73 accepted papers
Flow-based generative models, including diffusion models, excel at modeling continuous distributions in high-dimensional spaces. In this work, we introduce Flow Policy Optimization (FPO), a simple on-policy reinforcement learning algorithm that brings flow matching into the policy gradient framework…
A dominant paradigm for teaching humanoid robots complex skills is to retarget human motions as kinematic references to train reinforcement learning (RL) policies. However, existing retargeting pipelines often struggle with the significant embodiment gap between humans and robots, producing physical…
While recent advances in humanoid locomotion have achieved stable walking on varied terrains, capturing the agility and adaptivity of highly dynamic human motions remains an open challenge. In particular, agile parkour in complex environments demands not only low-level robustness, but also human-lik…
Large-scale data has driven breakthroughs in robotics, from language models to vision-language-action models in bimanual manipulation. However, humanoid robotics lacks equally effective data collection frameworks. Existing humanoid teleoperation systems either use decoupled control or depend on expe…
We present Viser, a toolkit for 3D visualization in robotics and computer vision. Viser aims to bring easy and extensible 3D visualization to Python: we provide comprehensive 3D scene and 2D GUI primitives, which can be used independently with minimal setup or composed to build specialized interface…
We present Agent-to-Sim (ATS), a framework for learning interactive behavior models of 3D agents from casual longitudinal video collections. Different from prior works that rely on marker-based tracking and multiview cameras, ATS learns natural behaviors of animal agents non-invasively through video…
Transformers are increasingly prevalent for multiview computer vision tasks, where geometric relationships between viewpoints are critical for 3D perception. To leverage these relationships, multiview transformers must use camera geometry to ground visual tokens in 3D space. In this work, we compare…
We present a unified framework capable of solving a broad range of 3D tasks. Our approach features a stateful recurrent model that continuously updates its state representation with each new observation. Given a stream of images, this evolving state can be used to generate metric-scale pointmaps (pe…
Large-scale AI model training divides work across thousands of GPUs then synchronizes gradients across them at each step. This incurs a significant network burden that only centralized, monolithic clusters can support, driving up infrastructure costs and straining power systems. We propose Decentral…
We present EgoAllo, a system for human motion estimation from a head-mounted device. Using only egocentric SLAM poses and images, EgoAllo guides sampling from a conditional diffusion model to estimate 3D body pose, height, and hand parameters that capture a device wearer's actions in the allocentric…
Humans do not passively observe the visual world---we actively look in order to act. Motivated by this principle, we introduce EyeRobot, a robotic system with gaze behavior that emerges from the need to complete real-world tasks. We develop a mechanical eyeball that can freely rotate to observe its…
We present a system that allows for accurate, fast, and robust estimation of camera parameters and depth maps from casual monocular videos of dynamic scenes. Most conventional structure from motion and monocular SLAM techniques assume input videos that feature predominantly static scenes with large…
Whether snipping with scissors or opening a box, humans can quickly understand the 3D configurations of familiar objects. For novel objects, we can resort to long-form inspection to build intuition. The more we observe the object, the better we get at predicting its 3D state immediately. Existing sy…
Robot motion can have many goals. Depending on the task, we might optimize for pose error, speed, collision, or similarity to a human demonstration. Motivated by this, we present PyRoki: a modular, extensible, and deviceagnostic toolkit for solving kinematic optimization problems. PyRoki couples an
We present "Humans and Structure from Motion" (HSfM), a method for jointly reconstructing multiple human meshes, scene point clouds, and camera parameters in a metric world coordinate system from a sparse set of uncalibrated multi-view images featuring people. Our approach combines data-driven scene…
Moving object segmentation is a crucial task for achieving a high-level understanding of visual scenes and has numerous downstream applications. Humans can effortlessly segment moving objects in videos. Previous work has largely relied on optical flow to provide motion cues; however, this approach o…
Monocular dynamic reconstruction is a challenging and long-standing vision problem due to the highly ill-posed nature of the task. Existing approaches depend on templates, are effective only in quasi-static scenes, or fail to model 3D motion explicitly. We introduce a method for reconstructing gener…
Dynamic 3D reconstruction and point tracking in videos are typically treated as separate tasks, despite their deep connection. We propose St4RTrack, a feed-forward frame- work that simultaneously reconstructs and tracks dynamic video content in a world coordinate frame from RGB in- puts. This is ach…
How can we teach humanoids to climb staircases and sit on chairs using the surrounding environment context? Arguably the simplest way is to _just show them_—casually capture a human motion video and feed it to humanoids. We introduce **VideoMimic**, a real-to-sim-to-real pipeline that mines everyday…
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…
Grouping is inherently ambiguous due to the multiple levels of granularity in which one can decompose a scene --- should the wheels of an excavator be considered separate or part of the whole? We propose Group Anything with Radiance Fields (GARField) an approach for decomposing 3D scenes into a hier…
Social interaction is a fundamental aspect of human behavior and communication. The way individuals position themselves in relation to others also known as proxemics conveys social cues and affects the dynamics of social interaction. Reconstructing such interaction from images presents challenges be…
"We present , a principled method for distributing Neural Radiance Fields (NeRFs) across multiple GPUs, thus enabling the training and rendering of NeRFs with an arbitrarily large capacity. We begin by revisiting existing multi-GPU approaches, which decompose large scenes into multiple independently…
We propose NeRFiller an approach that completes missing portions of a 3D capture via generative 3D inpainting using off-the-shelf 2D visual generative models. Often parts of a captured 3D scene or object are missing due to mesh reconstruction failures or a lack of observations (e.g. contact regions…
We present an approach that can reconstruct hands in 3D from monocular input. Our approach for Hand Mesh Recovery HaMeR follows a fully transformer-based architecture and can analyze hands with significantly increased accuracy and robustness compared to previous work. The key to HaMeR's success lies…
Score distillation sampling (SDS) has proven to be an important tool, enabling the use of large-scale diffusion priors for tasks operating in data-poor domains. Unfortunately, SDS has a number of characteristic artifacts that limit its utility in general-purpose applications. In this paper, we make…
Humans can learn to manipulate new objects by simply watching others; providing robots with the ability to learn from such demonstrations would enable a natural interface specifying new behaviors. This work develops Robot See Robot Do (RSRD), a method for imitating articulated object manipulation fr…
Humans can infer 3D structure from 2D images of an object based on past experience and improve their 3D understanding as they see more images. Inspired by this behavior we introduce SAP3D a system for 3D reconstruction and novel view synthesis from an arbitrary number of unposed images. Given a few…
We present a framework for generating appropriate facial responses from a listener in dyadic social interactions based on the speaker's words. Given an input transcription of the speaker's words with their timestamps, our approach autoregressively predicts a response of a listener: a sequence of lis…
We propose a method to reconstruct global human trajectories from videos in the wild. Our optimization method decouples the camera and human motion, which allows us to place people in the same world coordinate frame. Most existing methods do not model the camera motion; methods that rely on the back…
Given a set of calibrated images of a scene, we present an approach that produces a simple, compact, and actionable 3D world representation by means of 3D primitives. While many approaches focus on recovering high-fidelity 3D scenes, we focus on parsing a scene into mid-level 3D representations made…
We present an approach to reconstruct humans and track them over time. At the core of our approach, we propose a fully "transformerized" version of a network for human mesh recovery. This network, HMR 2.0, advances the state of the art and shows the capability to analyze unusual poses that have in t…
We propose a method for editing NeRF scenes with text-instructions. Given a NeRF of a scene and the collection of images used to reconstruct it, our method uses an image-conditioned diffusion model (InstructPix2Pix) to iteratively edit the input images while optimizing the underlying scene, resultin…
We introduce k-planes, a white-box model for radiance fields in arbitrary dimensions. Our model uses d-choose-2 planes to represent a d-dimensional scene, providing a seamless way to go from static (d=3) to dynamic (d=4) scenes. This planar factorization makes adding dimension-specific priors easy,…
Humans describe the physical world using natural language to refer to specific 3D locations based on a vast range of properties: visual appearance, semantics, abstract associations, or actionable affordances. In this work we propose Language Embedded Radiance Fields (LERFs), a method for grounding l…
Grasping objects by a specific subpart is often crucial for safety and for executing downstream tasks. We propose LERF-TOGO, Language Embedded Radiance Fields for Task-Oriented Grasping of Objects, which uses vision-language models zero-shot to output a grasp distribution over an object given a natu…
Optimizing and rendering Neural Radiance Fields is computationally expensive due to the vast number of samples required by volume rendering. Recent works have included alternative sampling approaches to help accelerate their methods, however, they are often not the focus of the work. In this paper,…
Casually captured Neural Radiance Fields (NeRFs) suffer from artifacts such as floaters or flawed geometry when rendered outside the input camera trajectory. Existing evaluation protocols often do not capture these effects, since they usually only assess image quality at every 8th frame of the train…
In this work we study the benefits of using tracking and 3D poses for action recognition. To achieve this, we take the Lagrangian view on analysing actions over a trajectory of human motion rather than at a fixed point in space. Taking this stand allows us to use the tracklets of people to predict t…
We describe a method to extract persistent elements of a dynamic scene from an input video. We represent each scene element as a Deformable Sprite consisting of three components: 1) a 2D texture image for the entire video, 2) per-frame masks for the element, and 3) non-rigid deformations that map th…
Implicit shape models are promising 3D representations for modeling arbitrary locations, with Signed Distance Functions (SDFs) particularly suitable for clear mesh surface reconstruction. Existing approaches for single object reconstruction impose supervision signals based on the loss of the signed…
Sequential robot grasping of transparent objects, where a robot removes objects one by one from a workspace, is important in many industrial and household scenarios. We propose Evolving NeRF (Evo-NeRF), leveraging recent speedups in NeRF training and further extending it to rapidly train the NeRF re…
Videos from edited media like movies are a useful, yet under-explored source of information, with rich variety of appearance and interactions between humans depicted over a large temporal context. However, the richness of data comes at the expense of fundamental challenges such as abrupt shot change…
"We present a method for learning to generate unbounded flythrough videos of natural scenes starting from a single view. This capability is learned from a collection of single photographs, without requiring camera poses or even multiple views of each scene. To achieve this, we propose a novel self-s…
We present a framework for modeling interactional communication in dyadic conversations: given multimodal inputs of a speaker, we autoregressively output multiple possibilities of corresponding listener motion. We combine the motion and speech audio of the speaker using a motion-audio cross attentio…
We study the recent progress on dynamic view synthesis (DVS) from monocular video. Though existing approaches have demonstrated impressive results, we show a discrepancy between the practical capture process and the existing experimental protocols, which effectively leaks in multi-view signals durin…
We introduce Plenoxels (plenoptic voxels), a system for photorealistic view synthesis. Plenoxels represent a scene as a sparse 3D grid with spherical harmonics. This representation can be optimized from calibrated images via gradient methods and regularization without any neural components. On stand…
"In this work, we study how the performance and evaluation of generative image models are impacted by the racial composition of the datasets upon which these models are trained. By examining and controlling the racial distributions in various training datasets, we are able to observe the impacts of…
"Coordinate-based volumetric representations have the potential to generate photo-realistic virtual avatars from images. However, virtual avatars need to be controllable and be rendered in novel poses that may not have been observed. Traditional techniques, such as LBS, provide such a controlling fu…
"TV shows depict a wide variety of human behaviors and have been studied extensively for their potential to be a rich source of data for many applications. However, the majority of the existing work focuses on 2D recognition tasks. In this paper, we make the observation that there is a certain persi…
We present an approach for tracking people in monocular videos by predicting their future 3D representations. To achieve this, we first lift people to 3D from a single frame in a robust manner. This lifting includes information about the 3D pose of the person, their location in the 3D space, and the…
We present AIST++, a new multi-modal dataset of 3D dance motion and music, along with FACT, a Full-Attention Cross-modal Transformer network for generating 3D dance motion conditioned on music. The proposed AIST++ dataset contains 1.1M frames of 3D dance motion in 1408 sequences, covering 10 dance g…
Recent works have shown exciting results in unsupervised image de-rendering--learning to decompose 3D shape, appearance, and lighting from single-image collections without explicit supervision. However, many of these assume simplistic material and lighting models. We propose a method, termed RADAR,…
We introduce the problem of perpetual view generation - long-range generation of novel views corresponding to an arbitrarily long camera trajectory given a single image. This is a challenging problem that goes far beyond the capabilities of current view synthesis methods, which quickly degenerate wh…
We introduce KeypointDeformer, a novel unsupervised method for shape control through automatically discovered 3D keypoints. We cast this as the problem of aligning a source 3D object to a target 3D object from the same object category. Our method analyzes the difference between the shapes of the two…
We introduce a method to render Neural Radiance Fields (NeRFs) in real time using PlenOctrees, an octree-based 3D representation which supports view-dependent effects. Our method can render 800x800 images at more than 150 FPS, which is over 3000 times faster than conventional NeRFs. We do so without…
We study the problem of understanding hand-object interactions from 2D images in the wild. This requires reconstructing both the hand and the object in 3D, which is challenging because of the mutual occlusion between the hand and the object. In this paper we make two main contributions: (1) a novel…
We present a novel approach for tracking multiple people in video. Unlike past approaches which employ 2D representations, we focus on using 3D representations of people, located in three-dimensional space. To this end, we develop a method, Human Mesh and Appearance Recovery (HMAR) which in addition…
We propose pixelNeRF, a learning framework that predicts a continuous neural scene representation conditioned on one or few input images. The existing approach for constructing neural radiance fields (NeRFs) involves optimizing the representation to every scene independently, requiring many calibrat…
Symmetric orthogonalization via SVD, and closely related procedures, are well-known techniques for projecting matrices onto O(n) or SO(n). These tools have long been used for applications in computer vision, for example optimal 3D alignment problems solved by orthogonal Procrustes, rotation averagin…
We present a method that infers spatial arrangements and shapes of humans and objects in a globally consistent 3D scene, all from a single image in-the-wild captured in an uncontrolled environment. Notably, our method runs on datasets without any scene- or object-level 3D supervision. Our key insigh…
We present a learning framework that learns to recover the 3D shape, pose and texture from a single image, trained on an image collection without any ground truth 3D shape, multi-view, camera viewpoints or keypoint supervision. We approach this highly under-constrained problem in a ``analysis by syn…
From an image of a person in action, we can easily guess the 3D motion of the person in the immediate past and future. This is because we have a mental model of 3D human dynamics that we have acquired from observing visual sequences of humans in motion. We present a framework that can similarly lear…
We introduce Pixel-aligned Implicit Function (PIFu), an implicit representation that locally aligns pixels of 2D images with the global context of their corresponding 3D object. Using PIFu, we propose an end-to-end deep learning method for digitizing highly detailed clothed humans that can infer bot…
Given a video of a person in action, we can easily guess the 3D future motion of the person. In this work, we present perhaps the first approach for predicting a future 3D mesh model sequence of a person from past video input. We do this for periodic motions such as walking and also actions like bow…
We present the first method to perform automatic 3D pose, shape and texture capture of animals from images acquired in-the-wild. In particular, we focus on the problem of capturing 3D information about Grevy's zebras from a collection of images. The Grevy's zebra is one of the most endangered specie…
Adversarial learning methods have been proposed for a wide range of applications, but the training of adversarial models can be notoriously unstable. Effectively balancing the performance of the generator and discriminator is critical, since a discriminator that achieves very high accuracy will prod…
We describe Human Mesh Recovery (HMR), an end-to-end framework for reconstructing a full 3D mesh of a human body from a single RGB image. In contrast to most current methods that compute 2D or 3D joint locations, we produce a richer and more useful mesh representation that is parameterized by shape…
We present a learning framework for recovering the 3D shape, camera, and texture of an object from a single image. The shape is represented as a deformable 3D mesh model of an object category where a shape is parameterized by a learned mean shape and per-instance predicted deformation. Our approach…
Animals are widespread in nature and the analysis of their shape and motion is important in many fields and industries. Modeling 3D animal shape, however, is difficult because the 3D scanning methods used to capture human shape are not applicable to wild animals or natural settings. Consequently, we…
We present SfSNet, an end-to-end learning framework for producing an accurate decomposition of an unconstrained human face image into shape, reflectance and illuminance. SfSNet is designed to reflect a physical lambertian rendering model. SfSNet learns from a mixture of labeled synthetic and unlabel…
There has been significant work on learning realistic, articulated, 3D models of the human body. In contrast, there are few such models of animals, despite many applications. The main challenge is that animals are much less cooperative than humans. The best human body models are learned from thousan…
We present an approach to matching images of objects in fine-grained datasets without using part annotations, with an application to the challenging problem of weakly supervised single-view reconstruction. This is in contrast to prior works that require part annotations, since matching objects acros…