clothing appearance model that operates on top of explicit geometry: at training time we use high-fidelity tracking, whereas at animation time we rely on physically simulated geometry.
plingo: A system for probabilistic reasoning in clingo based on lpmln
We present plingo, an extension of the ASP system clingo with various probabilistic reasoning modes.
AutoAvatar: Autoregressive Neural Fields for Dynamic Avatar Modeling
In this work, for the first time, we enable autoregressive modeling of implicit avatars.
Embodied Hands: Modeling and Capturing Hands and Bodies Together
We attach MANO to a standard parameterized 3D body shape model (SMPL), resulting in a fully articulated body and hand model (SMPL+H).
Answer Set Programming Made Easy
We take up an idea from the folklore of Answer Set Programming, namely that choices, integrity constraints along with a restricted rule format is sufficient for Answer Set Programming.
Learning Realistic Human Reposing using Cyclic Self-Supervision with 3D Shape, Pose, and Appearance Consistency
Synthesizing images of a person in novel poses from a single image is a highly ambiguous task.
Planning with Incomplete Information in Quantified Answer Set Programming
We present a general approach to planning with incomplete information in Answer Set Programming (ASP).
Learning First-Order Representations for Planning from Black-Box States: New Results
For this, the learning problem is formulated as the search for a simplest first-order domain description D that along with information about instances I_i (number of objects and initial state) determine state space graphs G(P_i) that match the observed state graphs G_i where P_i = (D, I_i).
SMPLpix: Neural Avatars from 3D Human Models
Recent advances in deep generative models have led to an unprecedented level of realism for synthetically generated images of humans.
How to build your own ASP-based system?!
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.
eclingo: A solver for Epistemic Logic Programs
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.
Learning Multi-Human Optical Flow
Therefore, we develop a dataset of multi-human optical flow and train optical flow networks on this dataset.
FACSIMILE: Fast and Accurate Scans From an Image in Less Than a Second
Counterintuitively, the main loss which drives FAX is on per-pixel surface normals instead of per-pixel depth, making it possible to estimate detailed body geometry without any depth supervision.
Efficient Learning on Point Clouds with Basis Point Sets
The basis point set representation is a residual representation that can be computed efficiently and can be used with standard neural network architectures and other machine learning algorithms.
Learning Human Optical Flow
Given this, we devise an optical flow algorithm specifically for human motion and show that it is superior to generic flow methods.
Learning a model of facial shape and expression from 4D scans
FLAME is low-dimensional but more expressive than the FaceWarehouse model and the Basel Face Model.
Ranked #3 on
Face Alignment
on FaceScape
Dynamic FAUST: Registering Human Bodies in Motion
We propose a new mesh registration method that uses both 3D geometry and texture information to register all scans in a sequence to a common reference topology.
A simple yet effective baseline for 3d human pose estimation
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.
Ranked #20 on
3D Human Pose Estimation
on HumanEva-I
On human motion prediction using recurrent neural networks
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.
Unite the People: Closing the Loop Between 3D and 2D Human Representations
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.
Ranked #1 on
Monocular 3D Human Pose Estimation
on Human3.6M
(Use Video Sequence metric)
3D human pose and shape estimation
Monocular 3D Human Pose Estimation
Learning from Synthetic Humans
In this work we present SURREAL (Synthetic hUmans foR REAL tasks): a new large-scale dataset with synthetically-generated but realistic images of people rendered from 3D sequences of human motion capture data.
Coupling Adaptive Batch Sizes with Learning Rates
The batch size significantly influences the behavior of the stochastic optimization algorithm, though, since it determines the variance of the gradient estimates.
Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image
We then fit (top-down) a recently published statistical body shape model, called SMPL, to the 2D joints.
Ranked #31 on
3D Human Pose Estimation
on HumanEva-I
Detailed Full-Body Reconstructions of Moving People From Monocular RGB-D Sequences
The method then uses geometry and image texture over time to obtain accurate shape, pose, and appearance information despite unconstrained motion, partial views, varying resolution, occlusion, and soft tissue deformation.
FAUST: Dataset and Evaluation for 3D Mesh Registration
We address this with a novel mesh registration technique that combines 3D shape and appearance information to produce high-quality alignments.
