Ruofei Du

Xiang 'Anthony' Chen, Jeff Burke, Ruofei Du et al. · microsoft-research, salesforce

Through iterative, cross-disciplinary discussions, we define and propose next-steps for Human-centered Generative AI (HGAI). We contribute a comprehensive research agenda that lays out future directions of Generative AI spanning three levels: aligning with human values; assimilating human intents; and augmenting human abilities. By identifying these next-steps, we intend to draw interdisciplinary research teams to pursue a coherent set of emergent ideas in HGAI, focusing on their interested topics while maintaining a coherent big picture of the future work landscape.

Ziqian Bai, Feitong Tan, Zeng Huang et al.

We propose a method to learn a high-quality implicit 3D head avatar from a monocular RGB video captured in the wild. The learnt avatar is driven by a parametric face model to achieve user-controlled facial expressions and head poses. Our hybrid pipeline combines the geometry prior and dynamic tracking of a 3DMM with a neural radiance field to achieve fine-grained control and photorealism. To reduce over-smoothing and improve out-of-model expressions synthesis, we propose to predict local features anchored on the 3DMM geometry. These learnt features are driven by 3DMM deformation and interpolated in 3D space to yield the volumetric radiance at a designated query point. We further show that using a Convolutional Neural Network in the UV space is critical in incorporating spatial context and producing representative local features. Extensive experiments show that we are able to reconstruct high-quality avatars, with more accurate expression-dependent details, good generalization to out-of-training expressions, and quantitatively superior renderings compared to other state-of-the-art approaches.

Brandon Yushan Feng, Yinda Zhang, Danhang Tang et al.

We introduce a new implicit shape representation called Primary Ray-based Implicit Function (PRIF). In contrast to most existing approaches based on the signed distance function (SDF) which handles spatial locations, our representation operates on oriented rays. Specifically, PRIF is formulated to directly produce the surface hit point of a given input ray, without the expensive sphere-tracing operations, hence enabling efficient shape extraction and differentiable rendering. We demonstrate that neural networks trained to encode PRIF achieve successes in various tasks including single shape representation, category-wise shape generation, shape completion from sparse or noisy observations, inverse rendering for camera pose estimation, and neural rendering with color.

Ruofei Du, Benjamin Hersh, David Li et al.

While large language models have accelerated software development through "vibe coding", prototyping intelligent Extended Reality (XR) experiences remains inaccessible due to the friction of complex game engines and low-level sensor integration. To bridge this gap, we contribute XR Blocks, an open-source, modular WebXR framework that abstracts spatial computing complexities into high-level, human-centered primitives. Building upon this foundation, we present Vibe Coding XR, an end-to-end rapid prototyping workflow that leverages LLMs to translate natural language intent directly into functional XR software. Using a web-based interface, creators can transform high-level prompts (e.g., "create a dandelion that reacts to hand") into interactive WebXR applications in under a minute. We provide a preliminary technical evaluation on a pilot dataset (VCXR60) alongside diverse application scenarios highlighting mixed-reality realism, multi-modal interaction, and generative AI integrations. By democratizing spatial software creation, this work empowers practitioners to bypass low-level hurdles and rapidly move from "idea to reality." Code and live demos are available at https://xrblocks.github.io/gem and https://github.com/google/xrblocks.

Mustafa Doga Dogan, Eric J. Gonzalez, Karan Ahuja et al.

Seamless integration of physical objects as interactive digital entities remains a challenge for spatial computing. This paper explores Augmented Object Intelligence (AOI) in the context of XR, an interaction paradigm that aims to blur the lines between digital and physical by equipping real-world objects with the ability to interact as if they were digital, where every object has the potential to serve as a portal to digital functionalities. Our approach utilizes real-time object segmentation and classification, combined with the power of Multimodal Large Language Models (MLLMs), to facilitate these interactions without the need for object pre-registration. We implement the AOI concept in the form of XR-Objects, an open-source prototype system that provides a platform for users to engage with their physical environment in contextually relevant ways using object-based context menus. This system enables analog objects to not only convey information but also to initiate digital actions, such as querying for details or executing tasks. Our contributions are threefold: (1) we define the AOI concept and detail its advantages over traditional AI assistants, (2) detail the XR-Objects system's open-source design and implementation, and (3) show its versatility through various use cases and a user study.

David Li, Nels Numan, Xun Qian et al.

We are on the cusp where Artificial Intelligence (AI) and Extended Reality (XR) are converging to unlock new paradigms of interactive computing. However, a significant gap exists between the ecosystems of these two fields: while AI research and development is accelerated by mature frameworks like JAX and benchmarks like LMArena, prototyping novel AI-driven XR interactions remains a high-friction process, often requiring practitioners to manually integrate disparate, low-level systems for perception, rendering, and interaction. To bridge this gap, we present XR Blocks, a cross-platform framework designed to accelerate human-centered AI + XR innovation. XR Blocks strives to provide a modular architecture with plug-and-play components for core abstraction in AI + XR: user, world, peers; interface, context, and agents. Crucially, it is designed with the mission of "reducing frictions from idea to reality", thus accelerating rapid prototyping of AI + XR apps. Built upon accessible technologies (WebXR, three.js, TensorFlow, Gemini), our toolkit lowers the barrier to entry for XR creators. We demonstrate its utility through a set of open-source templates, samples, and advanced demos, empowering the community to quickly move from concept to interactive XR prototype. Site: https://xrblocks.github.io

Changqing Zou, Qian Yu, Ruofei Du et al.

We contribute the first large-scale dataset of scene sketches, SketchyScene, with the goal of advancing research on sketch understanding at both the object and scene level. The dataset is created through a novel and carefully designed crowdsourcing pipeline, enabling users to efficiently generate large quantities of realistic and diverse scene sketches. SketchyScene contains more than 29,000 scene-level sketches, 7,000+ pairs of scene templates and photos, and 11,000+ object sketches. All objects in the scene sketches have ground-truth semantic and instance masks. The dataset is also highly scalable and extensible, easily allowing augmenting and/or changing scene composition. We demonstrate the potential impact of SketchyScene by training new computational models for semantic segmentation of scene sketches and showing how the new dataset enables several applications including image retrieval, sketch colorization, editing, and captioning, etc. The dataset and code can be found at https://github.com/SketchyScene/SketchyScene.

Faraz Faruqi, Demircan Tas, Arthur Caetano et al.

Recent developments in 3D generative AI enable users to create bespoke 3D models from text or image prompts. However, these approaches provide limited control over spatial structure, making them ill suited for tasks requiring precise geometric composition. We present MiXR, an XR system for in-situ compositional modeling that enables users to create new 3D models by harvesting geometry from their environment. Users extract segments from captured objects and assemble new artifacts through direct 3D manipulation, while generative AI synthesizes a coherent model from the user-defined composition. This hybrid workflow allows users to define spatial structure explicitly while delegating geometric refinement to generative models, enabling them to specify spatial intent that is difficult to express through verbal prompts alone. In a controlled user study ($N=12$), participants using MiXR rated their designs as significantly closer to the target, felt more in control, and experienced lower cognitive workload compared to a generative composition baseline.

Zhongyi Zhou, Jing Jin, Vrushank Phadnis et al.

Visual programming has the potential of providing novice programmers with a low-code experience to build customized processing pipelines. Existing systems typically require users to build pipelines from scratch, implying that novice users are expected to set up and link appropriate nodes from a blank workspace. In this paper, we introduce InstructPipe, an AI assistant for prototyping machine learning (ML) pipelines with text instructions. We contribute two large language model (LLM) modules and a code interpreter as part of our framework. The LLM modules generate pseudocode for a target pipeline, and the interpreter renders the pipeline in the node-graph editor for further human-AI collaboration. Both technical and user evaluation (N=16) shows that InstructPipe empowers users to streamline their ML pipeline workflow, reduce their learning curve, and leverage open-ended commands to spark innovative ideas.

Zhongyi Zhou, Kohei Uehara, Haoyu Zhang et al.

Prior work synthesizes tool-use LLM datasets by first generating a user query, followed by complex tool-use annotations like DFS. This leads to inevitable annotation failures and low efficiency in data generation. We introduce ToolGrad, an agentic framework that inverts this paradigm. ToolGrad first constructs valid tool-use chains through an iterative process guided by textual "gradients", and then synthesizes corresponding user queries. This "answer-first" approach led to ToolGrad-5k, a dataset generated with more complex tool use, lower cost, and 100% pass rate. Experiments show that models trained on ToolGrad-5k outperform those on expensive baseline datasets and proprietary LLMs, even on OOD benchmarks.

Peng Dai, Feitong Tan, Qiangeng Xu et al.

While video generation models excel at producing high-quality monocular videos, generating 3D stereoscopic and spatial videos for immersive applications remains an underexplored challenge. We present a pose-free and training-free method that leverages an off-the-shelf monocular video generation model to produce immersive 3D videos. Our approach first warps the generated monocular video into pre-defined camera viewpoints using estimated depth information, then applies a novel \textit{frame matrix} inpainting framework. This framework utilizes the original video generation model to synthesize missing content across different viewpoints and timestamps, ensuring spatial and temporal consistency without requiring additional model fine-tuning. Moreover, we develop a \dualupdate~scheme that further improves the quality of video inpainting by alleviating the negative effects propagated from disoccluded areas in the latent space. The resulting multi-view videos are then adapted into stereoscopic pairs or optimized into 4D Gaussians for spatial video synthesis. We validate the efficacy of our proposed method by conducting experiments on videos from various generative models, such as Sora, Lumiere, WALT, and Zeroscope. The experiments demonstrate that our method has a significant improvement over previous methods. Project page at: https://daipengwa.github.io/S-2VG_ProjectPage/

Peng Dai, Feitong Tan, Qiangeng Xu et al.

Video generation models have demonstrated great capabilities of producing impressive monocular videos, however, the generation of 3D stereoscopic video remains under-explored. We propose a pose-free and training-free approach for generating 3D stereoscopic videos using an off-the-shelf monocular video generation model. Our method warps a generated monocular video into camera views on stereoscopic baseline using estimated video depth, and employs a novel frame matrix video inpainting framework. The framework leverages the video generation model to inpaint frames observed from different timestamps and views. This effective approach generates consistent and semantically coherent stereoscopic videos without scene optimization or model fine-tuning. Moreover, we develop a disocclusion boundary re-injection scheme that further improves the quality of video inpainting by alleviating the negative effects propagated from disoccluded areas in the latent space. We validate the efficacy of our proposed method by conducting experiments on videos from various generative models, including Sora [4 ], Lumiere [2], WALT [8 ], and Zeroscope [ 42]. The experiments demonstrate that our method has a significant improvement over previous methods. The code will be released at \url{https://daipengwa.github.io/SVG_ProjectPage}.

Safa C. Medin, Gengyan Li, Ruofei Du et al.

3D rendering of dynamic face captures is a challenging problem, and it demands improvements on several fronts$\unicode{x2014}$photorealism, efficiency, compatibility, and configurability. We present a novel representation that enables high-quality volumetric rendering of an actor's dynamic facial performances with minimal compute and memory footprint. It runs natively on commodity graphics soft- and hardware, and allows for a graceful trade-off between quality and efficiency. Our method utilizes recent advances in neural rendering, particularly learning discrete radiance manifolds to sparsely sample the scene to model volumetric effects. We achieve efficient modeling by learning a single set of manifolds for the entire dynamic sequence, while implicitly modeling appearance changes as temporal canonical texture. We export a single layered mesh and view-independent RGBA texture video that is compatible with legacy graphics renderers without additional ML integration. We demonstrate our method by rendering dynamic face captures of real actors in a game engine, at comparable photorealism to state-of-the-art neural rendering techniques at previously unseen frame rates.

Dhruv Jain, Khoa Huynh Anh Nguyen, Steven Goodman et al.

Recent advances have enabled automatic sound recognition systems for deaf and hard of hearing (DHH) users on mobile devices. However, these tools use pre-trained, generic sound recognition models, which do not meet the diverse needs of DHH users. We introduce ProtoSound, an interactive system for customizing sound recognition models by recording a few examples, thereby enabling personalized and fine-grained categories. ProtoSound is motivated by prior work examining sound awareness needs of DHH people and by a survey we conducted with 472 DHH participants. To evaluate ProtoSound, we characterized performance on two real-world sound datasets, showing significant improvement over state-of-the-art (e.g., +9.7% accuracy on the first dataset). We then deployed ProtoSound's end-user training and real-time recognition through a mobile application and recruited 19 hearing participants who listened to the real-world sounds and rated the accuracy across 56 locations (e.g., homes, restaurants, parks). Results show that ProtoSound personalized the model on-device in real-time and accurately learned sounds across diverse acoustic contexts. We close by discussing open challenges in personalizable sound recognition, including the need for better recording interfaces and algorithmic improvements.

David Li, Yinda Zhang, Christian Häne et al.

Immersive maps such as Google Street View and Bing Streetside provide true-to-life views with a massive collection of panoramas. However, these panoramas are only available at sparse intervals along the path they are taken, resulting in visual discontinuities during navigation. Prior art in view synthesis is usually built upon a set of perspective images, a pair of stereoscopic images, or a monocular image, but barely examines wide-baseline panoramas, which are widely adopted in commercial platforms to optimize bandwidth and storage usage. In this paper, we leverage the unique characteristics of wide-baseline panoramas and present OmniSyn, a novel pipeline for 360° view synthesis between wide-baseline panoramas. OmniSyn predicts omnidirectional depth maps using a spherical cost volume and a monocular skip connection, renders meshes in 360° images, and synthesizes intermediate views with a fusion network. We demonstrate the effectiveness of OmniSyn via comprehensive experimental results including comparison with the state-of-the-art methods on CARLA and Matterport datasets, ablation studies, and generalization studies on street views. We envision our work may inspire future research for this unheeded real-world task and eventually produce a smoother experience for navigating immersive maps.

Zhang Chen, Yinda Zhang, Kyle Genova et al.

We introduce Multiresolution Deep Implicit Functions (MDIF), a hierarchical representation that can recover fine geometry detail, while being able to perform global operations such as shape completion. Our model represents a complex 3D shape with a hierarchy of latent grids, which can be decoded into different levels of detail and also achieve better accuracy. For shape completion, we propose latent grid dropout to simulate partial data in the latent space and therefore defer the completing functionality to the decoder side. This along with our multires design significantly improves the shape completion quality under decoder-only latent optimization. To the best of our knowledge, MDIF is the first deep implicit function model that can at the same time (1) represent different levels of detail and allow progressive decoding; (2) support both encoder-decoder inference and decoder-only latent optimization, and fulfill multiple applications; (3) perform detailed decoder-only shape completion. Experiments demonstrate its superior performance against prior art in various 3D reconstruction tasks.

Zhenyi He, Ruofei Du, Ken Perlin

Video conferences play a vital role in our daily lives. However, many nonverbal cues are missing, including gaze and spatial information. We introduce LookAtChat, a web-based video conferencing system, which empowers remote users to identify gaze awareness and spatial relationships in small-group conversations. Leveraging real-time eye-tracking technology available with ordinary webcams, LookAtChat tracks each user's gaze direction, identifies who is looking at whom, and provides corresponding spatial cues. Informed by formative interviews with 5 participants who regularly use videoconferencing software, we explored the design space of gaze visualization in both 2D and 3D layouts. We further conducted an exploratory user study (N=20) to evaluate LookAtChat in three conditions: baseline layout, 2D directional layout, and 3D perspective layout. Our findings demonstrate how LookAtChat engages participants in small-group conversations, how gaze and spatial information improve conversation quality, and the potential benefits and challenges to incorporating gaze awareness visualization into existing videoconferencing systems.

Feitong Tan, Danhang Tang, Mingsong Dou et al.

In this paper, we address the problem of building dense correspondences between human images under arbitrary camera viewpoints and body poses. Prior art either assumes small motion between frames or relies on local descriptors, which cannot handle large motion or visually ambiguous body parts, e.g., left vs. right hand. In contrast, we propose a deep learning framework that maps each pixel to a feature space, where the feature distances reflect the geodesic distances among pixels as if they were projected onto the surface of a 3D human scan. To this end, we introduce novel loss functions to push features apart according to their geodesic distances on the surface. Without any semantic annotation, the proposed embeddings automatically learn to differentiate visually similar parts and align different subjects into an unified feature space. Extensive experiments show that the learned embeddings can produce accurate correspondences between images with remarkable generalization capabilities on both intra and inter subjects.

Yue Jiang, Ruofei Du, Christof Lutteroth et al.

We propose a novel approach for constraint-based graphical user interface (GUI) layout based on OR-constraints (ORC) in standard soft/hard linear constraint systems. ORC layout unifies grid layout and flow layout, supporting both their features as well as cases where grid and flow layouts individually fail. We describe ORC design patterns that enable designers to safely create flexible layouts that work across different screen sizes and orientations. We also present the ORC Editor, a GUI editor that enables designers to apply ORC in a safe and effective manner, mixing grid, flow and new ORC layout features as appropriate. We demonstrate that our prototype can adapt layouts to screens with different aspect ratios with only a single layout specification, easing the burden of GUI maintenance. Finally, we show that ORC specifications can be modified interactively and solved efficiently at runtime.

Changqing Zou, Haoran Mo, Ruofei Du et al.

We introduce LUCSS, a language-based system for interactive col- orization of scene sketches, based on their semantic understanding. LUCSS is built upon deep neural networks trained via a large-scale repository of scene sketches and cartoon-style color images with text descriptions. It con- sists of three sequential modules. First, given a scene sketch, the segmenta- tion module automatically partitions an input sketch into individual object instances. Next, the captioning module generates the text description with spatial relationships based on the instance-level segmentation results. Fi- nally, the interactive colorization module allows users to edit the caption and produce colored images based on the altered caption. Our experiments show the effectiveness of our approach and the desirability of its compo- nents to alternative choices.