Events & Talks

Social Foundations of Computation Talk Bryan Wilder 03-04-2025 Predictive vs causal targeting of social interventions Moritz Hardt

Social Foundations of Computation Talk Jason Hartline 24-03-2025 Optimization of Scoring Rules Moritz Hardt

Talk Nicolas Papernot 12-03-2025 Special Talk: Verifiable Approaches to Trustworthy Machine Learning: Lessons from Researching Unlearning The talk presents open problems in the study of trustworthy machine learning. We begin by broadly characterizing the attack surface of modern machine learning algorithms. We then illustrate the challenges of having end user’s trust that machine learning algorithms were deployed responsibly, i.e., verify its trustworthiness, through a deep dive on the problem of unlearning. The need for machine unlearning, i.e., obtaining a model one would get without training on a subset of data, arises from privacy legislation and as a potential solution to data poisoning or copyright claims. As we present... Moritz Hardt Eva Laemmerhirt Nisha Tyagi

Perceiving Systems Talk Robin Courant 10-03-2025 How and what to film in virtual environments? Content creation for movies and video games has been transformed with the rise of virtual environments, yet filming within these digital worlds remains a complex challenge. This talk explores the question: how and what to film in virtual environments? We examine the role of camera control and human interaction across different virtual settings, including NeRF, 3D engines, and video generation. Victoria Fernandez Abrevaya

Perceiving Systems Talk Ailing Zeng 18-02-2025 The Dawn of Video Generation: Preliminary Explorations with SORA-like Models High-quality video generation—encompassing text-to-video (T2V), image-to-video (I2V), and video-to-video (V2V) generation—plays a pivotal role in content creation and world simulation. While several DiT-based models have advanced rapidly in the past year, a thorough exploration of their capabilities, limitations, and alignment with human preferences remains incomplete. In this talk, I will present recent advancements in SORA-like T2V, I2V, and V2V models and products, bridging the gap between academic research and industry applications. Through live demonstrations and comparative analyses, ... Nikos Athanasiou Michael Black

Social Foundations of Computation Talk Stratis Tsirtsis 11-02-2025 - 11-03-2025 Counterfactual Token Generation in Large Language Models Moritz Hardt

Perceiving Systems Talk Yannis Siglidis 06-02-2025 Computer Vision at the Mirror Stage: Questioning and Refining Visual Categorization Computer vision advancements in predicting and visualizing labels, often motivate us to consider the relationship between labels and images as a given. Yet, the prototypical nature of coherent labels, such as the alphabet of handwritten characters, can help us question assumed families of handwritten variation. Nikos Athanasiou

Talk Dr. Isabella Fiorello 10-12-2024 Next-Generation Biohybrids: Engineering Miniature Machines Inspired by Plant Systems Among living organisms, plants are an ideal source of inspiration for robotics and engineering due to their remarkable evolutionary adaptations to almost every habitat. When miniaturized, plant-inspired machines can navigate confined and complex unstructured surfaces. We introduce a new class of plant-inspired, microfabricated hybrid machines designed for multifunctional tasks such as in situ monitoring and targeted cargo delivery. These machines combine bioinspired design with biohybrid approaches, incorporating the morphological and biomechanical features of both terrestrial and aquatic ... Katherine J. Kuchenbecker Christoph Keplinger

Perceiving Systems Talk Sergi Pujades 28-11-2024 How to predict the inside from the outside? Segment, register, model and infer! Observing and modeling the human body has attracted scientific efforts since the very early times in history. In the recent decades, though, several imaging modalities, such as Computed Tomography scanners (CT), Magnetic Resonance Imaging (MRI), or X-ray have provided the means to “see” inside the body. Most interestingly, there is growing evidence pointing that the shape of the surface of the human body is highly correlated with its internal properties, for example, the body composition, the size of the bones, and the amount of muscle and adipose tissue (fat). In this talk I will go over ... Marilyn Keller

Social Foundations of Computation Talk Dr. Krishna P. Gummadi 19-11-2024 Towards Better Foundations for Foundational Models: A Cognitivist Approach to Studying Large Language Models (LLMs) Moritz Hardt

Perceiving Systems Talk Guy Tevet 14-10-2024 Diffusion Models for Human Motion Synthesis Character motion synthesis stands as a central challenge in computer animation and graphics. The successful adaptation of diffusion models to the field boosted synthesis quality and provided intuitive controls such as text and music. One of the earliest and most popular methods to do so is Motion Diffusion Model (MDM) [ICLR 2023]. In this talk, I will review how MDM incorporates domain know-how into the diffusion model and enables intuitive editing capabilities. Then, I will present two recent works, each suggesting a refreshing take on motion diffusion and extending its abilities to new... Omid Taheri

Perceiving Systems Talk Egor Zakharov 10-10-2024 Reconstruction and Animation of Realistic Head Avatars Digital humans, or realistic avatars, are a centerpiece of future telepresence and special effects systems, and human head modeling is one of their main components. The abovementioned applications, however, are highly demanding in terms of avatar creation speed, as well as realism, and controllability. This talk will focus on the approaches that create controllable and detailed 3D head avatars using the data from consumer-grade devices, such as smartphones, in an uncalibrated and unconstrained capture setting. We will discuss leveraging in-the-wild internet videos and synthetic data sources... Vanessa Sklyarova

Perceiving Systems Talk Simon Donne 26-09-2024 Collaborative Control for Geometry-Conditioned PBR Image Generation Current diffusion models only generate RGB images. If we want to make progress towards graphics-ready 3D content generation, we need a PBR foundation model, but there is not enough PBR data available to train such a model from scratch. We introduce Collaborative Control, which tightly links a new PBR diffusion model to a pre-trained RGB model. We show that this dual architecture does not risk catastrophic forgetting, outputting high-quality PBR images and generalizing well beyond the PBR training dataset. Furthermore, the frozen base model remains compatible with techniques such as IP-Adapter. Soubhik Sanyal

Talk Adriana Cabrera 26-09-2024 From Experimentation to Innovation: Integration of Soft Robotics and Sensing in E-Textiles This talk explores the prototyping of e-textiles and the integration of Soft Robotics systems, grounded in experimentation within digital fabrication spaces and Open Innovation environments like Fab Labs. By leveraging CNC fabrication methods and soft material manipulation, this approach reduces barriers between high and low tech, making experimentation more accessible. It also enables the integration of pneumatic actuators, sensors, and data collection systems into e-textiles and wearable technologies. The presentation will highlight how these developments open up new possibilities for ... Paul Abel Christoph Keplinger

Perceiving Systems Talk Slava Elizarov 26-09-2024 Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representation In this talk, I will present Geometry Image Diffusion (GIMDiffusion), a novel method designed to generate 3D objects from text prompts efficiently. GIMDiffusion uses geometry images, a 2D representation of 3D shapes, which allows the use of existing image-based architectures instead of complex 3D-aware models. This approach reduces computational costs and simplifies the model design. By incorporating Collaborative Control, the method exploits rich priors of pretrained Text-to-Image models like Stable Diffusion, enabling strong generalization even with limited 3D training data. GIMDiffusion ... Soubhik Sanyal

Perceiving Systems Talk Wanyue Zhang 12-09-2024 Generalizable Object-aware Human Motion Synthesis Data-driven virtual 3D character animation has recently witnessed remarkable progress. The realism of virtual characters is a core contributing factor to the quality of computer animations and user experience in immersive applications like games, movies, and VR/AR. However, existing automatic approaches for 3D virtual character motion synthesis supporting scene interactions do not generalize well to new objects outside training distributions, even when trained on extensive motion capture datasets with diverse objects and annotated interactions. In this talk, I will present ROAM, an alternat... Nikos Athanasiou

Haptic Intelligence Talk Lorena Velásquez 05-09-2024 Towards Tendon-Actuated Prostheses with Integrated Haptic Feedback Individuals with limb loss often choose prosthetic devices to complete activities of daily living (ADLs) as they can provide enhanced dexterity and customizable utility. Despite these benefits, high abandonment rates persist due to uncomfortable, cumbersome, and unreliable designs. Despite restoring motor function, dexterous sensorimotor control remains severely impaired due to the absence of haptic feedback. This presentation details the design and evaluation of tendon-actuated mock prostheses with integrated state-based haptic feedback and their anthropomorphic tendon-actuated end effect... Katherine J. Kuchenbecker Uli Bartels

Social Foundations of Computation Talk Kate Donahue 27-08-2024 AI as a resource: strategy, uncertainty, and societal welfare Ana-Andreea Stoica

Perceiving Systems Talk István Sárándi 22-08-2024 Real Virtual Humans With the explosive growth of available training data, 3D human pose and shape estimation is ahead of a transition to a data-centric paradigm. To leverage data scale, we need flexible models trainable from heterogeneous data sources. To this end, our latest work, Neural Localizer Fields, seamlessly unifies different human pose and shape-related tasks and datasets though the ability - both at training and test time - to query any arbitrary point of the human volume, and obtain its estimated location in 3D, based on a single RGB image. We achieve this by learning a continuous neural field of b... Marilyn Keller

Robotic Materials Talk Prof. Zhanshan Wang 22-08-2024 Technologies of Thin Films for High-power Laser Systems High-power laser systems significantly influence solutions for major scientific issues and high-tech industries. Thin films are one of the core components of advanced high-power laser systems. With the development of output power and application scenarios, high-power laser systems have to satisfy increasingly stringent requirements on the damage threshold, optical loss, and capabilities of optical field control for thin-film components of laser systems. In terms of improving the laser damage threshold, we revealed a physical mechanism of "localized strong point", which will induce laser d... Christoph Keplinger

Perceiving Systems Talk Jiawei Liu 25-07-2024 4D Dynamic Scene Reconstruction, Editing, and Generation. People live in a 4D dynamic moving world. While videos serve as the most convenient medium to capture this dynamic world, they lack the capability to present the 4D nature of our world. Therefore, 4D video reconstruction, free-viewpoint rendering, and high-quality editing and generation offer innovative opportunities for content creation, virtual reality, telepresence, and robotics. Although promising, they also pose significant challenges in terms of efficiency, 4D motion and dynamics, temporal and subject consistency, and text-3D/video alignment. In light of these challenges, this talk wi... Omid Taheri

Perceiving Systems Talk Angelica Lim 23-07-2024 Multimodal Social Signal Processing for Human-Robot Interaction Science fiction has long promised us interfaces and robots that interact with us as smoothly as humans do - Rosie the Robot from The Jetsons, C-3PO from Star Wars, and Samantha from Her. Today, interactive robots and voice user interfaces are moving us closer to effortless, human-like interactions in the real world. In this talk, I will discuss the opportunities and challenges in finely analyzing, detecting and generating non-verbal communication in context, including gestures, gaze, auditory signals, and facial expressions. Specifically, I will discuss how we might allow robots and virtual... Yao Feng Michael Black

Perceiving Systems Talk Siheng Chen 18-07-2024 Integrating AI Agents into Human Lives via a Simulation Approach As the rapid growth of AI techniques, we might witness the emergence of AI agents entering our lives, reminiscent of new species. Ensuring these AI agents can well integrate into human life would be a profounding challenge. We urge these agents to be highly performant, safe, and well-aligned with human values. However, directly training and testing AI agents in real-world environments to guarantee their performance and safety is costly and can disrupt everyday life. Thus, we are exploring a simulation-based approach to incubate these AI agents. In this talk, we will highlight the role of si... Yao Feng

Perceiving Systems Talk Boxiang Rong 18-07-2024 Recreating Real Garments in Virtual Space with Gaussian Splatting and GNNs Recent advances in scene reconstruction with 3D Gaussian Splatting and cloth simulation with Graph neural networks open the prospects for methods that reconstruct proto-realistic virtual garments from visual observations. In this talk we will present our recently submitted paper – Gaussian Garments. There we reconstruct simulation ready photorealistic garments from multi-view videos. With the power of 3D Gaussian Splatting we are able to match three key aspects of real garments in virtual space: their geometry, appearance and behavior. The resulting virtual garments can then be combined int... Artur Grigorev

Social Foundations of Computation Talk Zachary Robertson 16-07-2024 Towards Scalable Information Elicitation for Oversight in Human-AI Systems Moritz Hardt

Perceiving Systems Talk Yafes Sahin 08-07-2024 Creating High-End Visuals with Real-Time Technology Creating captivating 3D visuals, particularly photorealistic CGI, demands a diverse range of tools, techniques, and expertise, from concept design to the creation of entire 3D worlds. Linear content generation represents the highest standard of visual quality and has long been a source of inspiration for game developers. In this talk, we will explore the advancements in techniques that have contributed to the rise of real-time technologies in movies and game cinematics. We will delve into projects created with Unreal Engine, such as The Matrix Awakens, Vaulted Halls Entombed (Netflix S... Yao Feng

Perceiving Systems Talk Pranav Manu 04-07-2024 Text-Driven 3D Modeling of Avatars Generating 3D objects poses notable challenges due to the limited availability of annotated 3D datasets, unlike their 2D counterparts. Current approaches often resort to models trained on 2D data, resulting in prolonged optimization phases. Conversely, models trained on 3D datasets enable inference without optimization but suffer from limited dataset diversity. This talk explores methodologies for generative 3D modelling of human heads and garments, pivotal for human avatar creation. First, we introduce "Clip-Head," a text-to-textured 3D head generation model that generates a textured NPHM ... Victoria Fernandez Abrevaya

Social Foundations of Computation Talk Evimaria Terzi 01-07-2024 Beyond accuracy: understanding the performance of LLMs on exams designed for humans Ana-Andreea Stoica

Social Foundations of Computation Talk Nathan Kallus 24-06-2024 The Unreasonable Effectiveness of Distributional Reinforcement Learning Moritz Hardt

Talk Dr. Chaoqun Dong 14-06-2024 Soft Materials and Electronics: Novel Designs and Applications Soft materials assemblies offer a diverse range of sophisticated functions, including sensing and actuation, particularly relevant in intimate interactions with the human body. While hard materials dominate current machine and robot construction, there is a growing recognition of the advantages of soft materials in biomedical devices and human-machine interfaces. Soft systems offer comfort, safety, adaptability, and cost-effectiveness. However, the development of soft devices, encompassing sensors, actuators, and power sources, is in its early stages, requiring further research in materials... Katherine J. Kuchenbecker Christoph Keplinger

Perceiving Systems Talk Shixiang Tang 10-06-2024 Towards Human-Centric Foundation Models: Pretraining Datasets and Unified Architectures Recent years have witnessed great research interests in Human-Centric Visual Computing, such as person re-identification in social surveillance, mesh recovery in Metaverse, and pedestrian detection in autonomous driving. The recent development of large model offers the opportunity to unify these human-centric tasks and achieve improved performance by merging public datasets from different tasks. This talk will present our recent work on developing human-centric unified models on 2D vision, 3D vision, Skelton-based and vision-language tasks. We hope our model will be integrated to the curre... Yandong Wen

Talk Dr.-Ing. Renate Sachse 07-05-2024 Computational Mechanics for Plant-Inspired Soft Robots Soft robotics, an emerging field, focuses on creating flexible and adaptable robots inspired by the pliability found in living organisms. Developed through advancements in materials and manufacturing techniques, soft robots offer unique capabilities such as delicate object manipulation and safe human interaction. In soft robot design, the greatest challenge currently lies in identifying a structure capable of executing a targeted maneuver considering its intricate mechanical behavior. A possible design concept is to learn from biological systems and transfer the functionalities to biomime... Katherine J. Kuchenbecker Christoph Keplinger

Perceiving Systems Talk Shengqu Cai 02-05-2024 Generative Rendering and Beyond Traditional 3D content creation tools empower users to bring their imagination to life by giving them direct control over a scene's geometry, appearance, motion, and camera path. Creating computer-generated videos, however, is a tedious manual process, which can be automated by emerging text-to-video diffusion models (SORA). Despite great promise, video diffusion models are difficult to control, hindering users from applying their own creativity rather than amplifying it. In this talk, we present a novel approach called Generative Rendering that combines the controllability of dynamic 3D me... Shrisha Bharadwaj Michael Black

Perceiving Systems Talk Maria Korosteleva 04-04-2024 Modeling and Reconstructing Garments with Sewing Patterns The problems of creating new garments (modeling) or reproducing the existing ones (reconstruction) appear in various fields: from fashion production to digital human modeling for the metaverse. The talk introduces approaches to a novel garment creation paradigm: programming-based parametric sewing pattern construction and its application to generating rich synthetic datasets of garments with sewing patterns. We will then discuss how the availability of ground truth sewing patterns allows posing the learning-based garment reconstruction problem as a sewing pattern recovery. Such reformulatio... Yao Feng Michael Black

Robotic Materials Talk Dr. Jianyu Li 18-03-2024 Bioadhesive Technologies with Mechanical Principles Bioadhesive technologies are important in a wide range of applications, spanning from wound management to wearable technologies. Forming and controlling tough adhesion on biological tissues has been a long-lasting challenge, necessitating transdisciplinary approaches. In my talk, I will share our recent progress in the design, mechanics, and applications of tough bioadhesives. I will first discuss the limitations of clinically used surgical glues and blood clots in terms of adhesion properties. I will then present the mechanical principles for making tough bioadhesives that exhibit superior... Christoph Keplinger Adrian Koh

Perceiving Systems Talk Qixing Huang 13-03-2024 Geometric Regularizations for 3D Shape Generation Generative models, which map a latent parameter space to instances in an ambient space, enjoy various applications in 3D Vision and related domains. A standard scheme of these models is probabilistic, which aligns the induced ambient distribution of a generative model from a prior distribution of the latent space with the empirical ambient distribution of training instances. While this paradigm has proven to be quite successful on images, its current applications in 3D generation encounter fundamental challenges in the limited training data and generalization behavior. The key difference be... Yuliang Xiu

Social Foundations of Computation Talk Lili Xu 19-02-2024 High-stakes decisions from low-quality data:  AI decision-making for planetary health Ana-Andreea Stoica

Haptic Intelligence Talk Marie Großmann 23-01-2024 Constructing Perceptions: A Sociological Perspective on Sensors The sensory perception of the world, including seeing and hearing, tasting and smelling,touching and feeling, are necessary social skills to become a social counterpart. In this context,the construction of a perceptible technology is an intersection where technical artifacts have the capability to interact and sense their environment. Sensors as technical artifacts not only measure various (physical) states, with their presented results influencing perceptions and actions, but they also undergo technical and computational processing. Sensors generate differences by capturing and measuring ... Katherine J. Kuchenbecker

Perceiving Systems Talk Luming Tang 18-01-2024 Mining Visual Knowledge from Large Pre-trained Models Computer vision made huge progress in the past decade with the dominant supervised learning paradigm, that is training large-scale neural networks on each task with ever larger datasets. However, in many cases, scalable data or annotation collection is intractable. In contrast, humans can easily adapt to new vision tasks with very little data or labels. In order to bridge this gap, we found that there actually exists rich visual knowledge in large pre-trained models, i.e., models trained on scalable internet images with either self-supervised or generative objectives. And we proposed differ... Yuliang Xiu Yandong Wen

Haptic Intelligence Talk Dr. Janneke Schwaner 07-12-2023 Biomechanics and Control of Agile Locomotion: from Walking to Jumping Animals seem to effortlessly navigate complex terrain. This is in stark contrast with even the most advanced robot, illustrating that navigating complex terrain is by no means trivial. Humans’ neuromusculoskeletal system is equipped with two key mechanisms that allow us to recover from unexpected perturbations: muscle intrinsic properties and sensory-driven feedback control. We used unique in vivo and in situ approaches to explore how guinea fowl (Numida meleagris) integrate these two mechanisms to maintain robust locomotion. For example, our work showed a modular task-level control of leg ... Katherine J. Kuchenbecker Andrew Schulz

Perceiving Systems Talk Partha Ghosh 30-11-2023 RAVEN: Rethinking Adversarial Video generation with Efficient tri-plane Networks We present a novel unconditional video generative model designed to address long-term spatial and temporal dependencies. To capture these dependencies, our approach incorporates a hybrid explicit-implicit tri-plane representation inspired by 3D-aware generative frameworks developed for three-dimensional object representation and employs a singular latent code to model an entire video sequence. Individual video frames are then synthesized from an intermediate tri-plane representation, which itself is derived from the primary latent code. This novel strategy reduces computational complexity b... Yandong Wen

Perceiving Systems Talk Weiyang Liu 19-10-2023 Orthogonal Butterfly: Parameter-Efficient Orthogonal Adaptation of Foundation Models via Butterfly Factorization Large foundation models are becoming ubiquitous, but training them from scratch is prohibitively expensive. Thus, efficiently adapting these powerful models to downstream tasks is increasingly important. In this paper, we study a principled finetuning paradigm -- Orthogonal Finetuning (OFT) -- for downstream task adaptation. Despite demonstrating good generalizability, OFT still uses a fairly large number of trainable parameters due to the high dimensionality of orthogonal matrices. To address this, we start by examining OFT from an information transmission perspective, and then identify a ... Yandong Wen

Haptic Intelligence Talk Dr. Diego Ospina 17-10-2023 Project neuroArm: Image-guided Medical Robotics Program Project neuroArm was established in 2002, with the idea of building the world’s first robot for brain surgery and stereotaxy. With the launch (2007) and integration of the neuroArm robot in the neurosurgical operating room (May 2008), the project continues to spawn newer technological innovations, advance tele-robotics through sensors and AI, and intelligent surgical systems towards improving safety of surgery. This talk will provide a high-level overview of two such technologies the team at Project neuroArm is currently developing and deploying: i) neuroArm+HD, a medical-grade sensory imme... Katherine J. Kuchenbecker Rachael Lorsa

Perceiving Systems Talk Zhen Liu 12-10-2023 Ghost on the Shell: An Expressive Representation of General 3D Shapes The creation of photorealistic virtual worlds requires the accurate modeling of 3D surface geometry for a wide range of objects. For this, meshes are appealing since they enable 1) fast physics-based rendering with realistic material and lighting, 2) physical simulation, and 3) are memory-efficient for modern graphics pipelines. Recent work on reconstructing and statistically modeling 3D shape, however, has critiqued meshes as being topologically inflexible. To capture a wide range of object shapes, any 3D representation must be able to model solid, watertight, shapes as well as thin, open,... Yandong Wen

Haptic Intelligence Talk Andreea Tulbure 10-10-2023 Towards Seamless Handovers with Legged Manipulators Deploying perception and control modules for handovers is challenging because they require a high degree of robustness and generalizability to work reliably for a diversity of objects and situations, but also adaptivity to adjust to individual preferences. On legged robots, deployment is particularly challenging because of the limited computational resources and the additional sensing noise resulting from locomotion. In this talk, I will discuss how we tackle some of these challenges, by first introducing our perception framework and discussing the insights of the first human-robot handover... Katherine J. Kuchenbecker

Embodied Vision Talk Rama Kandukuri 28-09-2023 Physics-Based Rigid Body Object Tracking and Friction Filtering From RGB-D Videos Physics-based understanding of object interactions from sensory observations is an essential capability in augmented reality and robotics. It enables to capture the properties of a scene for simulation and control. In this paper, we propose a novel approach for real-to-sim which tracks rigid objects in 3D from RGB-D images and infers physical properties of the objects. We use a differentiable physics simulation as state-transition model in an Extended Kalman Filter, which can model contact and friction for arbitrary mesh-based shapes and in this way estimate physically plausible trajectorie... Yandong Wen

Perceiving Systems Talk Claudia Gallatz 17-08-2023 Face Exploration - Capture all Degrees of Freedom of the Face A high quality data capture is decisive for your scientific work. As a member of the data team, it is a core task of my daily routine to ensure good quality standards in this field. My talk will enlighten the background of this work, starting from scanner set-up and the corresponding data outcome with focus on the Face Scanner. A work, each scientist can profit from for his personal projects. I will take the occasion to present our most recent face capture study named FACE EXPLORATION, of which Timo Bolkart is the leading scientist. A selection of representative sequences including facial m... Yandong Wen

Robotic Materials Talk Prof. Dr. Kyu-Jin Cho 18-07-2023 Nature-inspired designs for innovating soft robotic grippers and prosthetics In this talk, I will discuss the cutting-edge research conducted at our Soft Robotics Research Center and Biorobotics Lab, with an emphasis on the development of grippers and prosthetics inspired by the adaptive behaviors and embodied intelligence observed in nature. Traditional robots are designed for structured environments and navigate unstructured environments using sensors and intricate computation. To adapt to and flourish in unstructured environments, nature employs simple embodied intelligence, which does not necessarily require sensing or complex computation. Christoph Keplinger Metin Sitti

Talk Prof. Dr. Björn Ommer 14-07-2023 Why This is (Not) the End of Research in Generative AI: Stable Diffusion & the Revolution in Visual Synthesis Recently, deep generative modeling has become the most prominent paradigm for learning powerful representations of our (visual) world and for generating novel samples thereof. At the same time, most of the progress came from sizing up models - to the point where the development seemed to be restricted to few big tech companies with boundless resources and with implications on future (academic) research, industry, and society. Michael Black

Perceiving Systems Talk Yangyi Huang 13-07-2023 Full-body avatars from single images and textual guidance The reconstruction of full body appearance of clothed humans from single-view RGB images is a crucial yet challenging task, primarily due to depth ambiguities and the absence of observations from unseen regions. While existing methods have shown impressive results, they still suffer from limitations such as over-smooth surfaces and blurry textures, particularly lacking details at the backside of the avatar. In this talk, I will delve into how we have addressed these limitations by leveraging text guidance and pretrained text-image models, introducing two novel methods. Firstly, I will prese... Hongwei Yi

Research

Departments

Research Groups

People

Contact

Our Institute

Our History

Career

Doctoral Programs

Training

Service Units

Central Scientific Facilities

Workshops

Campus Services

Impact

Cooperation

Partners and Initiatives