Shubham Tulsiani

Yufei Ye, Abhinav Gupta, Shubham Tulsiani

Our work aims to reconstruct hand-held objects given a single RGB image. In contrast to prior works that typically assume known 3D templates and reduce the problem to 3D pose estimation, our work reconstructs generic hand-held object without knowing their 3D templates. Our key insight is that hand articulation is highly predictive of the object shape, and we propose an approach that conditionally reconstructs the object based on the articulation and the visual input. Given an image depicting a hand-held object, we first use off-the-shelf systems to estimate the underlying hand pose and then infer the object shape in a normalized hand-centric coordinate frame. We parameterized the object by signed distance which are inferred by an implicit network which leverages the information from both visual feature and articulation-aware coordinates to process a query point. We perform experiments across three datasets and show that our method consistently outperforms baselines and is able to reconstruct a diverse set of objects. We analyze the benefits and robustness of explicit articulation conditioning and also show that this allows the hand pose estimation to further improve in test-time optimization.

Jason Y. Zhang, Deva Ramanan, Shubham Tulsiani

We describe a data-driven method for inferring the camera viewpoints given multiple images of an arbitrary object. This task is a core component of classic geometric pipelines such as SfM and SLAM, and also serves as a vital pre-processing requirement for contemporary neural approaches (e.g. NeRF) to object reconstruction and view synthesis. In contrast to existing correspondence-driven methods that do not perform well given sparse views, we propose a top-down prediction based approach for estimating camera viewpoints. Our key technical insight is the use of an energy-based formulation for representing distributions over relative camera rotations, thus allowing us to explicitly represent multiple camera modes arising from object symmetries or views. Leveraging these relative predictions, we jointly estimate a consistent set of camera rotations from multiple images. We show that our approach outperforms state-of-the-art SfM and SLAM methods given sparse images on both seen and unseen categories. Further, our probabilistic approach significantly outperforms directly regressing relative poses, suggesting that modeling multimodality is important for coherent joint reconstruction. We demonstrate that our system can be a stepping stone toward in-the-wild reconstruction from multi-view datasets. The project page with code and videos can be found at https://jasonyzhang.com/relpose.

Hang Gao, Ruilong Li, Shubham Tulsiani et al.

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 during training. We define effective multi-view factors (EMFs) to quantify the amount of multi-view signal present in the input capture sequence based on the relative camera-scene motion. We introduce two new metrics: co-visibility masked image metrics and correspondence accuracy, which overcome the issue in existing protocols. We also propose a new iPhone dataset that includes more diverse real-life deformation sequences. Using our proposed experimental protocol, we show that the state-of-the-art approaches observe a 1-2 dB drop in masked PSNR in the absence of multi-view cues and 4-5 dB drop when modeling complex motion. Code and data can be found at https://hangg7.com/dycheck.

Paritosh Mittal, Yen-Chi Cheng, Maneesh Singh et al.

Powerful priors allow us to perform inference with insufficient information. In this paper, we propose an autoregressive prior for 3D shapes to solve multimodal 3D tasks such as shape completion, reconstruction, and generation. We model the distribution over 3D shapes as a non-sequential autoregressive distribution over a discretized, low-dimensional, symbolic grid-like latent representation of 3D shapes. This enables us to represent distributions over 3D shapes conditioned on information from an arbitrary set of spatially anchored query locations and thus perform shape completion in such arbitrary settings (e.g., generating a complete chair given only a view of the back leg). We also show that the learned autoregressive prior can be leveraged for conditional tasks such as single-view reconstruction and language-based generation. This is achieved by learning task-specific naive conditionals which can be approximated by light-weight models trained on minimal paired data. We validate the effectiveness of the proposed method using both quantitative and qualitative evaluation and show that the proposed method outperforms the specialized state-of-the-art methods trained for individual tasks. The project page with code and video visualizations can be found at https://yccyenchicheng.github.io/AutoSDF/.

Homanga Bharadhwaj, Debidatta Dwibedi, Abhinav Gupta et al.

How can robot manipulation policies generalize to novel tasks involving unseen object types and new motions? In this paper, we provide a solution in terms of predicting motion information from web data through human video generation and conditioning a robot policy on the generated video. Instead of attempting to scale robot data collection which is expensive, we show how we can leverage video generation models trained on easily available web data, for enabling generalization. Our approach Gen2Act casts language-conditioned manipulation as zero-shot human video generation followed by execution with a single policy conditioned on the generated video. To train the policy, we use an order of magnitude less robot interaction data compared to what the video prediction model was trained on. Gen2Act doesn't require fine-tuning the video model at all and we directly use a pre-trained model for generating human videos. Our results on diverse real-world scenarios show how Gen2Act enables manipulating unseen object types and performing novel motions for tasks not present in the robot data. Videos are at https://homangab.github.io/gen2act/

Zhizhuo Zhou, Shubham Tulsiani

We propose SparseFusion, a sparse view 3D reconstruction approach that unifies recent advances in neural rendering and probabilistic image generation. Existing approaches typically build on neural rendering with re-projected features but fail to generate unseen regions or handle uncertainty under large viewpoint changes. Alternate methods treat this as a (probabilistic) 2D synthesis task, and while they can generate plausible 2D images, they do not infer a consistent underlying 3D. However, we find that this trade-off between 3D consistency and probabilistic image generation does not need to exist. In fact, we show that geometric consistency and generative inference can be complementary in a mode-seeking behavior. By distilling a 3D consistent scene representation from a view-conditioned latent diffusion model, we are able to recover a plausible 3D representation whose renderings are both accurate and realistic. We evaluate our approach across 51 categories in the CO3D dataset and show that it outperforms existing methods, in both distortion and perception metrics, for sparse-view novel view synthesis.

Kalyan Vasudev Alwala, Abhinav Gupta, Shubham Tulsiani

Our work learns a unified model for single-view 3D reconstruction of objects from hundreds of semantic categories. As a scalable alternative to direct 3D supervision, our work relies on segmented image collections for learning 3D of generic categories. Unlike prior works that use similar supervision but learn independent category-specific models from scratch, our approach of learning a unified model simplifies the training process while also allowing the model to benefit from the common structure across categories. Using image collections from standard recognition datasets, we show that our approach allows learning 3D inference for over 150 object categories. We evaluate using two datasets and qualitatively and quantitatively show that our unified reconstruction approach improves over prior category-specific reconstruction baselines. Our final 3D reconstruction model is also capable of zero-shot inference on images from unseen object categories and we empirically show that increasing the number of training categories improves the reconstruction quality.

Homanga Bharadhwaj, Jay Vakil, Mohit Sharma et al.

The grand aim of having a single robot that can manipulate arbitrary objects in diverse settings is at odds with the paucity of robotics datasets. Acquiring and growing such datasets is strenuous due to manual efforts, operational costs, and safety challenges. A path toward such an universal agent would require a structured framework capable of wide generalization but trained within a reasonable data budget. In this paper, we develop an efficient system (RoboAgent) for training universal agents capable of multi-task manipulation skills using (a) semantic augmentations that can rapidly multiply existing datasets and (b) action representations that can extract performant policies with small yet diverse multi-modal datasets without overfitting. In addition, reliable task conditioning and an expressive policy architecture enable our agent to exhibit a diverse repertoire of skills in novel situations specified using language commands. Using merely 7500 demonstrations, we are able to train a single agent capable of 12 unique skills, and demonstrate its generalization over 38 tasks spread across common daily activities in diverse kitchen scenes. On average, RoboAgent outperforms prior methods by over 40% in unseen situations while being more sample efficient and being amenable to capability improvements and extensions through fine-tuning. Videos at https://robopen.github.io/

Yufei Ye, Xueting Li, Abhinav Gupta et al.

Recent successes in image synthesis are powered by large-scale diffusion models. However, most methods are currently limited to either text- or image-conditioned generation for synthesizing an entire image, texture transfer or inserting objects into a user-specified region. In contrast, in this work we focus on synthesizing complex interactions (ie, an articulated hand) with a given object. Given an RGB image of an object, we aim to hallucinate plausible images of a human hand interacting with it. We propose a two-step generative approach: a LayoutNet that samples an articulation-agnostic hand-object-interaction layout, and a ContentNet that synthesizes images of a hand grasping the object given the predicted layout. Both are built on top of a large-scale pretrained diffusion model to make use of its latent representation. Compared to baselines, the proposed method is shown to generalize better to novel objects and perform surprisingly well on out-of-distribution in-the-wild scenes of portable-sized objects. The resulting system allows us to predict descriptive affordance information, such as hand articulation and approaching orientation. Project page: https://judyye.github.io/affordiffusion-www

Yufei Ye, Poorvi Hebbar, Abhinav Gupta et al.

We tackle the task of reconstructing hand-object interactions from short video clips. Given an input video, our approach casts 3D inference as a per-video optimization and recovers a neural 3D representation of the object shape, as well as the time-varying motion and hand articulation. While the input video naturally provides some multi-view cues to guide 3D inference, these are insufficient on their own due to occlusions and limited viewpoint variations. To obtain accurate 3D, we augment the multi-view signals with generic data-driven priors to guide reconstruction. Specifically, we learn a diffusion network to model the conditional distribution of (geometric) renderings of objects conditioned on hand configuration and category label, and leverage it as a prior to guide the novel-view renderings of the reconstructed scene. We empirically evaluate our approach on egocentric videos across 6 object categories, and observe significant improvements over prior single-view and multi-view methods. Finally, we demonstrate our system's ability to reconstruct arbitrary clips from YouTube, showing both 1st and 3rd person interactions.

Homanga Bharadhwaj, Abhinav Gupta, Shubham Tulsiani et al.

Can we learn robot manipulation for everyday tasks, only by watching videos of humans doing arbitrary tasks in different unstructured settings? Unlike widely adopted strategies of learning task-specific behaviors or direct imitation of a human video, we develop a a framework for extracting agent-agnostic action representations from human videos, and then map it to the agent's embodiment during deployment. Our framework is based on predicting plausible human hand trajectories given an initial image of a scene. After training this prediction model on a diverse set of human videos from the internet, we deploy the trained model zero-shot for physical robot manipulation tasks, after appropriate transformations to the robot's embodiment. This simple strategy lets us solve coarse manipulation tasks like opening and closing drawers, pushing, and tool use, without access to any in-domain robot manipulation trajectories. Our real-world deployment results establish a strong baseline for action prediction information that can be acquired from diverse arbitrary videos of human activities, and be useful for zero-shot robotic manipulation in unseen scenes.

Jeff Tan, Donglai Xiang, Shubham Tulsiani et al.

We present a method to reconstruct time-consistent human body models from monocular videos, focusing on extremely loose clothing or handheld object interactions. Prior work in human reconstruction is either limited to tight clothing with no object interactions, or requires calibrated multi-view captures or personalized template scans which are costly to collect at scale. Our key insight for high-quality yet flexible reconstruction is the careful combination of generic human priors about articulated body shape (learned from large-scale training data) with video-specific articulated "bag-of-bones" deformation (fit to a single video via test-time optimization). We accomplish this by learning a neural implicit model that disentangles body versus clothing deformations as separate motion model layers. To capture subtle geometry of clothing, we leverage image-based priors such as human body pose, surface normals, and optical flow during optimization. The resulting neural fields can be extracted into time-consistent meshes, or further optimized as explicit 3D Gaussians for high-fidelity interactive rendering. On datasets with highly challenging clothing deformations and object interactions, DressRecon yields higher-fidelity 3D reconstructions than prior art. Project page: https://jefftan969.github.io/dressrecon/

Alexey Bokhovkin, Shubham Tulsiani, Angela Dai

Remarkable advances have been achieved recently in learning neural representations that characterize object geometry, while generating textured objects suitable for downstream applications and 3D rendering remains at an early stage. In particular, reconstructing textured geometry from images of real objects is a significant challenge -- reconstructed geometry is often inexact, making realistic texturing a significant challenge. We present Mesh2Tex, which learns a realistic object texture manifold from uncorrelated collections of 3D object geometry and photorealistic RGB images, by leveraging a hybrid mesh-neural-field texture representation. Our texture representation enables compact encoding of high-resolution textures as a neural field in the barycentric coordinate system of the mesh faces. The learned texture manifold enables effective navigation to generate an object texture for a given 3D object geometry that matches to an input RGB image, which maintains robustness even under challenging real-world scenarios where the mesh geometry approximates an inexact match to the underlying geometry in the RGB image. Mesh2Tex can effectively generate realistic object textures for an object mesh to match real images observations towards digitization of real environments, significantly improving over previous state of the art.

Yehonathan Litman, Or Patashnik, Kangle Deng et al.

Recent works in inverse rendering have shown promise in using multi-view images of an object to recover shape, albedo, and materials. However, the recovered components often fail to render accurately under new lighting conditions due to the intrinsic challenge of disentangling albedo and material properties from input images. To address this challenge, we introduce MaterialFusion, an enhanced conventional 3D inverse rendering pipeline that incorporates a 2D prior on texture and material properties. We present StableMaterial, a 2D diffusion model prior that refines multi-lit data to estimate the most likely albedo and material from given input appearances. This model is trained on albedo, material, and relit image data derived from a curated dataset of approximately ~12K artist-designed synthetic Blender objects called BlenderVault. we incorporate this diffusion prior with an inverse rendering framework where we use score distillation sampling (SDS) to guide the optimization of the albedo and materials, improving relighting performance in comparison with previous work. We validate MaterialFusion's relighting performance on 4 datasets of synthetic and real objects under diverse illumination conditions, showing our diffusion-aided approach significantly improves the appearance of reconstructed objects under novel lighting conditions. We intend to publicly release our BlenderVault dataset to support further research in this field.

Naveen Venkat, Mayank Agarwal, Maneesh Singh et al.

We tackle the task of synthesizing novel views of an object given a few input images and associated camera viewpoints. Our work is inspired by recent 'geometry-free' approaches where multi-view images are encoded as a (global) set-latent representation, which is then used to predict the color for arbitrary query rays. While this representation yields (coarsely) accurate images corresponding to novel viewpoints, the lack of geometric reasoning limits the quality of these outputs. To overcome this limitation, we propose 'Geometry-biased Transformers' (GBTs) that incorporate geometric inductive biases in the set-latent representation-based inference to encourage multi-view geometric consistency. We induce the geometric bias by augmenting the dot-product attention mechanism to also incorporate 3D distances between rays associated with tokens as a learnable bias. We find that this, along with camera-aware embeddings as input, allows our models to generate significantly more accurate outputs. We validate our approach on the real-world CO3D dataset, where we train our system over 10 categories and evaluate its view-synthesis ability for novel objects as well as unseen categories. We empirically validate the benefits of the proposed geometric biases and show that our approach significantly improves over prior works.

Yu Wu, Minsik Jeon, Jen-Hao Rick Chang et al.

We study positional encodings for multi-view transformers that process tokens from a set of posed input images, and seek a mechanism that encodes patches uniquely, allows SE(3)-invariant attention with multi-frequency similarity, and can be adaptive to the geometry of the underlying scene. We find that prior (absolute or relative) encoding schemes for multi-view attention do not meet the above desiderata, and present RayRoPE to address this gap. RayRoPE represents patch positions based on associated rays but leverages a predicted point along the ray instead of the direction for a geometry-aware encoding. To achieve SE(3) invariance, RayRoPE computes query-frame projective coordinates for computing multi-frequency similarity. Lastly, as the 'predicted' 3D point along a ray may not be precise, RayRoPE presents a mechanism to analytically compute the expected position encoding under uncertainty. We validate RayRoPE on the tasks of novel-view synthesis and stereo depth estimation and show that it consistently improves over alternate position encoding schemes (e.g. 15% relative improvement on LPIPS in CO3D). We also show that RayRoPE can seamlessly incorporate RGB-D input, resulting in even larger gains over alternatives that cannot positionally encode this information.

Nikolaos Gkanatsios, Mayank Singh, Zhaoyuan Fang et al.

We present Analogical Networks, a model that encodes domain knowledge explicitly, in a collection of structured labelled 3D scenes, in addition to implicitly, as model parameters, and segments 3D object scenes with analogical reasoning: instead of mapping a scene to part segments directly, our model first retrieves related scenes from memory and their corresponding part structures, and then predicts analogous part structures for the input scene, via an end-to-end learnable modulation mechanism. By conditioning on more than one retrieved memories, compositions of structures are predicted, that mix and match parts across the retrieved memories. One-shot, few-shot or many-shot learning are treated uniformly in Analogical Networks, by conditioning on the appropriate set of memories, whether taken from a single, few or many memory exemplars, and inferring analogous parses. We show Analogical Networks are competitive with state-of-the-art 3D segmentation transformers in many-shot settings, and outperform them, as well as existing paradigms of meta-learning and few-shot learning, in few-shot settings. Analogical Networks successfully segment instances of novel object categories simply by expanding their memory, without any weight updates. Our code and models are publicly available in the project webpage: http://analogicalnets.github.io/.

Yehonathan Litman, Shikun Liu, Dario Seyb et al.

High-fidelity generative video editing has seen significant quality improvements by leveraging pre-trained video foundation models. However, their computational cost is a major bottleneck, as they are often designed to inefficiently process the full video context regardless of the inpainting mask's size, even for sparse, localized edits. In this paper, we introduce EditCtrl, an efficient video inpainting control framework that focuses computation only where it is needed. Our approach features a novel local video context module that operates solely on masked tokens, yielding a computational cost proportional to the edit size. This local-first generation is then guided by a lightweight temporal global context embedder that ensures video-wide context consistency with minimal overhead. Not only is EditCtrl 10 times more compute efficient than state-of-the-art generative editing methods, it even improves editing quality compared to methods designed with full-attention. Finally, we showcase how EditCtrl unlocks new capabilities, including multi-region editing with text prompts and autoregressive content propagation.

Qitao Zhao, Hao Tan, Qianqian Wang et al.

Self-supervised pre-training has revolutionized foundation models for languages, individual 2D images and videos, but remains largely unexplored for learning 3D-aware representations from multi-view images. In this paper, we present E-RayZer, a self-supervised large 3D Vision model that learns truly 3D-aware representations directly from unlabeled images. Unlike prior self-supervised methods such as RayZer that infer 3D indirectly through latent-space view synthesis, E-RayZer operates directly in 3D space, performing self-supervised 3D reconstruction with Explicit geometry. This formulation eliminates shortcut solutions and yields representations that are geometrically grounded. To ensure convergence and scalability, we introduce a novel fine-grained learning curriculum that organizes training from easy to hard samples and harmonizes heterogeneous data sources in an entirely unsupervised manner. Experiments demonstrate that E-RayZer significantly outperforms RayZer on pose estimation, matches or sometimes surpasses fully supervised reconstruction models such as VGGT. Furthermore, its learned representations outperform leading visual pre-training models (e.g., DINOv3, CroCo v2, VideoMAE V2, and RayZer) when transferring to 3D downstream tasks, establishing E-RayZer as a new paradigm for 3D-aware visual pre-training.

Yuxuan Kuang, Sungjae Park, Katerina Fragkiadaki et al.

Learning generalist policies capable of accomplishing a plethora of everyday tasks remains an open challenge in dexterous manipulation. In particular, collecting large-scale manipulation data via real-world teleoperation is expensive and difficult to scale. While learning in simulation provides a feasible alternative, designing multiple task-specific environments and rewards for training is similarly challenging. We propose Dex4D, a framework that instead leverages simulation for learning task-agnostic dexterous skills that can be flexibly recomposed to perform diverse real-world manipulation tasks. Specifically, Dex4D learns a domain-agnostic 3D point track conditioned policy capable of manipulating any object to any desired pose. We train this 'Anypose-to-Anypose' policy in simulation across thousands of objects with diverse pose configurations, covering a broad space of robot-object interactions that can be composed at test time. At deployment, this policy can be zero-shot transferred to real-world tasks without finetuning, simply by prompting it with desired object-centric point tracks extracted from generated videos. During execution, Dex4D uses online point tracking for closed-loop perception and control. Extensive experiments in simulation and on real robots show that our method enables zero-shot deployment for diverse dexterous manipulation tasks and yields consistent improvements over prior baselines. Furthermore, we demonstrate strong generalization to novel objects, scene layouts, backgrounds, and trajectories, highlighting the robustness and scalability of the proposed framework.

Zhongxiao Cong, Qitao Zhao, Minsik Jeon et al.

Current feed-forward 3D/4D reconstruction systems rely on dense geometry and pose supervision -- expensive to obtain at scale and particularly scarce for dynamic real-world scenes. We present Flow3r, a framework that augments visual geometry learning with dense 2D correspondences (`flow') as supervision, enabling scalable training from unlabeled monocular videos. Our key insight is that the flow prediction module should be factored: predicting flow between two images using geometry latents from one and pose latents from the other. This factorization directly guides the learning of both scene geometry and camera motion, and naturally extends to dynamic scenes. In controlled experiments, we show that factored flow prediction outperforms alternative designs and that performance scales consistently with unlabeled data. Integrating factored flow into existing visual geometry architectures and training with ${\sim}800$K unlabeled videos, Flow3r achieves state-of-the-art results across eight benchmarks spanning static and dynamic scenes, with its largest gains on in-the-wild dynamic videos where labeled data is most scarce.

Bernardo Aceituno, Alberto Rodriguez, Shubham Tulsiani et al.

Specifying tasks with videos is a powerful technique towards acquiring novel and general robot skills. However, reasoning over mechanics and dexterous interactions can make it challenging to scale learning contact-rich manipulation. In this work, we focus on the problem of visual non-prehensile planar manipulation: given a video of an object in planar motion, find contact-aware robot actions that reproduce the same object motion. We propose a novel architecture, Differentiable Learning for Manipulation (\ours), that combines video decoding neural models with priors from contact mechanics by leveraging differentiable optimization and finite difference based simulation. Through extensive simulated experiments, we investigate the interplay between traditional model-based techniques and modern deep learning approaches. We find that our modular and fully differentiable architecture performs better than learning-only methods on unseen objects and motions. \url{https://github.com/baceituno/dlm}.

Jason Y. Zhang, Amy Lin, Moneish Kumar et al.

Estimating camera poses is a fundamental task for 3D reconstruction and remains challenging given sparsely sampled views (<10). In contrast to existing approaches that pursue top-down prediction of global parametrizations of camera extrinsics, we propose a distributed representation of camera pose that treats a camera as a bundle of rays. This representation allows for a tight coupling with spatial image features improving pose precision. We observe that this representation is naturally suited for set-level transformers and develop a regression-based approach that maps image patches to corresponding rays. To capture the inherent uncertainties in sparse-view pose inference, we adapt this approach to learn a denoising diffusion model which allows us to sample plausible modes while improving performance. Our proposed methods, both regression- and diffusion-based, demonstrate state-of-the-art performance on camera pose estimation on CO3D while generalizing to unseen object categories and in-the-wild captures.

Homanga Bharadhwaj, Roozbeh Mottaghi, Abhinav Gupta et al.

We seek to learn a generalizable goal-conditioned policy that enables zero-shot robot manipulation: interacting with unseen objects in novel scenes without test-time adaptation. While typical approaches rely on a large amount of demonstration data for such generalization, we propose an approach that leverages web videos to predict plausible interaction plans and learns a task-agnostic transformation to obtain robot actions in the real world. Our framework,Track2Act predicts tracks of how points in an image should move in future time-steps based on a goal, and can be trained with diverse videos on the web including those of humans and robots manipulating everyday objects. We use these 2D track predictions to infer a sequence of rigid transforms of the object to be manipulated, and obtain robot end-effector poses that can be executed in an open-loop manner. We then refine this open-loop plan by predicting residual actions through a closed loop policy trained with a few embodiment-specific demonstrations. We show that this approach of combining scalably learned track prediction with a residual policy requiring minimal in-domain robot-specific data enables diverse generalizable robot manipulation, and present a wide array of real-world robot manipulation results across unseen tasks, objects, and scenes. https://homangab.github.io/track2act/

Hanzhe Hu, Zhizhuo Zhou, Varun Jampani et al.

We present MVD-Fusion: a method for single-view 3D inference via generative modeling of multi-view-consistent RGB-D images. While recent methods pursuing 3D inference advocate learning novel-view generative models, these generations are not 3D-consistent and require a distillation process to generate a 3D output. We instead cast the task of 3D inference as directly generating mutually-consistent multiple views and build on the insight that additionally inferring depth can provide a mechanism for enforcing this consistency. Specifically, we train a denoising diffusion model to generate multi-view RGB-D images given a single RGB input image and leverage the (intermediate noisy) depth estimates to obtain reprojection-based conditioning to maintain multi-view consistency. We train our model using large-scale synthetic dataset Obajverse as well as the real-world CO3D dataset comprising of generic camera viewpoints. We demonstrate that our approach can yield more accurate synthesis compared to recent state-of-the-art, including distillation-based 3D inference and prior multi-view generation methods. We also evaluate the geometry induced by our multi-view depth prediction and find that it yields a more accurate representation than other direct 3D inference approaches.

Yufei Ye, Abhinav Gupta, Kris Kitani et al.

We propose G-HOP, a denoising diffusion based generative prior for hand-object interactions that allows modeling both the 3D object and a human hand, conditioned on the object category. To learn a 3D spatial diffusion model that can capture this joint distribution, we represent the human hand via a skeletal distance field to obtain a representation aligned with the (latent) signed distance field for the object. We show that this hand-object prior can then serve as generic guidance to facilitate other tasks like reconstruction from interaction clip and human grasp synthesis. We believe that our model, trained by aggregating seven diverse real-world interaction datasets spanning across 155 categories, represents a first approach that allows jointly generating both hand and object. Our empirical evaluations demonstrate the benefit of this joint prior in video-based reconstruction and human grasp synthesis, outperforming current task-specific baselines. Project website: https://judyye.github.io/ghop-www

Bharath Raj Nagoor Kani, Hsin-Ying Lee, Sergey Tulyakov et al.

We propose UpFusion, a system that can perform novel view synthesis and infer 3D representations for an object given a sparse set of reference images without corresponding pose information. Current sparse-view 3D inference methods typically rely on camera poses to geometrically aggregate information from input views, but are not robust in-the-wild when such information is unavailable/inaccurate. In contrast, UpFusion sidesteps this requirement by learning to implicitly leverage the available images as context in a conditional generative model for synthesizing novel views. We incorporate two complementary forms of conditioning into diffusion models for leveraging the input views: a) via inferring query-view aligned features using a scene-level transformer, b) via intermediate attentional layers that can directly observe the input image tokens. We show that this mechanism allows generating high-fidelity novel views while improving the synthesis quality given additional (unposed) images. We evaluate our approach on the Co3Dv2 and Google Scanned Objects datasets and demonstrate the benefits of our method over pose-reliant sparse-view methods as well as single-view methods that cannot leverage additional views. Finally, we also show that our learned model can generalize beyond the training categories and even allow reconstruction from self-captured images of generic objects in-the-wild.

Alexey Bokhovkin, Quan Meng, Shubham Tulsiani et al.

We present SceneFactor, a diffusion-based approach for large-scale 3D scene generation that enables controllable generation and effortless editing. SceneFactor enables text-guided 3D scene synthesis through our factored diffusion formulation, leveraging latent semantic and geometric manifolds for generation of arbitrary-sized 3D scenes. While text input enables easy, controllable generation, text guidance remains imprecise for intuitive, localized editing and manipulation of the generated 3D scenes. Our factored semantic diffusion generates a proxy semantic space composed of semantic 3D boxes that enables controllable editing of generated scenes by adding, removing, changing the size of the semantic 3D proxy boxes that guides high-fidelity, consistent 3D geometric editing. Extensive experiments demonstrate that our approach enables high-fidelity 3D scene synthesis with effective controllable editing through our factored diffusion approach.

Khiem Vuong, Anurag Ghosh, Deva Ramanan et al.

We explore the task of geometric reconstruction of images captured from a mixture of ground and aerial views. Current state-of-the-art learning-based approaches fail to handle the extreme viewpoint variation between aerial-ground image pairs. Our hypothesis is that the lack of high-quality, co-registered aerial-ground datasets for training is a key reason for this failure. Such data is difficult to assemble precisely because it is difficult to reconstruct in a scalable way. To overcome this challenge, we propose a scalable framework combining pseudo-synthetic renderings from 3D city-wide meshes (e.g., Google Earth) with real, ground-level crowd-sourced images (e.g., MegaDepth). The pseudo-synthetic data simulates a wide range of aerial viewpoints, while the real, crowd-sourced images help improve visual fidelity for ground-level images where mesh-based renderings lack sufficient detail, effectively bridging the domain gap between real images and pseudo-synthetic renderings. Using this hybrid dataset, we fine-tune several state-of-the-art algorithms and achieve significant improvements on real-world, zero-shot aerial-ground tasks. For example, we observe that baseline DUSt3R localizes fewer than 5% of aerial-ground pairs within 5 degrees of camera rotation error, while fine-tuning with our data raises accuracy to nearly 56%, addressing a major failure point in handling large viewpoint changes. Beyond camera estimation and scene reconstruction, our dataset also improves performance on downstream tasks like novel-view synthesis in challenging aerial-ground scenarios, demonstrating the practical value of our approach in real-world applications.

Hanzhe Hu, Tianwei Yin, Fujun Luan et al.

We present Turbo3D, an ultra-fast text-to-3D system capable of generating high-quality Gaussian splatting assets in under one second. Turbo3D employs a rapid 4-step, 4-view diffusion generator and an efficient feed-forward Gaussian reconstructor, both operating in latent space. The 4-step, 4-view generator is a student model distilled through a novel Dual-Teacher approach, which encourages the student to learn view consistency from a multi-view teacher and photo-realism from a single-view teacher. By shifting the Gaussian reconstructor's inputs from pixel space to latent space, we eliminate the extra image decoding time and halve the transformer sequence length for maximum efficiency. Our method demonstrates superior 3D generation results compared to previous baselines, while operating in a fraction of their runtime.

Qitao Zhao, Shubham Tulsiani

Inferring the 3D structure underlying a set of multi-view images typically requires solving two co-dependent tasks -- accurate 3D reconstruction requires precise camera poses, and predicting camera poses relies on (implicitly or explicitly) modeling the underlying 3D. The classical framework of analysis by synthesis casts this inference as a joint optimization seeking to explain the observed pixels, and recent instantiations learn expressive 3D representations (e.g., Neural Fields) with gradient-descent-based pose refinement of initial pose estimates. However, given a sparse set of observed views, the observations may not provide sufficient direct evidence to obtain complete and accurate 3D. Moreover, large errors in pose estimation may not be easily corrected and can further degrade the inferred 3D. To allow robust 3D reconstruction and pose estimation in this challenging setup, we propose SparseAGS, a method that adapts this analysis-by-synthesis approach by: a) including novel-view-synthesis-based generative priors in conjunction with photometric objectives to improve the quality of the inferred 3D, and b) explicitly reasoning about outliers and using a discrete search with a continuous optimization-based strategy to correct them. We validate our framework across real-world and synthetic datasets in combination with several off-the-shelf pose estimation systems as initialization. We find that it significantly improves the base systems' pose accuracy while yielding high-quality 3D reconstructions that outperform the results from current multi-view reconstruction baselines.

Qitao Zhao, Amy Lin, Jeff Tan et al.

Current Structure-from-Motion (SfM) methods typically follow a two-stage pipeline, combining learned or geometric pairwise reasoning with a subsequent global optimization step. In contrast, we propose a data-driven multi-view reasoning approach that directly infers 3D scene geometry and camera poses from multi-view images. Our framework, DiffusionSfM, parameterizes scene geometry and cameras as pixel-wise ray origins and endpoints in a global frame and employs a transformer-based denoising diffusion model to predict them from multi-view inputs. To address practical challenges in training diffusion models with missing data and unbounded scene coordinates, we introduce specialized mechanisms that ensure robust learning. We empirically validate DiffusionSfM on both synthetic and real datasets, demonstrating that it outperforms classical and learning-based approaches while naturally modeling uncertainty.

Sungjae Park, Homanga Bharadhwaj, Shubham Tulsiani

We propose DemoDiffusion, a simple and scalable method for enabling robots to perform manipulation tasks in natural environments by imitating a single human demonstration. Our approach is based on two key insights. First, the hand motion in a human demonstration provides a useful prior for the robot's end-effector trajectory, which we can convert into a rough open-loop robot motion trajectory via kinematic retargeting. Second, while this retargeted motion captures the overall structure of the task, it may not align well with plausible robot actions in-context. To address this, we leverage a pre-trained generalist diffusion policy to modify the trajectory, ensuring it both follows the human motion and remains within the distribution of plausible robot actions. Our approach avoids the need for online reinforcement learning or paired human-robot data, enabling robust adaptation to new tasks and scenes with minimal manual effort. Experiments in both simulation and real-world settings show that DemoDiffusion outperforms both the base policy and the retargeted trajectory, enabling the robot to succeed even on tasks where the pre-trained generalist policy fails entirely. Project page: https://demodiffusion.github.io/

Hongyi Chen, Yunchao Yao, Yufei Ye et al.

Functional grasp is essential for enabling dexterous multi-finger robot hands to manipulate objects effectively. However, most prior work either focuses on power grasping, which simply involves holding an object still, or relies on costly teleoperated robot demonstrations to teach robots how to grasp each object functionally. Instead, we propose extracting human grasp information from web images since they depict natural and functional object interactions, thereby bypassing the need for curated demonstrations. We reconstruct human hand-object interaction (HOI) 3D meshes from RGB images, retarget the human hand to multi-finger robot hands, and align the noisy object mesh with its accurate 3D shape. We show that these relatively low-quality HOI data from inexpensive web sources can effectively train a functional grasping model. To further expand the grasp dataset for seen and unseen objects, we use the initially-trained grasping policy with web data in the IsaacGym simulator to generate physically feasible grasps while preserving functionality. We train the grasping model on 10 object categories and evaluate it on 9 unseen objects, including challenging items such as syringes, pens, spray bottles, and tongs, which are underrepresented in existing datasets. The model trained on the web HOI dataset, achieving a 75.8% success rate on seen objects and 61.8% across all objects in simulation, with a 6.7% improvement in success rate and a 1.8x increase in functionality ratings over baselines. Simulator-augmented data further boosts performance from 61.8% to 83.4%. The sim-to-real transfer to the LEAP Hand achieves a 85% success rate. Project website is at: https://web2grasp.github.io/.

Yufei Ye, Yao Feng, Omid Taheri et al.

We present HaPTIC, an approach that infers coherent 4D hand trajectories from monocular videos. Current video-based hand pose reconstruction methods primarily focus on improving frame-wise 3D pose using adjacent frames rather than studying consistent 4D hand trajectories in space. Despite the additional temporal cues, they generally underperform compared to image-based methods due to the scarcity of annotated video data. To address these issues, we repurpose a state-of-the-art image-based transformer to take in multiple frames and directly predict a coherent trajectory. We introduce two types of lightweight attention layers: cross-view self-attention to fuse temporal information, and global cross-attention to bring in larger spatial context. Our method infers 4D hand trajectories similar to the ground truth while maintaining strong 2D reprojection alignment. We apply the method to both egocentric and allocentric videos. It significantly outperforms existing methods in global trajectory accuracy while being comparable to the state-of-the-art in single-image pose estimation. Project website: https://judyye.github.io/haptic-www

Yanbo Xu, Yu Wu, Sungjae Park et al.

We present a mechanism to steer the sampling diversity of denoising diffusion and flow matching models, allowing users to sample from a sharper or broader distribution than the training distribution. We build on the observation that these models leverage (learned) score functions of noisy data distributions for sampling and show that rescaling these allows one to effectively control a `local' sampling temperature. Notably, this approach does not require any finetuning or alterations to training strategy, and can be applied to any off-the-shelf model and is compatible with both deterministic and stochastic samplers. We first validate our framework on toy 2D data, and then demonstrate its application for diffusion models trained across five disparate tasks -- image generation, pose estimation, depth prediction, robot manipulation, and protein design. We find that across these tasks, our approach allows sampling from sharper (or flatter) distributions, yielding performance gains e.g., depth prediction models benefit from sampling more likely depth estimates, whereas image generation models perform better when sampling a slightly flatter distribution. Project page: https://temporalscorerescaling.github.io

Yehonathan Litman, Fernando De la Torre, Shubham Tulsiani

Recent approaches for 3D relighting have shown promise in integrating 2D image relighting generative priors to alter the appearance of a 3D representation while preserving the underlying structure. Nevertheless, generative priors used for 2D relighting that directly relight from an input image do not take advantage of intrinsic properties of the subject that can be inferred or cannot consider multi-view data at scale, leading to subpar relighting. In this paper, we propose Lightswitch, a novel finetuned material-relighting diffusion framework that efficiently relights an arbitrary number of input images to a target lighting condition while incorporating cues from inferred intrinsic properties. By using multi-view and material information cues together with a scalable denoising scheme, our method consistently and efficiently relights dense multi-view data of objects with diverse material compositions. We show that our 2D relighting prediction quality exceeds previous state-of-the-art relighting priors that directly relight from images. We further demonstrate that LightSwitch matches or outperforms state-of-the-art diffusion inverse rendering methods in relighting synthetic and real objects in as little as 2 minutes.

Himangi Mittal, Peiye Zhuang, Hsin-Ying Lee et al.

We propose UniPhy, a common latent-conditioned neural constitutive model that can encode the physical properties of diverse materials. At inference UniPhy allows `inverse simulation' i.e. inferring material properties by optimizing the scene-specific latent to match the available observations via differentiable simulation. In contrast to existing methods that treat such inference as system identification, UniPhy does not rely on user-specified material type information. Compared to prior neural constitutive modeling approaches which learn instance specific networks, the shared training across materials improves both, robustness and accuracy of the estimates. We train UniPhy using simulated trajectories across diverse geometries and materials -- elastic, plasticine, sand, and fluids (Newtonian & non-Newtonian). At inference, given an object with unknown material properties, UniPhy can infer the material properties via latent optimization to match the motion observations, and can then allow re-simulating the object under diverse scenarios. We compare UniPhy against prior inverse simulation methods, and show that the inference from UniPhy enables more accurate replay and re-simulation under novel conditions.

Thomas Sugg, Kyle O'Brien, Lekh Poudel et al.

This paper introduces ACC-NVS1, a specialized dataset designed for research on Novel View Synthesis specifically for airborne and ground imagery. Data for ACC-NVS1 was collected in Austin, TX and Pittsburgh, PA in 2023 and 2024. The collection encompasses six diverse real-world scenes captured from both airborne and ground cameras, resulting in a total of 148,000 images. ACC-NVS1 addresses challenges such as varying altitudes and transient objects. This dataset is intended to supplement existing datasets, providing additional resources for comprehensive research, rather than serving as a benchmark.

Zihan Wang, Jiashun Wang, Jeff Tan et al.

We introduce CRISP, a method that recovers simulatable human motion and scene geometry from monocular video. Prior work on joint human-scene reconstruction relies on data-driven priors and joint optimization with no physics in the loop, or recovers noisy geometry with artifacts that cause motion tracking policies with scene interactions to fail. In contrast, our key insight is to recover convex, clean, and simulation-ready geometry by fitting planar primitives to a point cloud reconstruction of the scene, via a simple clustering pipeline over depth, normals, and flow. To reconstruct scene geometry that might be occluded during interactions, we make use of human-scene contact modeling (e.g., we use human posture to reconstruct the occluded seat of a chair). Finally, we ensure that human and scene reconstructions are physically-plausible by using them to drive a humanoid controller via reinforcement learning. Our approach reduces motion tracking failure rates from 55.2\% to 6.9\% on human-centric video benchmarks (EMDB, PROX), while delivering a 43\% faster RL simulation throughput. We further validate it on in-the-wild videos including casually-captured videos, Internet videos, and even Sora-generated videos. This demonstrates CRISP's ability to generate physically-valid human motion and interaction environments at scale, greatly advancing real-to-sim applications for robotics and AR/VR.

Yanbo Xu, Jayanth Srinivasa, Gaowen Liu et al.

Score distillation of 2D diffusion models has proven to be a powerful mechanism to guide 3D optimization, for example enabling text-based 3D generation or single-view reconstruction. A common limitation of existing score distillation formulations, however, is that the outputs of the (mode-seeking) optimization are limited in diversity despite the underlying diffusion model being capable of generating diverse samples. In this work, inspired by the sampling process in denoising diffusion, we propose a score formulation that guides the optimization to follow generation paths defined by random initial seeds, thus ensuring diversity. We then present an approximation to adopt this formulation for scenarios where the optimization may not precisely follow the generation paths (\eg a 3D representation whose renderings evolve in a co-dependent manner). We showcase the applications of our `Diverse Score Distillation' (DSD) formulation across tasks such as 2D optimization, text-based 3D inference, and single-view reconstruction. We also empirically validate DSD against prior score distillation formulations and show that it significantly improves sample diversity while preserving fidelity.

Homanga Bharadhwaj, Abhinav Gupta, Shubham Tulsiani

Motivated by the intuitive understanding humans have about the space of possible interactions, and the ease with which they can generalize this understanding to previously unseen scenes, we develop an approach for learning visual affordances for guiding robot exploration. Given an input image of a scene, we infer a distribution over plausible future states that can be achieved via interactions with it. We use a Transformer-based model to learn a conditional distribution in the latent embedding space of a VQ-VAE and show that these models can be trained using large-scale and diverse passive data, and that the learned models exhibit compositional generalization to diverse objects beyond the training distribution. We show how the trained affordance model can be used for guiding exploration by acting as a goal-sampling distribution, during visual goal-conditioned policy learning in robotic manipulation.

Amy Lin, Jason Y. Zhang, Deva Ramanan et al.

We address the task of estimating 6D camera poses from sparse-view image sets (2-8 images). This task is a vital pre-processing stage for nearly all contemporary (neural) reconstruction algorithms but remains challenging given sparse views, especially for objects with visual symmetries and texture-less surfaces. We build on the recent RelPose framework which learns a network that infers distributions over relative rotations over image pairs. We extend this approach in two key ways; first, we use attentional transformer layers to process multiple images jointly, since additional views of an object may resolve ambiguous symmetries in any given image pair (such as the handle of a mug that becomes visible in a third view). Second, we augment this network to also report camera translations by defining an appropriate coordinate system that decouples the ambiguity in rotation estimation from translation prediction. Our final system results in large improvements in 6D pose prediction over prior art on both seen and unseen object categories and also enables pose estimation and 3D reconstruction for in-the-wild objects.

Meera Hahn, Devendra Chaplot, Shubham Tulsiani et al.

Most prior methods for learning navigation policies require access to simulation environments, as they need online policy interaction and rely on ground-truth maps for rewards. However, building simulators is expensive (requires manual effort for each and every scene) and creates challenges in transferring learned policies to robotic platforms in the real-world, due to the sim-to-real domain gap. In this paper, we pose a simple question: Do we really need active interaction, ground-truth maps or even reinforcement-learning (RL) in order to solve the image-goal navigation task? We propose a self-supervised approach to learn to navigate from only passive videos of roaming. Our approach, No RL, No Simulator (NRNS), is simple and scalable, yet highly effective. NRNS outperforms RL-based formulations by a significant margin. We present NRNS as a strong baseline for any future image-based navigation tasks that use RL or Simulation.

Jason Y. Zhang, Gengshan Yang, Shubham Tulsiani et al.

Recent history has seen a tremendous growth of work exploring implicit representations of geometry and radiance, popularized through Neural Radiance Fields (NeRF). Such works are fundamentally based on a (implicit) volumetric representation of occupancy, allowing them to model diverse scene structure including translucent objects and atmospheric obscurants. But because the vast majority of real-world scenes are composed of well-defined surfaces, we introduce a surface analog of such implicit models called Neural Reflectance Surfaces (NeRS). NeRS learns a neural shape representation of a closed surface that is diffeomorphic to a sphere, guaranteeing water-tight reconstructions. Even more importantly, surface parameterizations allow NeRS to learn (neural) bidirectional surface reflectance functions (BRDFs) that factorize view-dependent appearance into environmental illumination, diffuse color (albedo), and specular "shininess." Finally, rather than illustrating our results on synthetic scenes or controlled in-the-lab capture, we assemble a novel dataset of multi-view images from online marketplaces for selling goods. Such "in-the-wild" multi-view image sets pose a number of challenges, including a small number of views with unknown/rough camera estimates. We demonstrate that surface-based neural reconstructions enable learning from such data, outperforming volumetric neural rendering-based reconstructions. We hope that NeRS serves as a first step toward building scalable, high-quality libraries of real-world shape, materials, and illumination. The project page with code and video visualizations can be found at https://jasonyzhang.com/ners.

Shubham Tulsiani, Abhinav Gupta

We propose a generative model that can infer a distribution for the underlying spatial signal conditioned on sparse samples e.g. plausible images given a few observed pixels. In contrast to sequential autoregressive generative models, our model allows conditioning on arbitrary samples and can answer distributional queries for any location. We empirically validate our approach across three image datasets and show that we learn to generate diverse and meaningful samples, with the distribution variance reducing given more observed pixels. We also show that our approach is applicable beyond images and can allow generating other types of spatial outputs e.g. polynomials, 3D shapes, and videos.

Yufei Ye, Shubham Tulsiani, Abhinav Gupta

We aim to infer 3D shape and pose of object from a single image and propose a learning-based approach that can train from unstructured image collections, supervised by only segmentation outputs from off-the-shelf recognition systems (i.e. 'shelf-supervised'). We first infer a volumetric representation in a canonical frame, along with the camera pose. We enforce the representation geometrically consistent with both appearance and masks, and also that the synthesized novel views are indistinguishable from image collections. The coarse volumetric prediction is then converted to a mesh-based representation, which is further refined in the predicted camera frame. These two steps allow both shape-pose factorization from image collections and per-instance reconstruction in finer details. We examine the method on both synthetic and real-world datasets and demonstrate its scalability on 50 categories in the wild, an order of magnitude more classes than existing works.

Kaichun Mo, Leonidas Guibas, Mustafa Mukadam et al.

One of the fundamental goals of visual perception is to allow agents to meaningfully interact with their environment. In this paper, we take a step towards that long-term goal -- we extract highly localized actionable information related to elementary actions such as pushing or pulling for articulated objects with movable parts. For example, given a drawer, our network predicts that applying a pulling force on the handle opens the drawer. We propose, discuss, and evaluate novel network architectures that given image and depth data, predict the set of actions possible at each pixel, and the regions over articulated parts that are likely to move under the force. We propose a learning-from-interaction framework with an online data sampling strategy that allows us to train the network in simulation (SAPIEN) and generalizes across categories. Check the website for code and data release: https://cs.stanford.edu/~kaichun/where2act/

Sarah Young, Dhiraj Gandhi, Shubham Tulsiani et al.

Visual imitation learning provides a framework for learning complex manipulation behaviors by leveraging human demonstrations. However, current interfaces for imitation such as kinesthetic teaching or teleoperation prohibitively restrict our ability to efficiently collect large-scale data in the wild. Obtaining such diverse demonstration data is paramount for the generalization of learned skills to novel scenarios. In this work, we present an alternate interface for imitation that simplifies the data collection process while allowing for easy transfer to robots. We use commercially available reacher-grabber assistive tools both as a data collection device and as the robot's end-effector. To extract action information from these visual demonstrations, we use off-the-shelf Structure from Motion (SfM) techniques in addition to training a finger detection network. We experimentally evaluate on two challenging tasks: non-prehensile pushing and prehensile stacking, with 1000 diverse demonstrations for each task. For both tasks, we use standard behavior cloning to learn executable policies from the previously collected offline demonstrations. To improve learning performance, we employ a variety of data augmentations and provide an extensive analysis of its effects. Finally, we demonstrate the utility of our interface by evaluating on real robotic scenarios with previously unseen objects and achieve a 87% success rate on pushing and a 62% success rate on stacking. Robot videos are available at https://dhiraj100892.github.io/Visual-Imitation-Made-Easy.

Shubham Tulsiani, Or Litany, Charles R. Qi et al.

We present an approach for aggregating a sparse set of views of an object in order to compute a semi-implicit 3D representation in the form of a volumetric feature grid. Key to our approach is an object-centric canonical 3D coordinate system into which views can be lifted, without explicit camera pose estimation, and then combined -- in a manner that can accommodate a variable number of views and is view order independent. We show that computing a symmetry-aware mapping from pixels to the canonical coordinate system allows us to better propagate information to unseen regions, as well as to robustly overcome pose ambiguities during inference. Our aggregate representation enables us to perform 3D inference tasks like volumetric reconstruction and novel view synthesis, and we use these tasks to demonstrate the benefits of our aggregation approach as compared to implicit or camera-centric alternatives.